Panduan Pembelajaran Mesin
1.0.0
Catatan: Anda dapat dengan mudah mengonversi file penurunan harga ini ke PDF di VSCode menggunakan ekstensi praktis ini Markdown PDF.
Kerangka Pembelajaran Mesin/Pembelajaran Mendalam.
Sumber Belajar untuk ML
Kerangka Kerja, Pustaka, dan Alat ML
Algoritma
Pengembangan PyTorch
Pengembangan TensorFlow
Pengembangan Inti ML
Pengembangan Pembelajaran Mendalam
Pengembangan Pembelajaran Penguatan
Pengembangan Visi Komputer
Pengembangan Pemrosesan Bahasa Alami (NLP).
Bioinformatika
Pengembangan CUDA
Pengembangan MATLAB
Pengembangan C/C++
Pembangunan Jawa
Pengembangan Python
Pengembangan Skala
Pengembangan R
Perkembangan Julia
Kembali ke Atas
Pembelajaran Mesin adalah cabang kecerdasan buatan (AI) yang berfokus pada pembuatan aplikasi menggunakan algoritme yang belajar dari model data dan meningkatkan akurasinya seiring waktu tanpa perlu diprogram.
Kembali ke Atas
Praktik Terbaik Pemrosesan Bahasa Alami (NLP) oleh Microsoft
Buku Masak Mengemudi Otonom oleh Microsoft
Azure Machine Learning - ML sebagai Layanan | Microsoft Azure
Cara menjalankan Notebook Jupyter di ruang kerja Azure Machine Learning Anda
Pembelajaran Mesin dan Kecerdasan Buatan | Layanan Web Amazon
Menjadwalkan notebook Jupyter pada instans sementara Amazon SageMaker
AI & Pembelajaran Mesin | Google Awan
Menggunakan Notebook Jupyter dengan Apache Spark di Google Cloud
Pembelajaran Mesin | Pengembang Apple
Kecerdasan Buatan & Autopilot | Tesla
Alat Meta AI | Facebook
Tutorial PyTorch
Tutorial TensorFlow
Lab Jupyter
Difusi Stabil dengan Core ML di Apple Silicon
Kembali ke Atas
Pembelajaran Mesin oleh Universitas Stanford oleh Andrew Ng | Kursus
Pelatihan dan Sertifikasi AWS untuk Kursus Machine Learning (ML).
Program Beasiswa Pembelajaran Mesin untuk Microsoft Azure | kota Uda
Bersertifikat Microsoft: Rekan Ilmuwan Data Azure
Bersertifikat Microsoft: Rekan Insinyur AI Azure
Pelatihan dan penerapan Azure Machine Learning
Pembelajaran Machine learning dan kecerdasan buatan dari Google Cloud Training
Kursus Singkat Machine Learning untuk Google Cloud
Kursus Pembelajaran Mesin Online | Udemy
Kursus Pembelajaran Mesin Online | Kursus
Pelajari Pembelajaran Mesin dengan Kursus dan Kelas Online | edX
Kembali ke Atas
Pengantar Pembelajaran Mesin (PDF)
Kecerdasan Buatan: Pendekatan Modern oleh Stuart J. Russel dan Peter Norvig
Pembelajaran Mendalam oleh Ian Goodfellow, Yoshoua Bengio, dan Aaron Courville
Buku Pembelajaran Mesin Seratus Halaman oleh Andriy Burkov
Pembelajaran Mesin oleh Tom M. Mitchell
Pemrograman Kecerdasan Kolektif: Membangun Aplikasi Smart Web 2.0 oleh Toby Segaran
Pembelajaran Mesin: Perspektif Algoritma, Edisi Kedua
Pengenalan Pola dan Pembelajaran Mesin oleh Christopher M. Bishop
Pemrosesan Bahasa Alami dengan Python oleh Steven Bird, Ewan Klein, dan Edward Loper
Pembelajaran Mesin Python: Pendekatan Teknis Pembelajaran Mesin untuk Pemula oleh Leonard Eddison
Penalaran Bayesian dan Pembelajaran Mesin oleh David Barber
Pembelajaran Mesin untuk Pemula Mutlak: Pengantar Bahasa Inggris yang Sederhana oleh Oliver Theobald
Pembelajaran Mesin dalam Aksi oleh Ben Wilson
Pembelajaran Mesin Praktis dengan Scikit-Learn, Keras, dan TensorFlow: Konsep, Alat, dan Teknik untuk Membangun Sistem Cerdas oleh Aurélien Géron
Pengantar Pembelajaran Mesin dengan Python: Panduan untuk Ilmuwan Data oleh Andreas C. Müller & Sarah Guido
Pembelajaran Mesin untuk Peretas: Studi Kasus dan Algoritma untuk Membantu Anda Memulai oleh Drew Conway dan John Myles White
Elemen Pembelajaran Statistik: Penambangan Data, Inferensi, dan Prediksi oleh Trevor Hastie, Robert Tibshirani, dan Jerome Friedman
Pola Pembelajaran Mesin Terdistribusi - Buku (gratis untuk dibaca online) + Kode
Pembelajaran Mesin Dunia Nyata [Bab Gratis]
Pengantar Pembelajaran Statistik - Buku + Kode R
Elemen Pembelajaran Statistik - Buku
Pikirkan Bayes - Buku + Kode Python
Menambang Kumpulan Data Besar-besaran
Pertemuan Pertama dengan Pembelajaran Mesin
Pengantar Pembelajaran Mesin - Alex Smola dan SVN Vishwanathan
Teori Pengenalan Pola Probabilistik
Pengantar Pengambilan Informasi
Peramalan: prinsip dan praktik
Pengantar Pembelajaran Mesin - Amnon Shashua
Pembelajaran Penguatan
Pembelajaran Mesin
Sebuah Pencarian untuk AI
Pemrograman R untuk Ilmu Data
Penambangan Data - Alat dan Teknik Pembelajaran Mesin Praktis
Pembelajaran Mesin dengan TensorFlow
Sistem Pembelajaran Mesin
Dasar-dasar Pembelajaran Mesin - Mehryar Mohri, Afshin Rostamizadeh, dan Ameet Talwalkar
Pencarian Bertenaga AI - Trey Grainger, Doug Turnbull, Max Irwin -
Metode Ensemble untuk Pembelajaran Mesin - Gautam Kunapuli
Aksi Rekayasa Pembelajaran Mesin - Ben Wilson
Pembelajaran Mesin yang Menjaga Privasi - J. Morris Chang, Di Zhuang, G. Dumindu Samaraweera
Pembelajaran Mesin Otomatis sedang Beraksi - Qingquan Song, Haifeng Jin, dan Xia Hu
Pola Pembelajaran Mesin Terdistribusi - Yuan Tang
Mengelola Proyek Pembelajaran Mesin: Dari desain hingga penerapan - Simon Thompson
Pembelajaran Mesin Kausal - Robert Ness
Optimasi Bayesian dalam Aksi - Quan Nguyen
Algoritma Pembelajaran Mesin Secara Mendalam) - Vadim Smolyakov
Algoritma Optimasi - Alaa Khamis
Peningkatan Gradien Praktis oleh Guillaume Saupin
Kembali ke Atas
Kembali ke Atas
TensorFlow adalah platform sumber terbuka menyeluruh untuk pembelajaran mesin. Ini memiliki ekosistem alat, perpustakaan, dan sumber daya komunitas yang komprehensif dan fleksibel yang memungkinkan peneliti mendorong teknologi tercanggih dalam ML dan pengembang dengan mudah membangun dan menerapkan aplikasi yang didukung ML.
Keras adalah API jaringan saraf tingkat tinggi, ditulis dengan Python dan mampu berjalan di atas TensorFlow, CNTK, atau Theano. Keras dikembangkan dengan fokus untuk memungkinkan eksperimen cepat. Itu mampu berjalan di atas TensorFlow, Microsoft Cognitive Toolkit, R, Theano, atau PlaidML.
PyTorch adalah perpustakaan untuk pembelajaran mendalam tentang data masukan tidak beraturan seperti grafik, point cloud, dan manifold. Terutama dikembangkan oleh laboratorium Penelitian AI Facebook.
Amazon SageMaker adalah layanan terkelola sepenuhnya yang memberikan setiap pengembang dan ilmuwan data kemampuan untuk membangun, melatih, dan menerapkan model pembelajaran mesin (ML) dengan cepat. SageMaker menghilangkan beban berat dari setiap langkah proses pembelajaran mesin untuk mempermudah pengembangan model berkualitas tinggi.
Azure Databricks adalah layanan analisis data besar berbasis Apache Spark yang cepat dan kolaboratif yang dirancang untuk ilmu data dan rekayasa data. Azure Databricks, siapkan lingkungan Apache Spark Anda dalam hitungan menit, skala otomatis, dan berkolaborasi pada proyek bersama di ruang kerja interaktif. Azure Databricks mendukung Python, Scala, R, Java, dan SQL, serta kerangka kerja dan pustaka ilmu data termasuk TensorFlow, PyTorch, dan scikit-learn.
Microsoft Cognitive Toolkit (CNTK) adalah toolkit sumber terbuka untuk pembelajaran mendalam terdistribusi tingkat komersial. Ini menggambarkan jaringan saraf sebagai serangkaian langkah komputasi melalui grafik terarah. CNTK memungkinkan pengguna dengan mudah mewujudkan dan menggabungkan jenis model populer seperti DNN feed-forward, jaringan saraf konvolusional (CNN), dan jaringan saraf berulang (RNN/LSTM). CNTK mengimplementasikan pembelajaran penurunan gradien stokastik (SGD, error backpropagation) dengan diferensiasi dan paralelisasi otomatis di beberapa GPU dan server.
Apple CoreML adalah kerangka kerja yang membantu mengintegrasikan model pembelajaran mesin ke dalam aplikasi Anda. Core ML memberikan representasi terpadu untuk semua model. Aplikasi Anda menggunakan API Core ML dan data pengguna untuk membuat prediksi, dan untuk melatih atau menyempurnakan model, semuanya di perangkat pengguna. Model adalah hasil penerapan algoritma pembelajaran mesin pada sekumpulan data pelatihan. Anda menggunakan model untuk membuat prediksi berdasarkan data masukan baru.
Apache OpenNLP adalah pustaka sumber terbuka untuk perangkat berbasis pembelajaran mesin yang digunakan dalam pemrosesan teks bahasa alami. Ini menampilkan API untuk kasus penggunaan seperti Pengenalan Entitas Bernama, Deteksi Kalimat, penandaan POS (Part-Of-Speech), ekstraksi Fitur Tokenisasi, Chunking, Parsing, dan resolusi Coreference.
Apache Airflow adalah platform manajemen alur kerja sumber terbuka yang dibuat oleh komunitas untuk menulis, menjadwalkan, dan memantau alur kerja secara terprogram. Memasang. Prinsip. Dapat diskalakan. Airflow memiliki arsitektur modular dan menggunakan antrian pesan untuk mengatur sejumlah pekerja. Aliran udara siap untuk ditingkatkan hingga tak terbatas.
Open Neural Network Exchange (ONNX) adalah ekosistem terbuka yang memberdayakan pengembang AI untuk memilih alat yang tepat seiring berkembangnya proyek mereka. ONNX menyediakan format sumber terbuka untuk model AI, baik pembelajaran mendalam maupun ML tradisional. Ini mendefinisikan model grafik komputasi yang dapat diperluas, serta definisi operator bawaan dan tipe data standar.
Apache MXNet adalah kerangka pembelajaran mendalam yang dirancang untuk efisiensi dan fleksibilitas. Hal ini memungkinkan Anda untuk menggabungkan pemrograman simbolik dan imperatif untuk memaksimalkan efisiensi dan produktivitas. Pada intinya, MXNet berisi penjadwal ketergantungan dinamis yang secara otomatis memparalelkan operasi simbolik dan imperatif dengan cepat. Lapisan pengoptimalan grafik di atasnya membuat eksekusi simbolik menjadi cepat dan hemat memori. MXNet bersifat portabel dan ringan, dapat diskalakan secara efektif ke beberapa GPU dan beberapa mesin. Dukungan untuk Python, R, Julia, Scala, Go, Javascript, dan lainnya.
AutoGluon adalah perangkat untuk Pembelajaran mendalam yang mengotomatiskan tugas pembelajaran mesin sehingga Anda dapat dengan mudah mencapai kinerja prediktif yang kuat dalam aplikasi Anda. Hanya dengan beberapa baris kode, Anda dapat melatih dan menerapkan model pembelajaran mendalam dengan akurasi tinggi pada data tabel, gambar, dan teks.
Anaconda adalah platform Ilmu Data yang sangat populer untuk pembelajaran mesin dan pembelajaran mendalam yang memungkinkan pengguna mengembangkan model, melatihnya, dan menerapkannya.
PlaidML adalah kompiler tensor canggih dan portabel untuk mengaktifkan pembelajaran mendalam pada laptop, perangkat tertanam, atau perangkat lain yang perangkat keras komputasinya tidak didukung dengan baik atau tumpukan perangkat lunak yang tersedia berisi batasan lisensi yang tidak menyenangkan.
OpenCV adalah perpustakaan yang sangat optimal dengan fokus pada aplikasi visi komputer waktu nyata. Antarmuka C++, Python, dan Java mendukung Linux, MacOS, Windows, iOS, dan Android.
Scikit-Learn adalah modul Python untuk pembelajaran mesin yang dibangun di atas SciPy, NumPy, dan matplotlib, sehingga memudahkan penerapan implementasi yang kuat dan sederhana dari banyak algoritma pembelajaran mesin populer.
Weka adalah perangkat lunak pembelajaran mesin sumber terbuka yang dapat diakses melalui antarmuka pengguna grafis, aplikasi terminal standar, atau Java API. Ini banyak digunakan untuk pengajaran, penelitian, dan aplikasi industri, berisi banyak alat bawaan untuk tugas pembelajaran mesin standar, dan juga memberikan akses transparan ke kotak peralatan terkenal seperti scikit-learn, R, dan Deeplearning4j.
Caffe adalah kerangka pembelajaran mendalam yang dibuat dengan mempertimbangkan ekspresi, kecepatan, dan modularitas. Ini dikembangkan oleh Berkeley AI Research (BAIR)/The Berkeley Vision and Learning Center (BVLC) dan kontributor komunitas.
Theano adalah pustaka Python yang memungkinkan Anda mendefinisikan, mengoptimalkan, dan mengevaluasi ekspresi matematika yang melibatkan array multidimensi secara efisien termasuk integrasi erat dengan NumPy.
nGraph adalah pustaka C++ open source, compiler dan runtime untuk Deep Learning. nGraph Compiler bertujuan untuk mempercepat pengembangan beban kerja AI menggunakan kerangka pembelajaran mendalam apa pun dan menerapkannya ke berbagai target perangkat keras. Ini memberikan kebebasan, kinerja, dan kemudahan penggunaan bagi pengembang AI.
NVIDIA cuDNN adalah pustaka primitif yang dipercepat GPU untuk jaringan neural dalam. cuDNN menyediakan implementasi yang sangat disesuaikan untuk rutinitas standar seperti konvolusi maju dan mundur, pengumpulan, normalisasi, dan lapisan aktivasi. cuDNN mempercepat framework deep learning yang banyak digunakan, termasuk Caffe2, Chainer, Keras, MATLAB, MxNet, PyTorch, dan TensorFlow.
Huginn adalah sistem yang dihosting sendiri untuk agen bangunan yang melakukan tugas otomatis untuk Anda secara online. Itu dapat membaca web, menonton acara, dan mengambil tindakan atas nama Anda. Agen Huginn membuat dan menggunakan peristiwa, menyebarkannya sepanjang grafik terarah. Anggap saja sebagai versi IFTTT atau Zapier yang dapat diretas di server Anda sendiri.
Netron adalah penampil model jaringan saraf, pembelajaran mendalam, dan pembelajaran mesin. Mendukung ONNX, TensorFlow Lite, Caffe, Keras, Darknet, PaddlePaddle, ncnn, MNN, Core ML, RKNN, MXNet, MindSpore Lite, TNN, Barracuda, Tengine, CNTK, TensorFlow.js, Caffe2 dan UFF.
Dopamin adalah kerangka penelitian untuk pembuatan prototipe cepat algoritma pembelajaran penguatan.
DALI adalah perpustakaan dengan akselerasi GPU yang berisi blok penyusun yang sangat optimal dan mesin eksekusi untuk pemrosesan data guna mempercepat pelatihan pembelajaran mendalam dan aplikasi inferensi.
MindSpore Lite adalah kerangka pelatihan/inferensi pembelajaran mendalam open source baru yang dapat digunakan untuk skenario seluler, edge, dan cloud.
Darknet adalah kerangka jaringan saraf sumber terbuka yang ditulis dalam C dan CUDA. Ini cepat, mudah dipasang, dan mendukung komputasi CPU dan GPU.
PaddlePaddle adalah platform pembelajaran mendalam yang mudah digunakan, efisien, fleksibel, dan terukur, yang awalnya dikembangkan oleh para ilmuwan dan insinyur Baidu dengan tujuan menerapkan pembelajaran mendalam pada banyak produk di Baidu.
GoogleNotebookLM adalah alat AI eksperimental yang menggunakan kekuatan model bahasa yang dipasangkan dengan konten Anda yang ada untuk mendapatkan wawasan penting dengan lebih cepat. Mirip dengan asisten peneliti virtual yang dapat merangkum fakta, menjelaskan ide-ide kompleks, dan bertukar pikiran tentang koneksi baru berdasarkan sumber yang Anda pilih.
Unilm adalah Pra-pelatihan Lintas Tugas, Bahasa, dan Modalitas yang diawasi sendiri dan berskala besar.
Kernel Semantik (SK) adalah SDK ringan yang memungkinkan integrasi AI Model Bahasa Besar (LLM) dengan bahasa pemrograman konvensional. Model pemrograman SK yang dapat diperluas menggabungkan fungsi semantik bahasa alami, fungsi asli kode tradisional, dan memori berbasis embeddings yang membuka potensi baru dan menambah nilai pada aplikasi dengan AI.
Pandas AI adalah pustaka Python yang mengintegrasikan kemampuan kecerdasan buatan generatif ke dalam Pandas, menjadikan kerangka data bersifat komunikatif.
NCNN adalah kerangka inferensi jaringan saraf berkinerja tinggi yang dioptimalkan untuk platform seluler.
MNN adalah kerangka pembelajaran mendalam yang sangat cepat dan ringan, yang telah teruji dalam kasus penggunaan bisnis penting di Alibaba.
MediaPipe dioptimalkan untuk kinerja ujung ke ujung pada beragam platform. Lihat demo Pelajari lebih lanjut ML di perangkat yang rumit, disederhanakan Kami telah mengabstraksi kompleksitas dalam membuat ML di perangkat dapat disesuaikan, siap produksi, dan dapat diakses di seluruh platform.
MegEngine adalah kerangka pembelajaran mendalam yang cepat, terukur, dan ramah pengguna dengan 3 fitur utama: Kerangka kerja terpadu untuk pelatihan dan inferensi.
ML.NET adalah pustaka pembelajaran mesin yang dirancang sebagai platform yang dapat diperluas sehingga Anda dapat menggunakan kerangka kerja ML populer lainnya (TensorFlow, ONNX, Infer.NET, dan lainnya) dan memiliki akses ke lebih banyak skenario pembelajaran mesin, seperti klasifikasi gambar, deteksi objek, dan banyak lagi.
Ludwig adalah kerangka kerja pembelajaran mesin deklaratif yang memudahkan penentuan alur pembelajaran mesin menggunakan sistem konfigurasi berbasis data yang sederhana dan fleksibel.
MMdnn adalah alat yang komprehensif dan lintas kerangka untuk mengonversi, memvisualisasikan, dan mendiagnosis model pembelajaran mendalam (DL). "MM" adalah singkatan dari manajemen model, dan "dnn" adalah akronim dari jaringan saraf dalam. Konversi model antara Caffe, Keras, MXNet, Tensorflow, CNTK, PyTorch Onnx, dan CoreML.
Horovod adalah kerangka pelatihan pembelajaran mendalam terdistribusi untuk TensorFlow, Keras, PyTorch, dan Apache MXNet.
Vaex adalah pustaka Python berkinerja tinggi untuk DataFrame Out-of-Core yang lambat (mirip dengan Pandas), untuk memvisualisasikan dan menjelajahi kumpulan data tabel besar.
GluonTS adalah paket Python untuk pemodelan deret waktu probabilistik, dengan fokus pada model berbasis pembelajaran mendalam, berdasarkan PyTorch dan MXNet.
MindsDB adalah Server ML-SQL yang memungkinkan alur kerja pembelajaran mesin untuk database dan gudang data paling kuat menggunakan SQL.
Jupyter Notebook adalah aplikasi web sumber terbuka yang memungkinkan Anda membuat dan berbagi dokumen yang berisi kode langsung, persamaan, visualisasi, dan teks naratif. Jupyter digunakan secara luas di industri yang melakukan pembersihan dan transformasi data, simulasi numerik, pemodelan statistik, visualisasi data, ilmu data, dan pembelajaran mesin.
Apache Spark adalah mesin analitik terpadu untuk pemrosesan data skala besar. Ini menyediakan API tingkat tinggi dalam Scala, Java, Python, dan R, dan mesin yang dioptimalkan yang mendukung grafik komputasi umum untuk analisis data. Ini juga mendukung serangkaian alat tingkat tinggi termasuk Spark SQL untuk SQL dan DataFrames, MLlib untuk pembelajaran mesin, GraphX untuk pemrosesan grafik, dan Streaming Terstruktur untuk pemrosesan aliran.
Konektor Apache Spark untuk SQL Server dan Azure SQL adalah konektor berkinerja tinggi yang memungkinkan Anda menggunakan data transaksional dalam analisis data besar dan mempertahankan hasil untuk kueri atau pelaporan ad-hoc. Konektor ini memungkinkan Anda menggunakan database SQL apa pun, lokal atau di cloud, sebagai sumber data input atau sink data output untuk pekerjaan Spark.
Apache PredictionIO adalah kerangka pembelajaran mesin sumber terbuka untuk pengembang, ilmuwan data, dan pengguna akhir. Ini mendukung pengumpulan peristiwa, penerapan algoritme, evaluasi, menanyakan hasil prediktif melalui REST API. Hal ini didasarkan pada layanan sumber terbuka yang dapat diskalakan seperti Hadoop, HBase (dan DB lainnya), Elasticsearch, Spark dan mengimplementasikan apa yang disebut Arsitektur Lambda.
Cluster Manager untuk Apache Kafka (CMAK) adalah alat untuk mengelola cluster Apache Kafka.
BigDL adalah perpustakaan pembelajaran mendalam yang didistribusikan untuk Apache Spark. Dengan BigDL, pengguna dapat menulis aplikasi pembelajaran mendalam mereka sebagai program Spark standar, yang dapat langsung dijalankan di atas klaster Spark atau Hadoop yang ada.
Eclipse Deeplearning4J (DL4J) adalah serangkaian proyek yang dimaksudkan untuk mendukung semua kebutuhan aplikasi pembelajaran mendalam berbasis JVM (Scala, Kotlin, Clojure, dan Groovy). Ini berarti memulai dengan data mentah, memuat dan memprosesnya terlebih dahulu dari mana saja dan dalam format apa pun, hingga membangun dan menyempurnakan beragam jaringan pembelajaran mendalam yang sederhana dan kompleks.
Tensorman adalah utilitas untuk memudahkan pengelolaan kontainer Tensorflow yang dikembangkan oleh System76. Tensorman memungkinkan Tensorflow beroperasi di lingkungan terisolasi yang terkandung dari seluruh sistem. Lingkungan virtual ini dapat beroperasi secara independen dari sistem dasar, sehingga Anda dapat menggunakan versi Tensorflow apa pun pada versi distribusi Linux apa pun yang mendukung runtime Docker.
Numba adalah kompiler pengoptimalan NumPy-aware open source untuk Python yang disponsori oleh Anaconda, Inc. Numba menggunakan proyek kompiler LLVM untuk menghasilkan kode mesin dari sintaksis Python. Numba dapat mengkompilasi sebagian besar Python yang berfokus pada numerik, termasuk banyak fungsi NumPy. Selain itu, Numba memiliki dukungan untuk paralelisasi loop otomatis, pembuatan kode yang dipercepat GPU, dan pembuatan panggilan balik ufuncs dan C.
Chainer adalah kerangka pembelajaran mendalam berbasis Python yang bertujuan untuk fleksibilitas. Ini menyediakan API diferensiasi otomatis berdasarkan pendekatan definisikan demi proses (grafik komputasi dinamis) serta API tingkat tinggi berorientasi objek untuk membangun dan melatih jaringan saraf. Ini juga mendukung CUDA/cuDNN menggunakan CuPy untuk pelatihan dan inferensi kinerja tinggi.
XGBoost adalah pustaka peningkat gradien terdistribusi yang dioptimalkan dan dirancang agar sangat efisien, fleksibel, dan portabel. Ini mengimplementasikan algoritma pembelajaran mesin di bawah kerangka Gradient Boosting. XGBoost menyediakan peningkatan pohon paralel (juga dikenal sebagai GBDT, GBM) yang memecahkan banyak masalah ilmu data dengan cara yang cepat dan akurat. Ini mendukung pelatihan terdistribusi di beberapa mesin, termasuk klaster AWS, GCE, Azure, dan Yarn. Selain itu, dapat diintegrasikan dengan Flink, Spark, dan sistem aliran data cloud lainnya.
cuML adalah rangkaian perpustakaan yang mengimplementasikan algoritma pembelajaran mesin dan fungsi primitif matematika yang berbagi API yang kompatibel dengan proyek RAPIDS lainnya. cuML memungkinkan ilmuwan data, peneliti, dan insinyur perangkat lunak menjalankan tugas ML tabular tradisional pada GPU tanpa mempelajari detail pemrograman CUDA. Dalam kebanyakan kasus, API Python cuML cocok dengan API dari scikit-learn.
Emu adalah perpustakaan GPGPU untuk Rust dengan fokus pada portabilitas, modularitas, dan kinerja. Ini adalah abstraksi komputasi khusus mirip CUDA melalui WebGPU yang menyediakan fungsionalitas khusus untuk membuat WebGPU terasa lebih seperti CUDA.
Scalene adalah profiler CPU, GPU, dan memori berkinerja tinggi untuk Python yang melakukan sejumlah hal yang tidak dan tidak dapat dilakukan oleh profiler Python lainnya. Ini berjalan jauh lebih cepat daripada banyak profiler lainnya sambil memberikan informasi yang jauh lebih rinci.
MLpack adalah pustaka pembelajaran mesin C++ yang cepat dan fleksibel yang ditulis dalam C++ dan dibangun di atas pustaka aljabar linier Armadillo, pustaka pengoptimalan numerik yang diperkecil, dan bagian dari Boost.
Netron adalah penampil model jaringan saraf, pembelajaran mendalam, dan pembelajaran mesin. Mendukung ONNX, TensorFlow Lite, Caffe, Keras, Darknet, PaddlePaddle, ncnn, MNN, Core ML, RKNN, MXNet, MindSpore Lite, TNN, Barracuda, Tengine, CNTK, TensorFlow.js, Caffe2 dan UFF.
Lightning adalah alat yang membuat dan melatih model PyTorch dan menghubungkannya ke siklus hidup ML menggunakan template Aplikasi Lightning, tanpa menangani infrastruktur DIY, manajemen biaya, penskalaan, dll.
OpenNN adalah perpustakaan jaringan saraf sumber terbuka untuk pembelajaran mesin. Ini berisi algoritma dan utilitas canggih untuk menangani banyak solusi kecerdasan buatan.
H20 adalah platform AI Cloud yang memecahkan masalah bisnis yang kompleks dan mempercepat penemuan ide-ide baru dengan hasil yang dapat Anda pahami dan percayai.
Gensim adalah perpustakaan Python untuk pemodelan topik, pengindeksan dokumen, dan pengambilan kesamaan dengan corpora besar. Target audiensnya adalah komunitas pemrosesan bahasa alami (NLP) dan pengambilan informasi (IR).
llama.cpp adalah Port model LLaMA Facebook di C/C++.
hmmlearn adalah sekumpulan algoritme untuk pembelajaran tanpa pengawasan dan inferensi Model Markov Tersembunyi.
Nextjournal adalah buku catatan untuk penelitian yang dapat direproduksi. Ini menjalankan apa pun yang dapat Anda masukkan ke dalam wadah Docker. Tingkatkan alur kerja Anda dengan buku catatan poliglot, pembuatan versi otomatis, dan kolaborasi waktu nyata. Hemat waktu dan uang dengan penyediaan on-demand, termasuk dukungan GPU.
IPython menyediakan arsitektur yang kaya untuk komputasi interaktif dengan:
Veles adalah platform terdistribusi untuk pengembangan aplikasi pembelajaran mendalam yang cepat yang saat ini dikembangkan oleh Samsung.
DyNet adalah perpustakaan jaringan saraf yang dikembangkan oleh Universitas Carnegie Mellon dan banyak lainnya. Itu ditulis dalam C++ (dengan pengikatan dalam Python) dan dirancang agar efisien ketika dijalankan pada CPU atau GPU, dan untuk bekerja dengan baik dengan jaringan yang memiliki struktur dinamis yang berubah untuk setiap contoh pelatihan. Jaringan semacam ini sangat penting dalam tugas pemrosesan bahasa alami, dan DyNet telah digunakan untuk membangun sistem canggih untuk penguraian sintaksis, terjemahan mesin, infleksi morfologi, dan banyak area aplikasi lainnya.
Ray adalah kerangka kerja terpadu untuk menskalakan aplikasi AI dan Python. Ini terdiri dari runtime inti yang terdistribusi dan toolkit perpustakaan (Ray AIR) untuk mempercepat beban kerja ML.
Whisper.cpp adalah inferensi performa tinggi dari model pengenalan ucapan otomatis (ASR) Whisper OpenAI.
ChatGPT Plus adalah paket berlangganan percontohan ( $20/bulan ) untuk ChatGPT, AI percakapan yang dapat mengobrol dengan Anda, menjawab pertanyaan lanjutan, dan menantang asumsi yang salah.
Auto-GPT adalah "agen AI" yang memiliki tujuan dalam bahasa alami, dapat berupaya mencapainya dengan memecahnya menjadi beberapa subtugas dan menggunakan internet serta alat lainnya dalam putaran otomatis. Aplikasi ini menggunakan API GPT-4 atau GPT-3.5 OpenAI, dan merupakan salah satu contoh pertama aplikasi yang menggunakan GPT-4 untuk melakukan tugas otonom.
Chatbot UI oleh mckaywrigley adalah kit chatbot tingkat lanjut untuk model obrolan OpenAI yang dibangun di atas Chatbot UI Lite menggunakan Next.js, TypeScript, dan Tailwind CSS. Versi ChatBot UI ini mendukung model GPT-3.5 dan GPT-4. Percakapan disimpan secara lokal di dalam browser Anda. Anda dapat mengekspor dan mengimpor percakapan untuk melindungi dari kehilangan data. Lihat demonya.
Chatbot UI Lite oleh mckaywrigley adalah starter kit chatbot sederhana untuk model obrolan OpenAI menggunakan Next.js, TypeScript, dan Tailwind CSS. Lihat demonya.
MiniGPT-4 adalah Peningkatan Pemahaman Bahasa Vision dengan Model Bahasa Besar Tingkat Lanjut.
GPT4All adalah ekosistem chatbot sumber terbuka yang dilatih tentang kumpulan besar data asisten yang bersih termasuk kode, cerita, dan dialog berdasarkan LLaMa.
GPT4All UI adalah aplikasi web Flask yang menyediakan UI chat untuk berinteraksi dengan chatbot GPT4All.
Alpaca.cpp adalah model mirip ChatGPT yang cepat secara lokal di perangkat Anda. Ini menggabungkan model dasar LLaMA dengan reproduksi terbuka Stanford Alpaca, penyempurnaan model dasar untuk mematuhi instruksi (mirip dengan RLHF yang digunakan untuk melatih ChatGPT) dan serangkaian modifikasi pada llama.cpp untuk menambahkan antarmuka obrolan.
llama.cpp adalah Port model LLaMA Facebook di C/C++.
OpenPlayground adalah tempat bermain untuk menjalankan model mirip ChatGPT secara lokal di perangkat Anda.
Vicuna adalah chatbot sumber terbuka yang dilatih dengan menyempurnakan LLaMA. Tampaknya mencapai lebih dari 90% kualitas chatgpt dan biaya pelatihan $300.
Yeagar ai adalah pembuat Agen Langchain yang dirancang untuk membantu Anda membangun, membuat prototipe, dan menerapkan agen bertenaga AI dengan mudah.
Vicuna dibuat dengan menyempurnakan model dasar LLaMA menggunakan sekitar 70 ribu percakapan bersama pengguna yang dikumpulkan dari ShareGPT.com dengan API publik. Untuk memastikan kualitas data, ini mengubah HTML kembali ke penurunan harga dan memfilter beberapa sampel yang tidak pantas atau berkualitas rendah.
ShareGPT adalah tempat untuk berbagi percakapan ChatGPT terliar Anda dengan satu klik. Dengan 198.404 percakapan yang dibagikan sejauh ini.
FastChat adalah platform terbuka untuk melatih, melayani, dan mengevaluasi chatbot berbasis model bahasa besar.
Haystack adalah kerangka kerja NLP sumber terbuka untuk berinteraksi dengan data Anda menggunakan model Transformer dan LLM (GPT-4, ChatGPT, dan sejenisnya). Ini menawarkan alat siap produksi untuk dengan cepat membangun pengambilan keputusan yang kompleks, menjawab pertanyaan, pencarian semantik, aplikasi pembuatan teks, dan banyak lagi.
StableLM (Stability AI Language Models) adalah rangkaian model bahasa StableLM dan akan terus diperbarui dengan pos pemeriksaan baru.
Dolly Databricks adalah model bahasa besar yang mengikuti instruksi yang dilatih pada platform pembelajaran mesin Databricks yang dilisensikan untuk penggunaan komersial.
GPTCach adalah Perpustakaan untuk Membuat Cache Semantik untuk Kueri LLM.
AlaC adalah Generator Infrastruktur sebagai Kode Kecerdasan Buatan.
Adrenalin adalah alat yang memungkinkan Anda berbicara dengan basis kode Anda. Ini didukung oleh analisis statis, pencarian vektor, dan model bahasa besar.
OpenAssistant adalah asisten berbasis obrolan yang memahami tugas, dapat berinteraksi dengan sistem pihak ketiga, dan mengambil informasi secara dinamis untuk melakukannya.
DoctorGPT adalah biner mandiri ringan yang memantau log aplikasi Anda untuk mencari masalah dan mendiagnosisnya.
HttpGPT adalah plugin Unreal Engine 5 yang memfasilitasi integrasi dengan layanan berbasis GPT OpenAI (ChatGPT dan DALL-E) melalui permintaan REST asinkron, sehingga memudahkan pengembang untuk berkomunikasi dengan layanan ini. Ini juga mencakup Alat Editor untuk mengintegrasikan pembuatan gambar Chat GPT dan DALL-E langsung di Mesin.
PaLM 2 adalah model bahasa besar generasi berikutnya yang dibangun berdasarkan penelitian terobosan Google dalam pembelajaran mesin dan AI yang bertanggung jawab. Ini mencakup tugas penalaran tingkat lanjut, termasuk kode dan matematika, klasifikasi dan menjawab pertanyaan, terjemahan dan kemahiran multibahasa, dan pembuatan bahasa alami yang lebih baik daripada LLM kami yang canggih sebelumnya.
Med-PaLM adalah model bahasa besar (LLM) yang dirancang untuk memberikan jawaban berkualitas tinggi atas pertanyaan medis. Hal ini memanfaatkan kekuatan model bahasa besar Google, yang telah kami selaraskan dengan domain medis melalui serangkaian demonstrasi pakar medis yang dikurasi dengan cermat.
Sec-PaLM adalah model bahasa besar (LLM), yang mempercepat kemampuan untuk membantu orang-orang yang bertanggung jawab menjaga keamanan organisasi mereka. Model-model baru ini tidak hanya memberi masyarakat cara yang lebih alami dan kreatif untuk memahami dan mengelola keamanan.
Kembali ke Atas
Kembali ke Atas
Kembali ke atas
Localai adalah API Openai-Compatible yang disembunyikan oleh masyarakat, yang digerakkan oleh masyarakat. Penggantian drop-in untuk OpenAi menjalankan LLMS pada perangkat keras kelas konsumen tanpa diperlukan GPU. Ini adalah API untuk menjalankan model yang kompatibel dengan GGML: llama, gpt4all, rwkv, wisper, vicuna, koala, gpt4all-j, cerebras, falcon, dolly, starcoder, dan banyak lainnya.
llama.cpp adalah port model Llama Facebook di C/C ++.
Ollama adalah alat untuk bangun dan berjalan dengan Llama 2 dan model bahasa besar lainnya secara lokal.
Localai adalah API Openai-Compatible yang disembunyikan oleh masyarakat, yang digerakkan oleh masyarakat. Penggantian drop-in untuk OpenAi menjalankan LLMS pada perangkat keras kelas konsumen tanpa diperlukan GPU. Ini adalah API untuk menjalankan model yang kompatibel dengan GGML: llama, gpt4all, rwkv, wisper, vicuna, koala, gpt4all-j, cerebras, falcon, dolly, starcoder, dan banyak lainnya.
Serge adalah antarmuka web untuk mengobrol dengan Alpaca melalui llama.cpp. Sepenuhnya diselenggarakan sendiri & berlabuh, dengan API yang mudah digunakan.
OpenLLM adalah platform terbuka untuk mengoperasikan model bahasa besar (LLM) dalam produksi. Menyaring, melayani, menggunakan, dan memantau LLM dengan mudah.
Llama-GPT adalah chatbot yang diselenggarakan sendiri, offline, seperti chatgpt. Didukung oleh Llama 2. 100% Pribadi, tanpa data meninggalkan perangkat Anda.
LLAMA2 WEBUI adalah alat untuk menjalankan Llama 2 secara lokal dengan Gradio UI di GPU atau CPU dari mana saja (Linux/Windows/Mac). Gunakan llama2-wrapper sebagai backend llama2 lokal Anda untuk agen/aplikasi generatif.
LLAMA2.C adalah alat untuk melatih arsitektur LLAMA 2 LLM di Pytorch kemudian menyimpulkannya dengan satu file C 700 baris sederhana (Run.c).
Alpaca.cpp adalah model chatgpt yang cepat secara lokal di perangkat Anda. Ini menggabungkan model Llama Foundation dengan reproduksi terbuka Stanford Alpaca, penyesuaian model dasar untuk mematuhi instruksi (mirip dengan RLHF yang digunakan untuk melatih chatgpt) dan serangkaian modifikasi ke llama.cpp untuk menambahkan antarmuka obrolan.
GPT4ALL adalah ekosistem chatbots open-source yang dilatih pada koleksi besar data asisten bersih termasuk kode, cerita, dan dialog berdasarkan Llama.
Minigpt-4 adalah pemahaman penglihatan-penglihatan yang meningkatkan dengan model bahasa besar canggih
Lollms WebUi adalah hub untuk model LLM (model bahasa besar). Ini bertujuan untuk menyediakan antarmuka yang ramah pengguna untuk mengakses dan memanfaatkan berbagai model LLM untuk berbagai tugas. Apakah Anda memerlukan bantuan dalam menulis, mengkode, mengatur data, menghasilkan gambar, atau mencari jawaban atas pertanyaan Anda.
LM Studio adalah alat untuk menemukan, mengunduh, dan menjalankan LLM lokal.
Gradio Web UI adalah alat untuk model bahasa besar. Mendukung Transformers, GPTQ, Llama.cpp (GGML/GGUF), model Llama.
Openplayground adalah playfround untuk menjalankan model chatgpt seperti secara lokal di perangkat Anda.
Vicuna adalah chatbot open source yang dilatih oleh fine tuning llama. Tampaknya mencapai lebih dari 90% kualitas chatgpt dan biaya $ 300 untuk berlatih.
Yeargar AI adalah pencipta agen Langchain yang dirancang untuk membantu Anda membangun, membuat prototipe, dan menggunakan agen bertenaga AI dengan mudah.
KoboldCPP adalah perangkat lunak generasi teks AI yang mudah digunakan untuk model GGML. Ini adalah satu -satunya yang dapat didistribusikan sendiri dari kebetulan, yang membangun llama.cpp, dan menambahkan titik akhir API kobold serbaguna, dukungan format tambahan, kompatibilitas ke belakang, serta UI mewah dengan cerita yang persisten, alat pengeditan, format simpan, memori, dunia Info, catatan penulis, karakter, dan skenario.
Kembali ke atas
Fuzzy Logic adalah pendekatan heuristik yang memungkinkan pemrosesan pohon keputusan yang lebih maju dan integrasi yang lebih baik dengan pemrograman berbasis aturan.
Arsitektur sistem logika fuzzy. Sumber: ResearchGate
Dukungan Vector Machine (SVM) adalah model pembelajaran mesin yang diawasi yang menggunakan algoritma klasifikasi untuk masalah klasifikasi dua kelompok.
Dukungan Mesin Vektor (SVM). Sumber: OpenClipart
Jaringan saraf adalah subset dari pembelajaran mesin dan merupakan jantung dari algoritma pembelajaran yang mendalam. Nama/struktur diilhami oleh otak manusia yang menyalin proses bahwa neuron biologis/node memberi sinyal satu sama lain.
Jaringan saraf yang dalam. Sumber: IBM
Convolutional Neural Networks (R-CNN) adalah algoritma deteksi objek yang pertama kali segmen gambar untuk menemukan kotak pembatas yang relevan potensial dan kemudian menjalankan algoritma deteksi untuk menemukan objek yang paling mungkin di dalam kotak pembatas tersebut.
Jaringan saraf konvolusional. Sumber: CS231N
Recurrent Neural Networks (RNNS) adalah jenis jaringan saraf buatan yang menggunakan data berurutan atau data deret waktu.
Jaringan saraf berulang. Sumber: SlideTeam
Perceptrons multilayer (MLP) adalah jaringan saraf multi-lapisan yang terdiri dari beberapa lapisan perceptron dengan aktivasi ambang batas.
Perceptrons multilayer. Sumber: Deepai
Random Forest adalah algoritma pembelajaran mesin yang biasa digunakan, yang menggabungkan output dari beberapa pohon keputusan untuk mencapai satu hasil. Pohon keputusan di hutan tidak dapat dipangkas untuk pengambilan sampel dan oleh karena itu, pemilihan prediksi. Kemudahan penggunaan dan fleksibilitasnya telah memicu adopsi, karena menangani masalah klasifikasi dan regresi.
Hutan acak. Sumber: Wikimedia
Pohon keputusan adalah model terstruktur pohon untuk klasifikasi dan regresi.
** Pohon Keputusan. Sumber: CMU
Naive Bayes adalah algoritma pembelajaran mesin yang digunakan masalah calssification yang diselesaikan. Ini didasarkan pada penerapan teorema Bayes dengan asumsi kemandirian yang kuat antara fitur.
Teorema Bayes. Sumber: Mathisfun
Kembali ke atas
Pytorch adalah kerangka pembelajaran mendalam sumber terbuka yang mempercepat jalan dari penelitian ke produksi, digunakan untuk aplikasi seperti visi komputer dan pemrosesan bahasa alami. Pytorch dikembangkan oleh Lab Penelitian AI Facebook.
Memulai dengan Pytorch
Dokumentasi Pytorch
Forum Diskusi Pytorch
Kursus Pytorch Top Online | Coursera
Kursus Pytorch Top Online | Udemy
Pelajari Pytorch dengan kursus dan kelas online | edx
Fundamental Pytorch - Pelajari | Microsoft Docs
Intro ke Deep Learning dengan Pytorch | Udacity
Pengembangan Pytorch dalam kode studio visual
Pytorch on Azure - Pembelajaran mendalam dengan Pytorch | Microsoft Azure
Pytorch - Azure Databricks | Microsoft Docs
Pembelajaran mendalam dengan Pytorch | Amazon Web Services (AWS)
Memulai dengan Pytorch di Google Cloud
Pytorch Mobile adalah alur kerja ML ujung ke ujung dari pelatihan hingga penyebaran untuk perangkat seluler iOS dan Android.
Torchscript adalah cara untuk membuat model yang dapat di -serial dan dapat dioptimalkan dari kode Pytorch. Ini memungkinkan program Torchscript apa pun disimpan dari proses Python dan dimuat dalam proses di mana tidak ada ketergantungan Python.
Torchserve adalah alat yang fleksibel dan mudah digunakan untuk menyajikan model Pytorch.
Keras adalah API jaringan saraf tingkat tinggi, yang ditulis dalam Python dan mampu berjalan di atas TensorFlow, CNTK, atau Theano.it dikembangkan dengan fokus pada memungkinkan eksperimen cepat. Ini mampu berjalan di atas TensorFlow, Microsoft Cognitive Toolkit, R, Theano, atau PlaidML.
Onnx Runtime adalah cross-platform, inferencing ml berkinerja tinggi dan akselerator pelatihan. Ini mendukung model dari kerangka pembelajaran yang mendalam seperti Pytorch dan TensorFlow/keras serta pustaka pembelajaran mesin klasik seperti Scikit-Learn, LightGBM, XGBoost, dll.
Kornia adalah perpustakaan visi komputer yang dapat dibedakan yang terdiri dari serangkaian rutinitas dan modul yang dapat dibedakan untuk menyelesaikan masalah CV (visi komputer) generik.
Pytorch-NLP adalah perpustakaan untuk pemrosesan bahasa alami (NLP) di Python. Ini dibangun dengan penelitian terbaru dalam pikiran, dan dirancang sejak hari pertama untuk mendukung prototipe cepat. Pytorch-NLP hadir dengan embeddings pra-terlatih, sampler, dataset loader, metrik, modul jaringan saraf dan encoder teks.
Ignite adalah perpustakaan tingkat tinggi untuk membantu pelatihan dan mengevaluasi jaringan saraf di Pytorch secara fleksibel dan transparan.
Hummingbird adalah perpustakaan untuk menyusun model ML tradisional yang terlatih menjadi perhitungan tensor. Ini memungkinkan pengguna untuk memanfaatkan kerangka kerja jaringan saraf yang mulus (seperti Pytorch) untuk mempercepat model ML tradisional.
Deep Graph Library (DGL) adalah paket Python yang dibangun untuk implementasi mudah dari keluarga model Neural Network, di atas Pytorch dan kerangka kerja lainnya.
Tensorly adalah API tingkat tinggi untuk metode tensor dan jaringan saraf yang tarik dalam di Python yang bertujuan untuk membuat pembelajaran tensor menjadi sederhana.
GPYTORCH adalah perpustakaan proses Gaussian yang diimplementasikan menggunakan Pytorch, yang dirancang untuk membuat model proses Gaussian yang dapat diskalakan dan fleksibel.
Poutyne adalah kerangka kerja seperti keras untuk Pytorch dan menangani banyak kode boilerplating yang diperlukan untuk melatih jaringan saraf.
Forte adalah toolkit untuk membangun jaringan pipa NLP yang menampilkan komponen yang dapat dikomposisi, antarmuka data yang nyaman, dan interaksi lintas tugas.
Torchmetrics adalah metrik pembelajaran mesin untuk aplikasi Pytorch yang didistribusikan dan dapat diskalakan.
Captum adalah source open, perpustakaan yang dapat diperluas untuk interpretabilitas model yang dibangun di Pytorch.
Transformer adalah pemrosesan bahasa alami yang canggih untuk Pytorch, TensorFlow, dan Jax.
Hydra adalah kerangka kerja untuk mengkonfigurasi aplikasi yang kompleks secara elegan.
Accelerate adalah cara sederhana untuk melatih dan menggunakan model Pytorch dengan multi-GPU, TPU, presisi campuran.
Ray adalah kerangka kerja yang cepat dan sederhana untuk membangun dan menjalankan aplikasi terdistribusi.
Parlai adalah platform terpadu untuk berbagi, melatih, dan mengevaluasi model dialog di banyak tugas.
Pytorchvideo adalah perpustakaan pembelajaran yang mendalam untuk penelitian pemahaman video. Host berbagai model yang berfokus pada video, dataset, pipa pelatihan dan banyak lagi.
Opacus adalah perpustakaan yang memungkinkan pelatihan model Pytorch dengan privasi diferensial.
Pytorch Lightning adalah perpustakaan ML seperti keras untuk Pytorch. Ini meninggalkan pelatihan inti dan logika validasi untuk Anda dan mengotomatiskan sisanya.
Pytorch Geometric Temporal adalah perpustakaan ekstensi temporal (dinamis) untuk Pytorch Geometric.
Pytorch Geometric adalah perpustakaan untuk pembelajaran yang mendalam pada data input yang tidak teratur seperti grafik, awan titik, dan manifold.
Raster Vision adalah kerangka kerja open source untuk pembelajaran yang mendalam pada citra satelit dan udara.
Crypten adalah kerangka kerja untuk pelestarian privasi ML. Tujuannya adalah untuk membuat teknik komputasi yang aman dapat diakses oleh praktisi ML.
Optuna adalah kerangka optimasi hyperparameter open source untuk mengotomatisasi pencarian hiperparameter.
Pyro adalah bahasa pemrograman probabilistik universal (PPL) yang ditulis dalam Python dan didukung oleh Pytorch di backend.
Albumentation adalah perpustakaan augmentasi gambar yang cepat dan dapat diperluas untuk berbagai tugas CV seperti klasifikasi, segmentasi, deteksi objek dan estimasi pose.
Skorch adalah perpustakaan tingkat tinggi untuk Pytorch yang menyediakan kompatibilitas scikit-learn penuh.
MMF adalah kerangka kerja modular untuk penelitian multimodal visi & bahasa dari Facebook AI Research (Fair).
AdaptDL adalah pelatihan pembelajaran mendalam dan adaptif sumber daya dan kerangka penjadwalan.
Polyaxon adalah platform untuk membangun, melatih, dan memantau aplikasi pembelajaran mendalam skala besar.
TextBrewer adalah toolkit distilasi pengetahuan berbasis pytorch untuk pemrosesan bahasa alami
Advertorch adalah kotak alat untuk penelitian ketahanan permusuhan. Ini berisi modul untuk menghasilkan contoh -contoh permusuhan dan bertahan melawan serangan.
Nemo adalah AA Toolkit untuk percakapan AI.
Clinicadl adalah kerangka kerja untuk klasifikasi penyakit Alzheimer yang dapat direproduksi
Stable Baselines3 (SB3) adalah seperangkat implementasi algoritma pembelajaran penguatan yang andal di Pytorch.
Torchio adalah seperangkat alat untuk membaca secara efisien, preprocess, sampel, augment, dan menulis gambar medis 3D dalam aplikasi pembelajaran mendalam yang ditulis dalam Pytorch.
Pysyft adalah perpustakaan Python untuk privasi yang dienkripsi dan privasi.
Flair adalah kerangka kerja yang sangat sederhana untuk pemrosesan bahasa alami yang canggih (NLP).
Glow adalah kompiler ML yang mempercepat kinerja kerangka pembelajaran yang mendalam pada platform perangkat keras yang berbeda.
FairScale adalah perpustakaan ekstensi Pytorch untuk pelatihan kinerja tinggi dan skala besar pada satu atau beberapa mesin/node.
Monai adalah kerangka kerja pembelajaran yang mendalam yang menyediakan kemampuan dasar yang dioptimalkan secara domain untuk mengembangkan alur kerja pelatihan pencitraan kesehatan.
PFRL adalah perpustakaan pembelajaran penguatan yang mendalam yang mengimplementasikan berbagai algoritma penguatan mendalam yang canggih di Python menggunakan Pytorch.
Einops adalah operasi tensor yang fleksibel dan kuat untuk kode yang dapat dibaca dan andal.
PyTorch3D adalah perpustakaan pembelajaran mendalam yang menyediakan komponen yang efisien dan dapat digunakan kembali untuk penelitian visi komputer 3D dengan Pytorch.
Ensemble Pytorch adalah kerangka kerja ensemble terpadu untuk Pytorch untuk meningkatkan kinerja dan ketahanan model pembelajaran mendalam Anda.
Lightly adalah kerangka kerja visi komputer untuk pembelajaran yang di-swadaya.
Tinggi adalah perpustakaan yang memfasilitasi implementasi algoritma belajar meta berbasis gradien yang rumit dan loop optimasi bersarang dengan pytorch dekat-vanilla.
Horovod adalah perpustakaan pelatihan terdistribusi untuk kerangka pembelajaran yang mendalam. Horovod bertujuan untuk membuat DL terdistribusi dengan cepat dan mudah digunakan.
Pennylane adalah perpustakaan untuk kuantum ML, diferensiasi otomatis, dan optimalisasi perhitungan kuantum hibrida.
Detectron2 adalah platform generasi berikutnya yang adil untuk deteksi dan segmentasi objek.
Fastai adalah perpustakaan yang menyederhanakan pelatihan jaring saraf yang cepat dan akurat menggunakan praktik terbaik modern.
Kembali ke atas
TensorFlow adalah platform open source ujung ke ujung untuk pembelajaran mesin. Ini memiliki ekosistem alat, perpustakaan, dan sumber daya masyarakat yang komprehensif dan fleksibel yang memungkinkan para peneliti mendorong ML yang canggih di ML dan pengembang dengan mudah membangun dan menggunakan aplikasi yang bertenaga ML.
Memulai dengan TensorFlow
Tutorial TensorFlow
Sertifikat Pengembang TensorFlow | Aliran Tensor
Komunitas TensorFlow
Model & Dataset TensorFlow
Tensorflow Cloud
Pendidikan Pembelajaran Mesin | Aliran Tensor
Kursus TensorFlow Top Online | Coursera
Kursus TensorFlow Top Online | Udemy
Pembelajaran mendalam dengan TensorFlow | Udemy
Pembelajaran mendalam dengan TensorFlow | edx
Intro ke TensorFlow untuk Pembelajaran Deep | Udacity
Intro to TensorFlow: Kursus Kecelakaan Pembelajaran Mesin | Pengembang Google
Latih dan sebarkan model TensorFlow - Azure Machine Learning
Terapkan model pembelajaran mesin dalam fungsi Azure dengan Python dan TensorFlow | Microsoft Azure
Pembelajaran mendalam dengan TensorFlow | Amazon Web Services (AWS)
TensorFlow - Amazon Emr | Dokumentasi AWS
TensorFlow Enterprise | Google Awan
TensorFlow Lite adalah kerangka pembelajaran mendalam sumber terbuka untuk menggunakan model pembelajaran mesin pada perangkat seluler dan IoT.
TensorFlow.js adalah perpustakaan JavaScript yang memungkinkan Anda mengembangkan atau menjalankan model ML dalam JavaScript, dan menggunakan ML langsung di sisi klien browser, sisi server melalui Node.js, asli seluler melalui React Native, desktop asli via elektron, dan bahkan di IoT Perangkat melalui Node.js di Raspberry Pi.
TensorFlow_Macos adalah versi yang dioptimalkan Mac dari TensorFlow dan TensorFlow Addons untuk MacOS 11.0+ yang dipercepat menggunakan kerangka komputasi ML Apple.
Google Colaboratory adalah lingkungan notebook Jupyter gratis yang tidak memerlukan pengaturan dan berjalan sepenuhnya di cloud, memungkinkan Anda untuk menjalankan kode TensorFlow di browser Anda dengan satu klik.
Alat What-IF adalah alat untuk menyelidik model pembelajaran mesin bebas kode, berguna untuk pemahaman model, debugging, dan keadilan. Tersedia di Tensorboard dan Jupyter atau Colab Notebooks.
Tensorboard adalah serangkaian alat visualisasi untuk memahami, men -debug, dan mengoptimalkan program TensorFlow.
Keras adalah API jaringan saraf tingkat tinggi, yang ditulis dalam Python dan mampu berjalan di atas TensorFlow, CNTK, atau Theano.it dikembangkan dengan fokus pada memungkinkan eksperimen cepat. Ini mampu berjalan di atas TensorFlow, Microsoft Cognitive Toolkit, R, Theano, atau PlaidML.
XLA (aljabar linier yang dipercepat) adalah kompiler khusus domain untuk aljabar linier yang mengoptimalkan perhitungan tensorflow. Hasilnya adalah peningkatan kecepatan, penggunaan memori, dan portabilitas pada server dan platform seluler.
ML Perf adalah rangkaian benchmark ML yang luas untuk mengukur kinerja kerangka kerja perangkat lunak ML, akselerator perangkat keras ML, dan platform cloud ML.
TensorFlow Playground adalah lingkungan pengembangan untuk bermain -main dengan jaringan saraf di browser Anda.
TPU Research Cloud (TRC) adalah program memungkinkan para peneliti untuk mengajukan akses ke sekelompok lebih dari 1.000 TPU cloud tanpa biaya untuk membantu mereka mempercepat gelombang terobosan penelitian berikutnya.
MLIR adalah representasi perantara baru dan kerangka kerja kompiler.
Lattice adalah perpustakaan untuk solusi ML yang fleksibel, terkontrol, dan dapat ditafsirkan dengan batasan bentuk yang masuk akal.
TensorFlow Hub adalah perpustakaan untuk pembelajaran mesin yang dapat digunakan kembali. Unduh dan gunakan kembali model terlatih terbaru dengan jumlah kode minimal.
TensorFlow Cloud adalah perpustakaan untuk menghubungkan lingkungan lokal Anda ke Google Cloud.
TensorFlow Model Optimization Toolkit adalah serangkaian alat untuk mengoptimalkan model ML untuk penyebaran dan eksekusi.
Rekomendasi TensorFlow adalah perpustakaan untuk membangun model sistem rekomendasi.
TensorFlow Text adalah kumpulan kelas dan OPS terkait teks dan NLP yang siap digunakan dengan TensorFlow 2.
TensorFlow Graphics adalah perpustakaan fungsionalitas grafis komputer mulai dari kamera, lampu, dan bahan hingga renderer.
TensorFlow Federated adalah kerangka kerja open source untuk pembelajaran mesin dan perhitungan lain pada data desentralisasi.
Probabilitas TensorFlow adalah perpustakaan untuk penalaran probabilistik dan analisis statistik.
Tensor2Tensor adalah perpustakaan model pembelajaran mendalam dan kumpulan data yang dirancang untuk membuat pembelajaran mendalam lebih mudah diakses dan mempercepat penelitian ML.
TensorFlow Privacy adalah perpustakaan Python yang mencakup implementasi pengoptimal TensorFlow untuk pelatihan model pembelajaran mesin dengan privasi diferensial.
TensorFlow Ranking adalah teknik Library for Learning-to-Rank (LTR) di platform TensorFlow.
Agen TensorFlow adalah perpustakaan untuk pembelajaran penguatan di TensorFlow.
TensorFlow Addons adalah repositori kontribusi yang sesuai dengan pola API yang mapan, tetapi mengimplementasikan fungsionalitas baru yang tidak tersedia di inti TensorFlow, dikelola oleh SIG Addons. TensorFlow secara asli mendukung sejumlah besar operator, lapisan, metrik, kerugian, dan pengoptimal.
TensorFlow I/O adalah dataset, streaming, dan ekstensi sistem file, dikelola oleh SIG IO.
TensorFlow Quantum adalah pustaka pembelajaran mesin kuantum untuk prototipe cepat model ML kuantum-klasik hibrida.
Dopamin adalah kerangka kerja penelitian untuk prototipe cepat algoritma pembelajaran penguatan.
TRFL adalah perpustakaan untuk penguatan blok bangunan pembelajaran yang dibuat oleh DeepMind.
Mesh TensorFlow adalah bahasa untuk pembelajaran mendalam yang didistribusikan, mampu menentukan kelas luas perhitungan tensor terdistribusi.
RaggedTensors adalah API yang membuatnya mudah untuk menyimpan dan memanipulasi data dengan bentuk yang tidak seragam, termasuk teks (kata, kalimat, karakter), dan batch dengan panjang variabel.
Unicode Ops adalah API yang mendukung bekerja dengan teks Unicode secara langsung di TensorFlow.
Magenta adalah proyek penelitian yang mengeksplorasi peran pembelajaran mesin dalam proses menciptakan seni dan musik.
Nucleus adalah perpustakaan kode Python dan C ++ yang dirancang untuk memudahkan untuk membaca, menulis, dan menganalisis data dalam format file genomik umum seperti SAM dan VCF.
Sonnet adalah perpustakaan dari DeepMind untuk membangun jaringan saraf.
Pembelajaran saraf terstruktur adalah kerangka pembelajaran untuk melatih jaringan saraf dengan memanfaatkan sinyal terstruktur selain input fitur.
Remediasi model adalah perpustakaan untuk membantu membuat dan melatih model dengan cara yang mengurangi atau menghilangkan kerusakan pengguna yang dihasilkan dari bias kinerja yang mendasarinya.
Indikator keadilan adalah perpustakaan yang memungkinkan perhitungan mudah dari metrik keadilan yang umum diidentifikasi untuk pengklasifikasi biner dan multiclass.
Decision Forests adalah algoritma canggih untuk pelatihan, melayani dan menafsirkan model yang menggunakan hutan keputusan untuk klasifikasi, regresi, dan peringkat.
Kembali ke atas
Core ML adalah kerangka kerja Apple untuk mengintegrasikan model pembelajaran mesin ke dalam aplikasi yang berjalan di perangkat Apple (termasuk iOS, watchOS, macOS, dan TVOS). Core ML memperkenalkan format file publik (.mlmodel) untuk serangkaian metode ML yang luas termasuk jaringan saraf dalam (baik konvolusional dan berulang), ansambel pohon dengan peningkatan, dan model linier umum. Model dalam format ini dapat secara langsung diintegrasikan ke dalam aplikasi melalui Xcode.
Pengantar Core ML
Mengintegrasikan model ML inti ke dalam aplikasi Anda
Model inti ML
Referensi API Inti ML
Spesifikasi Inti ML
Forum Pengembang Apple untuk Inti ML
Kursus ML Inti Top Online | Udemy
Kursus ML Inti Top Online | Coursera
Layanan IBM Watson untuk Core ML | IBM
Hasilkan Aset ML Inti Menggunakan IBM Maximo Visual Inspection | IBM
Core ML Tools adalah proyek yang berisi alat pendukung untuk konversi model Core ML, pengeditan, dan validasi.
Buat ML adalah alat yang menyediakan cara baru untuk melatih model pembelajaran mesin di Mac Anda. Dibutuhkan kompleksitas dari pelatihan model sambil memproduksi model ML inti yang kuat.
TensorFlow_Macos adalah versi yang dioptimalkan Mac dari TensorFlow dan TensorFlow Addons untuk MacOS 11.0+ yang dipercepat menggunakan kerangka komputasi ML Apple.
Apple Vision adalah kerangka kerja yang melakukan deteksi tengara wajah dan wajah, deteksi teks, pengenalan barcode, pendaftaran gambar, dan pelacakan fitur umum. Visi juga memungkinkan penggunaan model ML inti khusus untuk tugas -tugas seperti klasifikasi atau deteksi objek.
Keras adalah API jaringan saraf tingkat tinggi, yang ditulis dalam Python dan mampu berjalan di atas TensorFlow, CNTK, atau Theano.it dikembangkan dengan fokus pada memungkinkan eksperimen cepat. Ini mampu berjalan di atas TensorFlow, Microsoft Cognitive Toolkit, R, Theano, atau PlaidML.
XGBoost adalah perpustakaan meningkatkan gradien terdistribusi yang dioptimalkan yang dirancang untuk menjadi sangat efisien, fleksibel, dan portabel. Ini mengimplementasikan algoritma pembelajaran mesin di bawah kerangka kerja gradien. XGBoost menyediakan peningkatan pohon paralel (juga dikenal sebagai GBDT, GBM) yang menyelesaikan banyak masalah ilmu data dengan cara yang cepat dan akurat. Ini mendukung pelatihan terdistribusi pada beberapa mesin, termasuk AWS, GCE, Azure, dan Cluster Benang. Juga, dapat diintegrasikan dengan Flink, Spark, dan sistem Dataflow cloud lainnya.
LIBSVM adalah perangkat lunak terintegrasi untuk klasifikasi vektor dukungan, (C-SVC, Nu-SVC), regresi (Epsilon-SVR, Nu-SVR) dan estimasi distribusi (SVM satu kelas). Ini mendukung klasifikasi multi-kelas.
Scikit-Learn adalah alat yang sederhana dan efisien untuk penambangan data dan analisis data. Ini dibangun di atas Numpy, Scipy, dan Mathplotlib.
XCODE mencakup semua yang dibutuhkan pengembang untuk membuat aplikasi hebat untuk Mac, iPhone, iPad, Apple TV, dan Apple Watch. XCODE memberikan pengembang alur kerja terpadu untuk desain antarmuka pengguna, pengkodean, pengujian, dan debugging. Xcode dibangun sebagai aplikasi universal yang berjalan 100% secara asli pada CPU berbasis Intel dan Apple Silicon. Ini termasuk MacOS SDK terpadu yang menampilkan semua kerangka kerja, kompiler, debugger, dan alat lain yang Anda butuhkan untuk membangun aplikasi yang berjalan secara asli di Apple Silicon dan Intel X86_64 CPU.
SwiftUi adalah alat antarmuka pengguna yang menyediakan tampilan, kontrol, dan struktur tata letak untuk mendeklarasikan antarmuka pengguna aplikasi Anda. Kerangka kerja SwiftUi menyediakan penangan acara untuk memberikan keran, gerakan, dan jenis input lainnya ke aplikasi Anda.
Uikit adalah kerangka kerja yang menyediakan infrastruktur yang diperlukan untuk aplikasi iOS atau TVOS Anda. Ini menyediakan jendela dan tampilan arsitektur untuk mengimplementasikan antarmuka Anda, infrastruktur penanganan acara untuk memberikan multi-sentuh dan jenis input lainnya ke aplikasi Anda, dan loop run utama yang diperlukan untuk mengelola interaksi di antara pengguna, sistem, dan aplikasi Anda.
AppKit adalah alat antarmuka pengguna grafis yang berisi semua objek yang Anda butuhkan untuk mengimplementasikan antarmuka pengguna untuk aplikasi macOS seperti windows, panel, tombol, menu, gulir, dan bidang teks, dan menangani semua detail untuk Anda seperti halnya secara efisien Menggambar di layar, berkomunikasi dengan perangkat perangkat keras dan buffer layar, membersihkan area layar sebelum menggambar, dan klip tampilan.
Arkit adalah satu set alat pengembangan perangkat lunak untuk memungkinkan pengembang membangun aplikasi augmented-reality untuk iOS yang dikembangkan oleh Apple. Versi terbaru Arkit 3.5 mengambil keuntungan dari pemindai Lidar baru dan sistem penginderaan kedalaman di iPad Pro (2020) untuk mendukung generasi baru aplikasi AR yang menggunakan geometri adegan untuk pemahaman adegan yang ditingkatkan dan oklusi objek.
RealityKit adalah kerangka kerja untuk mengimplementasikan simulasi 3D kinerja tinggi dan rendering dengan informasi yang disediakan oleh kerangka kerja Arkit untuk mengintegrasikan objek virtual dengan mulus ke dalam dunia nyata.
Scenekit adalah kerangka kerja grafis 3D tingkat tinggi yang membantu Anda membuat adegan dan efek animasi 3D di aplikasi iOS Anda.
Instrumen adalah alat analisis dan pengujian kinerja yang kuat dan fleksibel yang merupakan bagian dari set alat Xcode. Ini dirancang untuk membantu Anda membuat profil aplikasi, proses, dan perangkat MacOS, WatchOS, TVOS, dan MacOS Anda agar dapat lebih memahami dan mengoptimalkan perilaku dan kinerja mereka.
Cocoapods adalah manajer ketergantungan untuk Swift dan Objective-C yang digunakan dalam proyek XCODE dengan menentukan dependensi untuk proyek Anda dalam file teks sederhana. Cocoapods kemudian secara rekursif menyelesaikan dependensi antara perpustakaan, mengambil kode sumber untuk semua dependensi, dan membuat dan memelihara ruang kerja Xcode untuk membangun proyek Anda.
AppCode terus memantau kualitas kode Anda. Ini memperingatkan Anda akan kesalahan dan bau dan menyarankan perbaikan cepat untuk menyelesaikannya secara otomatis. AppCode menyediakan banyak inspeksi kode untuk Objective-C, Swift, C/C ++, dan sejumlah inspeksi kode untuk bahasa yang didukung lainnya.
Kembali ke atas
Deep Learning adalah bagian dari pembelajaran mesin, yang pada dasarnya adalah jaringan saraf dengan tiga atau lebih lapisan. Jaringan saraf ini berupaya mensimulasikan perilaku otak manusia, meskipun, jauh dari mencocokkan kemampuannya. Ini memungkinkan jaringan saraf untuk "belajar" dari sejumlah besar data. Pembelajaran dapat diawasi, semi-diawasi atau tidak diawasi.
Kursus online pembelajaran mendalam | NVIDIA
Kursus Pembelajaran Top Deep Online | Coursera
Kursus Pembelajaran Top Deep Online | Udemy
Pelajari pembelajaran mendalam dengan kursus dan pelajaran online | edx
Kursus online pembelajaran mendalam nanodegree | Udacity
Kursus Pembelajaran Mesin oleh Andrew NG | Coursera
Kursus Teknik Pembelajaran Mesin untuk Produksi (MLOPS) oleh Andrew NG | Coursera
Ilmu Data: Jaringan Pembelajaran Deep and Neural di Python | Udemy
Memahami Pembelajaran Mesin dengan Python | pandangan jamak
Cara Berpikir Tentang Algoritma Pembelajaran Mesin | pandangan jamak
Kursus Pembelajaran Mendalam | Stanford Online
Pembelajaran mendalam - UW Profesional & Pendidikan Berkelanjutan
Kursus online pembelajaran mendalam | Universitas Harvard
Pembelajaran mesin untuk semua orang kursus | Datacamp
Kursus Pakar Kecerdasan Buatan: Edisi Platinum | Udemy
Kursus Kecerdasan Buatan Top Online | Coursera
Pelajari Kecerdasan Buatan dengan Kursus dan Pelajaran Online | edx
Sertifikat Profesional dalam Ilmu Komputer untuk Kecerdasan Buatan | edx
Program Nanodegree Kecerdasan Buatan
Kursus Online Kecerdasan Buatan (AI) | Udacity
Kursus Intro ke Kecerdasan Buatan | Udacity
Edge ai untuk kursus pengembang IoT | Udacity
Penalaran: Pohon tujuan dan sistem ahli berbasis aturan | MIT OpencourSeware
Sistem ahli dan kecerdasan buatan terapan
Sistem Otonomi - Microsoft AI
Pengantar Microsoft Project Bonsai
Pengajaran Mesin dengan Platform Sistem Otonomi Microsoft
Pelatihan Sistem Maritim Otonomi | Pencarian AMC
Kursus Mobil Otonomi Teratas Online | Udemy
Sistem Kontrol Terapan 1: Mobil Otonomi: Matematika + PID + MPC | Udemy
Pelajari robotika otonom dengan kursus dan pelajaran online | edx
Program Nanodegree Kecerdasan Buatan
Kursus & Program Online Sistem Ononomis | Udacity
Edge ai untuk kursus pengembang IoT | Udacity
Sistem otonom MOOC dan kursus online gratis | Daftar MOOC
Program Pascasarjana Sistem Robotika dan Otonomi | Standford Online
Laboratorium Sistem Otonomi Seluler | MIT OpencourSeware
Nvidia Cudnn adalah perpustakaan primitif yang dipercepat GPU untuk jaringan saraf yang dalam. Cudnn memberikan implementasi yang sangat disetel untuk rutinitas standar seperti konvolusi ke depan dan ke belakang, pooling, normalisasi, dan lapisan aktivasi. Cudnn mempercepat kerangka kerja pembelajaran yang dalam secara luas, termasuk Caffe2, Chainer, Keras, Matlab, Mxnet, Pytorch, dan Tensorflow.
NVIDIA DLSS (Deep Learning Super Sampling) adalah teknologi temporal yang meningkatkan teknologi rendering AI yang meningkatkan kinerja grafis menggunakan prosesor AI inti tensor khusus pada GEFORCE RTX ™ GPU. DLSS menggunakan kekuatan jaringan saraf pembelajaran yang mendalam untuk meningkatkan laju bingkai dan menghasilkan gambar yang indah dan tajam untuk permainan Anda.
AMD Fidelityfx Super Resolution (FSR) adalah solusi open source, berkualitas tinggi untuk menghasilkan bingkai resolusi tinggi dari input resolusi yang lebih rendah. Ini menggunakan kumpulan algoritma pembelajaran mendalam canggih dengan penekanan khusus pada menciptakan tepi berkualitas tinggi, memberikan peningkatan kinerja yang besar dibandingkan dengan rendering pada resolusi asli secara langsung. FSR memungkinkan "kinerja praktis" untuk operasi render yang mahal, seperti penelusuran ray perangkat keras untuk AMD RDNA ™ dan AMD RDNA ™ 2 arsitektur.
Intel XE Super Sampling (XESS) adalah teknologi rendering AI yang meningkatkan gambar temporal yang meningkatkan kinerja grafis yang mirip dengan DLSS NVIDIA (Deep Learning Super Sampling). Arsitektur GPU ARC Intel (awal 2022) akan memiliki GPU yang memiliki fitur XE-CORES khusus untuk menjalankan Xess. GPU akan memiliki mesin Xe Matrix Extenstions Matrix (XMX) untuk pemrosesan AI yang dipercepat perangkat keras. Xess akan dapat berjalan pada perangkat tanpa XMX, termasuk grafik terintegrasi, meskipun, kinerja Xess akan lebih rendah pada kartu grafis non-intel karena akan ditenagai oleh instruksi DP4A.
Jupyter Notebook adalah aplikasi web open-source yang memungkinkan Anda membuat dan berbagi dokumen yang berisi kode langsung, persamaan, visualisasi, dan teks naratif. Jupyter digunakan secara luas dalam industri yang melakukan pembersihan dan transformasi data, simulasi numerik, pemodelan statistik, visualisasi data, ilmu data, dan pembelajaran mesin.
Apache Spark adalah mesin analitik terpadu untuk pemrosesan data skala besar. It provides high-level APIs in Scala, Java, Python, and R, and an optimized engine that supports general computation graphs for data analysis. It also supports a rich set of higher-level tools including Spark SQL for SQL and DataFrames, MLlib for machine learning, GraphX for graph processing, and Structured Streaming for stream processing.
Apache Spark Connector for SQL Server and Azure SQL is a high-performance connector that enables you to use transactional data in big data analytics and persists results for ad-hoc queries or reporting. The connector allows you to use any SQL database, on-premises or in the cloud, as an input data source or output data sink for Spark jobs.
Apache PredictionIO is an open source machine learning framework for developers, data scientists, and end users. It supports event collection, deployment of algorithms, evaluation, querying predictive results via REST APIs. It is based on scalable open source services like Hadoop, HBase (and other DBs), Elasticsearch, Spark and implements what is called a Lambda Architecture.
Cluster Manager for Apache Kafka(CMAK) is a tool for managing Apache Kafka clusters.
BigDL is a distributed deep learning library for Apache Spark. With BigDL, users can write their deep learning applications as standard Spark programs, which can directly run on top of existing Spark or Hadoop clusters.
Eclipse Deeplearning4J (DL4J) is a set of projects intended to support all the needs of a JVM-based(Scala, Kotlin, Clojure, and Groovy) deep learning application. This means starting with the raw data, loading and preprocessing it from wherever and whatever format it is in to building and tuning a wide variety of simple and complex deep learning networks.
Deep Learning Toolbox™ is a tool that provides a framework for designing and implementing deep neural networks with algorithms, pretrained models, and apps. You can use convolutional neural networks (ConvNets, CNNs) and long short-term memory (LSTM) networks to perform classification and regression on image, time-series, and text data. You can build network architectures such as generative adversarial networks (GANs) and Siamese networks using automatic differentiation, custom training loops, and shared weights. With the Deep Network Designer app, you can design, analyze, and train networks graphically. It can exchange models with TensorFlow™ and PyTorch through the ONNX format and import models from TensorFlow-Keras and Caffe. The toolbox supports transfer learning with DarkNet-53, ResNet-50, NASNet, SqueezeNet and many other pretrained models.
Reinforcement Learning Toolbox™ is a tool that provides an app, functions, and a Simulink® block for training policies using reinforcement learning algorithms, including DQN, PPO, SAC, and DDPG. You can use these policies to implement controllers and decision-making algorithms for complex applications such as resource allocation, robotics, and autonomous systems.
Deep Learning HDL Toolbox™ is a tool that provides functions and tools to prototype and implement deep learning networks on FPGAs and SoCs. It provides pre-built bitstreams for running a variety of deep learning networks on supported Xilinx® and Intel® FPGA and SoC devices. Profiling and estimation tools let you customize a deep learning network by exploring design, performance, and resource utilization tradeoffs.
Parallel Computing Toolbox™ is a tool that lets you solve computationally and data-intensive problems using multicore processors, GPUs, and computer clusters. High-level constructs such as parallel for-loops, special array types, and parallelized numerical algorithms enable you to parallelize MATLAB® applications without CUDA or MPI programming. The toolbox lets you use parallel-enabled functions in MATLAB and other toolboxes. You can use the toolbox with Simulink® to run multiple simulations of a model in parallel. Programs and models can run in both interactive and batch modes.
XGBoost is an optimized distributed gradient boosting library designed to be highly efficient, flexible and portable. It implements machine learning algorithms under the Gradient Boosting framework. XGBoost provides a parallel tree boosting (also known as GBDT, GBM) that solve many data science problems in a fast and accurate way. It supports distributed training on multiple machines, including AWS, GCE, Azure, and Yarn clusters. Also, it can be integrated with Flink, Spark and other cloud dataflow systems.
LIBSVM is an integrated software for support vector classification, (C-SVC, nu-SVC), regression (epsilon-SVR, nu-SVR) and distribution estimation (one-class SVM). It supports multi-class classification.
Scikit-Learn is a simple and efficient tool for data mining and data analysis. It is built on NumPy,SciPy, and mathplotlib.
TensorFlow is an end-to-end open source platform for machine learning. It has a comprehensive, flexible ecosystem of tools, libraries and community resources that lets researchers push the state-of-the-art in ML and developers easily build and deploy ML powered applications.
Keras is a high-level neural networks API, written in Python and capable of running on top of TensorFlow, CNTK, or Theano.It was developed with a focus on enabling fast experimentation. It is capable of running on top of TensorFlow, Microsoft Cognitive Toolkit, R, Theano, or PlaidML.
PyTorch is a library for deep learning on irregular input data such as graphs, point clouds, and manifolds. Primarily developed by Facebook's AI Research lab.
Azure Databricks is a fast and collaborative Apache Spark-based big data analytics service designed for data science and data engineering. Azure Databricks, sets up your Apache Spark environment in minutes, autoscale, and collaborate on shared projects in an interactive workspace. Azure Databricks supports Python, Scala, R, Java, and SQL, as well as data science frameworks and libraries including TensorFlow, PyTorch, and scikit-learn.
Microsoft Cognitive Toolkit (CNTK) is an open-source toolkit for commercial-grade distributed deep learning. It describes neural networks as a series of computational steps via a directed graph. CNTK allows the user to easily realize and combine popular model types such as feed-forward DNNs, convolutional neural networks (CNNs) and recurrent neural networks (RNNs/LSTMs). CNTK implements stochastic gradient descent (SGD, error backpropagation) learning with automatic differentiation and parallelization across multiple GPUs and servers.
Tensorflow_macOS is a Mac-optimized version of TensorFlow and TensorFlow Addons for macOS 11.0+ accelerated using Apple's ML Compute framework.
Apache Airflow is an open-source workflow management platform created by the community to programmatically author, schedule and monitor workflows. Memasang. Principles. Dapat diskalakan. Airflow has a modular architecture and uses a message queue to orchestrate an arbitrary number of workers. Airflow is ready to scale to infinity.
Open Neural Network Exchange(ONNX) is an open ecosystem that empowers AI developers to choose the right tools as their project evolves. ONNX provides an open source format for AI models, both deep learning and traditional ML. It defines an extensible computation graph model, as well as definitions of built-in operators and standard data types.
Apache MXNet is a deep learning framework designed for both efficiency and flexibility. It allows you to mix symbolic and imperative programming to maximize efficiency and productivity. At its core, MXNet contains a dynamic dependency scheduler that automatically parallelizes both symbolic and imperative operations on the fly. A graph optimization layer on top of that makes symbolic execution fast and memory efficient. MXNet is portable and lightweight, scaling effectively to multiple GPUs and multiple machines. Support for Python, R, Julia, Scala, Go, Javascript and more.
AutoGluon is toolkit for Deep learning that automates machine learning tasks enabling you to easily achieve strong predictive performance in your applications. With just a few lines of code, you can train and deploy high-accuracy deep learning models on tabular, image, and text data.
Anaconda is a very popular Data Science platform for machine learning and deep learning that enables users to develop models, train them, and deploy them.
PlaidML is an advanced and portable tensor compiler for enabling deep learning on laptops, embedded devices, or other devices where the available computing hardware is not well supported or the available software stack contains unpalatable license restrictions.
OpenCV is a highly optimized library with focus on real-time computer vision applications. The C++, Python, and Java interfaces support Linux, MacOS, Windows, iOS, and Android.
Scikit-Learn is a Python module for machine learning built on top of SciPy, NumPy, and matplotlib, making it easier to apply robust and simple implementations of many popular machine learning algorithms.
Weka is an open source machine learning software that can be accessed through a graphical user interface, standard terminal applications, or a Java API. It is widely used for teaching, research, and industrial applications, contains a plethora of built-in tools for standard machine learning tasks, and additionally gives transparent access to well-known toolboxes such as scikit-learn, R, and Deeplearning4j.
Caffe is a deep learning framework made with expression, speed, and modularity in mind. It is developed by Berkeley AI Research (BAIR)/The Berkeley Vision and Learning Center (BVLC) and community contributors.
Theano is a Python library that allows you to define, optimize, and evaluate mathematical expressions involving multi-dimensional arrays efficiently including tight integration with NumPy.
Microsoft Project Bonsai is a low-code AI platform that speeds AI-powered automation development and part of the Autonomous Systems suite from Microsoft. Bonsai is used to build AI components that can provide operator guidance or make independent decisions to optimize process variables, improve production efficiency, and reduce downtime.
Microsoft AirSim is a simulator for drones, cars and more, built on Unreal Engine (with an experimental Unity release). AirSim is open-source, cross platform, and supports software-in-the-loop simulation with popular flight controllers such as PX4 & ArduPilot and hardware-in-loop with PX4 for physically and visually realistic simulations. It is developed as an Unreal plugin that can simply be dropped into any Unreal environment. AirSim is being developed as a platform for AI research to experiment with deep learning, computer vision and reinforcement learning algorithms for autonomous vehicles.
CARLA is an open-source simulator for autonomous driving research. CARLA has been developed from the ground up to support development, training, and validation of autonomous driving systems. In addition to open-source code and protocols, CARLA provides open digital assets (urban layouts, buildings, vehicles) that were created for this purpose and can be used freely.
ROS/ROS2 bridge for CARLA(package) is a bridge that enables two-way communication between ROS and CARLA. The information from the CARLA server is translated to ROS topics. In the same way, the messages sent between nodes in ROS get translated to commands to be applied in CARLA.
ROS Toolbox is a tool that provides an interface connecting MATLAB® and Simulink® with the Robot Operating System (ROS and ROS 2), enabling you to create a network of ROS nodes. The toolbox includes MATLAB functions and Simulink blocks to import, analyze, and play back ROS data recorded in rosbag files. You can also connect to a live ROS network to access ROS messages.
Robotics Toolbox™ provides a toolbox that brings robotics specific functionality(designing, simulating, and testing manipulators, mobile robots, and humanoid robots) to MATLAB, exploiting the native capabilities of MATLAB (linear algebra, portability, graphics). The toolbox also supports mobile robots with functions for robot motion models (bicycle), path planning algorithms (bug, distance transform, D*, PRM), kinodynamic planning (lattice, RRT), localization (EKF, particle filter), map building (EKF) and simultaneous localization and mapping (EKF), and a Simulink model a of non-holonomic vehicle. The Toolbox also including a detailed Simulink model for a quadrotor flying robot.
Image Processing Toolbox™ is a tool that provides a comprehensive set of reference-standard algorithms and workflow apps for image processing, analysis, visualization, and algorithm development. You can perform image segmentation, image enhancement, noise reduction, geometric transformations, image registration, and 3D image processing.
Computer Vision Toolbox™ is a tool that provides algorithms, functions, and apps for designing and testing computer vision, 3D vision, and video processing systems. You can perform object detection and tracking, as well as feature detection, extraction, and matching. You can automate calibration workflows for single, stereo, and fisheye cameras. For 3D vision, the toolbox supports visual and point cloud SLAM, stereo vision, structure from motion, and point cloud processing.
Robotics Toolbox™ is a tool that provides a toolbox that brings robotics specific functionality(designing, simulating, and testing manipulators, mobile robots, and humanoid robots) to MATLAB, exploiting the native capabilities of MATLAB (linear algebra, portability, graphics). The toolbox also supports mobile robots with functions for robot motion models (bicycle), path planning algorithms (bug, distance transform, D*, PRM), kinodynamic planning (lattice, RRT), localization (EKF, particle filter), map building (EKF) and simultaneous localization and mapping (EKF), and a Simulink model a of non-holonomic vehicle. The Toolbox also including a detailed Simulink model for a quadrotor flying robot.
Model Predictive Control Toolbox™ is a tool that provides functions, an app, and Simulink® blocks for designing and simulating controllers using linear and nonlinear model predictive control (MPC). The toolbox lets you specify plant and disturbance models, horizons, constraints, and weights. By running closed-loop simulations, you can evaluate controller performance.
Predictive Maintenance Toolbox™ is a tool that lets you manage sensor data, design condition indicators, and estimate the remaining useful life (RUL) of a machine. The toolbox provides functions and an interactive app for exploring, extracting, and ranking features using data-based and model-based techniques, including statistical, spectral, and time-series analysis.
Vision HDL Toolbox™ is a tool that provides pixel-streaming algorithms for the design and implementation of vision systems on FPGAs and ASICs. It provides a design framework that supports a diverse set of interface types, frame sizes, and frame rates. The image processing, video, and computer vision algorithms in the toolbox use an architecture appropriate for HDL implementations.
Automated Driving Toolbox™ is a MATLAB tool that provides algorithms and tools for designing, simulating, and testing ADAS and autonomous driving systems. You can design and test vision and lidar perception systems, as well as sensor fusion, path planning, and vehicle controllers. Visualization tools include a bird's-eye-view plot and scope for sensor coverage, detections and tracks, and displays for video, lidar, and maps. The toolbox lets you import and work with HERE HD Live Map data and OpenDRIVE® road networks. It also provides reference application examples for common ADAS and automated driving features, including FCW, AEB, ACC, LKA, and parking valet. The toolbox supports C/C++ code generation for rapid prototyping and HIL testing, with support for sensor fusion, tracking, path planning, and vehicle controller algorithms.
UAV Toolbox is an application that provides tools and reference applications for designing, simulating, testing, and deploying unmanned aerial vehicle (UAV) and drone applications. You can design autonomous flight algorithms, UAV missions, and flight controllers. The Flight Log Analyzer app lets you interactively analyze 3D flight paths, telemetry information, and sensor readings from common flight log formats.
Navigation Toolbox™ is a tool that provides algorithms and analysis tools for motion planning, simultaneous localization and mapping (SLAM), and inertial navigation. The toolbox includes customizable search and sampling-based path planners, as well as metrics for validating and comparing paths. You can create 2D and 3D map representations, generate maps using SLAM algorithms, and interactively visualize and debug map generation with the SLAM map builder app.
Lidar Toolbox™ is a tool that provides algorithms, functions, and apps for designing, analyzing, and testing lidar processing systems. You can perform object detection and tracking, semantic segmentation, shape fitting, lidar registration, and obstacle detection. Lidar Toolbox supports lidar-camera cross calibration for workflows that combine computer vision and lidar processing.
Mapping Toolbox™ is a tool that provides algorithms and functions for transforming geographic data and creating map displays. You can visualize your data in a geographic context, build map displays from more than 60 map projections, and transform data from a variety of sources into a consistent geographic coordinate system.
Back to the Top
Reinforcement Learning is a subset of machine learning, which is a neural network with three or more layers. These neural networks attempt to simulate the behavior of the human brain,though, far from matching its ability. This allows the neural networks to "learn" from a process in which a model learns to become more accurate for performing an action in an environment based on feedback in order to maximize the reward. The Learning can be supervised, semi-supervised or unsupervised.
Top Reinforcement Learning Courses | Coursera
Top Reinforcement Learning Courses | Udemy
Top Reinforcement Learning Courses | Udacity
Reinforcement Learning Courses | Stanford Online
Deep Learning Online Courses | NVIDIA
Top Deep Learning Courses Online | Coursera
Top Deep Learning Courses Online | Udemy
Learn Deep Learning with Online Courses and Lessons | edX
Deep Learning Online Course Nanodegree | Udacity
Machine Learning Course by Andrew Ng | Coursera
Machine Learning Engineering for Production (MLOps) course by Andrew Ng | Coursera
Data Science: Deep Learning and Neural Networks in Python | Udemy
Understanding Machine Learning with Python | pandangan jamak
How to Think About Machine Learning Algorithms | pandangan jamak
Deep Learning Courses | Stanford Online
Deep Learning - UW Professional & Continuing Education
Deep Learning Online Courses | Harvard University
Machine Learning for Everyone Courses | DataCamp
Artificial Intelligence Expert Course: Platinum Edition | Udemy
Top Artificial Intelligence Courses Online | Coursera
Learn Artificial Intelligence with Online Courses and Lessons | edX
Professional Certificate in Computer Science for Artificial Intelligence | edX
Artificial Intelligence Nanodegree program
Artificial Intelligence (AI) Online Courses | Udacity
Intro to Artificial Intelligence Course | Udacity
Edge AI for IoT Developers Course | Udacity
Reasoning: Goal Trees and Rule-Based Expert Systems | MIT OpenCourseWare
Expert Systems and Applied Artificial Intelligence
Autonomous Systems - Microsoft AI
Introduction to Microsoft Project Bonsai
Machine teaching with the Microsoft Autonomous Systems platform
Autonomous Maritime Systems Training | AMC Search
Top Autonomous Cars Courses Online | Udemy
Applied Control Systems 1: autonomous cars: Math + PID + MPC | Udemy
Learn Autonomous Robotics with Online Courses and Lessons | edX
Artificial Intelligence Nanodegree program
Autonomous Systems Online Courses & Programs | Udacity
Edge AI for IoT Developers Course | Udacity
Autonomous Systems MOOC and Free Online Courses | MOOC List
Robotics and Autonomous Systems Graduate Program | Standford Online
Mobile Autonomous Systems Laboratory | MIT OpenCourseWare
OpenAI is an open source Python library for developing and comparing reinforcement learning algorithms by providing a standard API to communicate between learning algorithms and environments, as well as a standard set of environments compliant with that API.
ReinforcementLearning.jl is a collection of tools for doing reinforcement learning research in Julia.
Reinforcement Learning Toolbox™ is a tool that provides an app, functions, and a Simulink® block for training policies using reinforcement learning algorithms, including DQN, PPO, SAC, and DDPG. You can use these policies to implement controllers and decision-making algorithms for complex applications such as resource allocation, robotics, and autonomous systems.
Amazon SageMaker is a fully managed service that provides every developer and data scientist with the ability to build, train, and deploy machine learning (ML) models quickly.
AWS RoboMaker is a service that provides a fully-managed, scalable infrastructure for simulation that customers use for multi-robot simulation and CI/CD integration with regression testing in simulation.
TensorFlow is an end-to-end open source platform for machine learning. It has a comprehensive, flexible ecosystem of tools, libraries and community resources that lets researchers push the state-of-the-art in ML and developers easily build and deploy ML powered applications.
Keras is a high-level neural networks API, written in Python and capable of running on top of TensorFlow, CNTK, or Theano.It was developed with a focus on enabling fast experimentation. It is capable of running on top of TensorFlow, Microsoft Cognitive Toolkit, R, Theano, or PlaidML.
PyTorch is a library for deep learning on irregular input data such as graphs, point clouds, and manifolds. Primarily developed by Facebook's AI Research lab.
Scikit-Learn is a simple and efficient tool for data mining and data analysis. It is built on NumPy,SciPy, and mathplotlib.
NVIDIA cuDNN is a GPU-accelerated library of primitives for deep neural networks. cuDNN provides highly tuned implementations for standard routines such as forward and backward convolution, pooling, normalization, and activation layers. cuDNN accelerates widely used deep learning frameworks, including Caffe2, Chainer, Keras, MATLAB, MxNet, PyTorch, and TensorFlow.
Jupyter Notebook is an open-source web application that allows you to create and share documents that contain live code, equations, visualizations and narrative text. Jupyter is used widely in industries that do data cleaning and transformation, numerical simulation, statistical modeling, data visualization, data science, and machine learning.
Apache Spark is a unified analytics engine for large-scale data processing. It provides high-level APIs in Scala, Java, Python, and R, and an optimized engine that supports general computation graphs for data analysis. It also supports a rich set of higher-level tools including Spark SQL for SQL and DataFrames, MLlib for machine learning, GraphX for graph processing, and Structured Streaming for stream processing.
Apache Spark Connector for SQL Server and Azure SQL is a high-performance connector that enables you to use transactional data in big data analytics and persists results for ad-hoc queries or reporting. The connector allows you to use any SQL database, on-premises or in the cloud, as an input data source or output data sink for Spark jobs.
Apache PredictionIO is an open source machine learning framework for developers, data scientists, and end users. It supports event collection, deployment of algorithms, evaluation, querying predictive results via REST APIs. It is based on scalable open source services like Hadoop, HBase (and other DBs), Elasticsearch, Spark and implements what is called a Lambda Architecture.
Cluster Manager for Apache Kafka(CMAK) is a tool for managing Apache Kafka clusters.
BigDL is a distributed deep learning library for Apache Spark. With BigDL, users can write their deep learning applications as standard Spark programs, which can directly run on top of existing Spark or Hadoop clusters.
Eclipse Deeplearning4J (DL4J) is a set of projects intended to support all the needs of a JVM-based(Scala, Kotlin, Clojure, and Groovy) deep learning application. This means starting with the raw data, loading and preprocessing it from wherever and whatever format it is in to building and tuning a wide variety of simple and complex deep learning networks.
Deep Learning Toolbox™ is a tool that provides a framework for designing and implementing deep neural networks with algorithms, pretrained models, and apps. You can use convolutional neural networks (ConvNets, CNNs) and long short-term memory (LSTM) networks to perform classification and regression on image, time-series, and text data. You can build network architectures such as generative adversarial networks (GANs) and Siamese networks using automatic differentiation, custom training loops, and shared weights. With the Deep Network Designer app, you can design, analyze, and train networks graphically. It can exchange models with TensorFlow™ and PyTorch through the ONNX format and import models from TensorFlow-Keras and Caffe. The toolbox supports transfer learning with DarkNet-53, ResNet-50, NASNet, SqueezeNet and many other pretrained models.
Deep Learning HDL Toolbox™ is a tool that provides functions and tools to prototype and implement deep learning networks on FPGAs and SoCs. It provides pre-built bitstreams for running a variety of deep learning networks on supported Xilinx® and Intel® FPGA and SoC devices. Profiling and estimation tools let you customize a deep learning network by exploring design, performance, and resource utilization tradeoffs.
Parallel Computing Toolbox™ is a tool that lets you solve computationally and data-intensive problems using multicore processors, GPUs, and computer clusters. High-level constructs such as parallel for-loops, special array types, and parallelized numerical algorithms enable you to parallelize MATLAB® applications without CUDA or MPI programming. The toolbox lets you use parallel-enabled functions in MATLAB and other toolboxes. You can use the toolbox with Simulink® to run multiple simulations of a model in parallel. Programs and models can run in both interactive and batch modes.
XGBoost is an optimized distributed gradient boosting library designed to be highly efficient, flexible and portable. It implements machine learning algorithms under the Gradient Boosting framework. XGBoost provides a parallel tree boosting (also known as GBDT, GBM) that solve many data science problems in a fast and accurate way. It supports distributed training on multiple machines, including AWS, GCE, Azure, and Yarn clusters. Also, it can be integrated with Flink, Spark and other cloud dataflow systems.
LIBSVM is an integrated software for support vector classification, (C-SVC, nu-SVC), regression (epsilon-SVR, nu-SVR) and distribution estimation (one-class SVM). It supports multi-class classification.
Azure Databricks is a fast and collaborative Apache Spark-based big data analytics service designed for data science and data engineering. Azure Databricks, sets up your Apache Spark environment in minutes, autoscale, and collaborate on shared projects in an interactive workspace. Azure Databricks supports Python, Scala, R, Java, and SQL, as well as data science frameworks and libraries including TensorFlow, PyTorch, and scikit-learn.
Microsoft Cognitive Toolkit (CNTK) is an open-source toolkit for commercial-grade distributed deep learning. It describes neural networks as a series of computational steps via a directed graph. CNTK allows the user to easily realize and combine popular model types such as feed-forward DNNs, convolutional neural networks (CNNs) and recurrent neural networks (RNNs/LSTMs). CNTK implements stochastic gradient descent (SGD, error backpropagation) learning with automatic differentiation and parallelization across multiple GPUs and servers.
Tensorflow_macOS is a Mac-optimized version of TensorFlow and TensorFlow Addons for macOS 11.0+ accelerated using Apple's ML Compute framework.
Apache Airflow is an open-source workflow management platform created by the community to programmatically author, schedule and monitor workflows. Memasang. Principles. Dapat diskalakan. Airflow has a modular architecture and uses a message queue to orchestrate an arbitrary number of workers. Airflow is ready to scale to infinity.
Open Neural Network Exchange(ONNX) is an open ecosystem that empowers AI developers to choose the right tools as their project evolves. ONNX provides an open source format for AI models, both deep learning and traditional ML. It defines an extensible computation graph model, as well as definitions of built-in operators and standard data types.
Apache MXNet is a deep learning framework designed for both efficiency and flexibility. It allows you to mix symbolic and imperative programming to maximize efficiency and productivity. At its core, MXNet contains a dynamic dependency scheduler that automatically parallelizes both symbolic and imperative operations on the fly. A graph optimization layer on top of that makes symbolic execution fast and memory efficient. MXNet is portable and lightweight, scaling effectively to multiple GPUs and multiple machines. Support for Python, R, Julia, Scala, Go, Javascript and more.
AutoGluon is toolkit for Deep learning that automates machine learning tasks enabling you to easily achieve strong predictive performance in your applications. With just a few lines of code, you can train and deploy high-accuracy deep learning models on tabular, image, and text data.
Anaconda is a very popular Data Science platform for machine learning and deep learning that enables users to develop models, train them, and deploy them.
PlaidML is an advanced and portable tensor compiler for enabling deep learning on laptops, embedded devices, or other devices where the available computing hardware is not well supported or the available software stack contains unpalatable license restrictions.
OpenCV is a highly optimized library with focus on real-time computer vision applications. The C++, Python, and Java interfaces support Linux, MacOS, Windows, iOS, and Android.
Scikit-Learn is a Python module for machine learning built on top of SciPy, NumPy, and matplotlib, making it easier to apply robust and simple implementations of many popular machine learning algorithms.
Weka is an open source machine learning software that can be accessed through a graphical user interface, standard terminal applications, or a Java API. It is widely used for teaching, research, and industrial applications, contains a plethora of built-in tools for standard machine learning tasks, and additionally gives transparent access to well-known toolboxes such as scikit-learn, R, and Deeplearning4j.
Caffe is a deep learning framework made with expression, speed, and modularity in mind. It is developed by Berkeley AI Research (BAIR)/The Berkeley Vision and Learning Center (BVLC) and community contributors.
Theano is a Python library that allows you to define, optimize, and evaluate mathematical expressions involving multi-dimensional arrays efficiently including tight integration with NumPy.
Microsoft Project Bonsai is a low-code AI platform that speeds AI-powered automation development and part of the Autonomous Systems suite from Microsoft. Bonsai is used to build AI components that can provide operator guidance or make independent decisions to optimize process variables, improve production efficiency, and reduce downtime.
Microsoft AirSim is a simulator for drones, cars and more, built on Unreal Engine (with an experimental Unity release). AirSim is open-source, cross platform, and supports software-in-the-loop simulation with popular flight controllers such as PX4 & ArduPilot and hardware-in-loop with PX4 for physically and visually realistic simulations. It is developed as an Unreal plugin that can simply be dropped into any Unreal environment. AirSim is being developed as a platform for AI research to experiment with deep learning, computer vision and reinforcement learning algorithms for autonomous vehicles.
CARLA is an open-source simulator for autonomous driving research. CARLA has been developed from the ground up to support development, training, and validation of autonomous driving systems. In addition to open-source code and protocols, CARLA provides open digital assets (urban layouts, buildings, vehicles) that were created for this purpose and can be used freely.
ROS/ROS2 bridge for CARLA(package) is a bridge that enables two-way communication between ROS and CARLA. The information from the CARLA server is translated to ROS topics. In the same way, the messages sent between nodes in ROS get translated to commands to be applied in CARLA.
ROS Toolbox is a tool that provides an interface connecting MATLAB® and Simulink® with the Robot Operating System (ROS and ROS 2), enabling you to create a network of ROS nodes. The toolbox includes MATLAB functions and Simulink blocks to import, analyze, and play back ROS data recorded in rosbag files. You can also connect to a live ROS network to access ROS messages.
Robotics Toolbox™ provides a toolbox that brings robotics specific functionality(designing, simulating, and testing manipulators, mobile robots, and humanoid robots) to MATLAB, exploiting the native capabilities of MATLAB (linear algebra, portability, graphics). The toolbox also supports mobile robots with functions for robot motion models (bicycle), path planning algorithms (bug, distance transform, D*, PRM), kinodynamic planning (lattice, RRT), localization (EKF, particle filter), map building (EKF) and simultaneous localization and mapping (EKF), and a Simulink model a of non-holonomic vehicle. The Toolbox also including a detailed Simulink model for a quadrotor flying robot.
Image Processing Toolbox™ is a tool that provides a comprehensive set of reference-standard algorithms and workflow apps for image processing, analysis, visualization, and algorithm development. You can perform image segmentation, image enhancement, noise reduction, geometric transformations, image registration, and 3D image processing.
Computer Vision Toolbox™ is a tool that provides algorithms, functions, and apps for designing and testing computer vision, 3D vision, and video processing systems. You can perform object detection and tracking, as well as feature detection, extraction, and matching. You can automate calibration workflows for single, stereo, and fisheye cameras. For 3D vision, the toolbox supports visual and point cloud SLAM, stereo vision, structure from motion, and point cloud processing.
Robotics Toolbox™ is a tool that provides a toolbox that brings robotics specific functionality(designing, simulating, and testing manipulators, mobile robots, and humanoid robots) to MATLAB, exploiting the native capabilities of MATLAB (linear algebra, portability, graphics). The toolbox also supports mobile robots with functions for robot motion models (bicycle), path planning algorithms (bug, distance transform, D*, PRM), kinodynamic planning (lattice, RRT), localization (EKF, particle filter), map building (EKF) and simultaneous localization and mapping (EKF), and a Simulink model a of non-holonomic vehicle. The Toolbox also including a detailed Simulink model for a quadrotor flying robot.
Model Predictive Control Toolbox™ is a tool that provides functions, an app, and Simulink® blocks for designing and simulating controllers using linear and nonlinear model predictive control (MPC). The toolbox lets you specify plant and disturbance models, horizons, constraints, and weights. By running closed-loop simulations, you can evaluate controller performance.
Predictive Maintenance Toolbox™ is a tool that lets you manage sensor data, design condition indicators, and estimate the remaining useful life (RUL) of a machine. The toolbox provides functions and an interactive app for exploring, extracting, and ranking features using data-based and model-based techniques, including statistical, spectral, and time-series analysis.
Vision HDL Toolbox™ is a tool that provides pixel-streaming algorithms for the design and implementation of vision systems on FPGAs and ASICs. It provides a design framework that supports a diverse set of interface types, frame sizes, and frame rates. The image processing, video, and computer vision algorithms in the toolbox use an architecture appropriate for HDL implementations.
Automated Driving Toolbox™ is a MATLAB tool that provides algorithms and tools for designing, simulating, and testing ADAS and autonomous driving systems. You can design and test vision and lidar perception systems, as well as sensor fusion, path planning, and vehicle controllers. Visualization tools include a bird's-eye-view plot and scope for sensor coverage, detections and tracks, and displays for video, lidar, and maps. The toolbox lets you import and work with HERE HD Live Map data and OpenDRIVE® road networks. It also provides reference application examples for common ADAS and automated driving features, including FCW, AEB, ACC, LKA, and parking valet. The toolbox supports C/C++ code generation for rapid prototyping and HIL testing, with support for sensor fusion, tracking, path planning, and vehicle controller algorithms.
Navigation Toolbox™ is a tool that provides algorithms and analysis tools for motion planning, simultaneous localization and mapping (SLAM), and inertial navigation. The toolbox includes customizable search and sampling-based path planners, as well as metrics for validating and comparing paths. You can create 2D and 3D map representations, generate maps using SLAM algorithms, and interactively visualize and debug map generation with the SLAM map builder app.
UAV Toolbox is an application that provides tools and reference applications for designing, simulating, testing, and deploying unmanned aerial vehicle (UAV) and drone applications. You can design autonomous flight algorithms, UAV missions, and flight controllers. The Flight Log Analyzer app lets you interactively analyze 3D flight paths, telemetry information, and sensor readings from common flight log formats.
Lidar Toolbox™ is a tool that provides algorithms, functions, and apps for designing, analyzing, and testing lidar processing systems. You can perform object detection and tracking, semantic segmentation, shape fitting, lidar registration, and obstacle detection. Lidar Toolbox supports lidar-camera cross calibration for workflows that combine computer vision and lidar processing.
Mapping Toolbox™ is a tool that provides algorithms and functions for transforming geographic data and creating map displays. You can visualize your data in a geographic context, build map displays from more than 60 map projections, and transform data from a variety of sources into a consistent geographic coordinate system.
Back to the Top
Computer Vision is a field of Artificial Intelligence (AI) that focuses on enabling computers to identify and understand objects and people in images and videos.
OpenCV Courses
Exploring Computer Vision in Microsoft Azure
Top Computer Vision Courses Online | Coursera
Top Computer Vision Courses Online | Udemy
Learn Computer Vision with Online Courses and Lessons | edX
Computer Vision and Image Processing Fundamentals | edX
Introduction to Computer Vision Courses | Udacity
Computer Vision Nanodegree program | Udacity
Machine Vision Course |MIT Open Courseware
Computer Vision Training Courses | NobleProg
Visual Computing Graduate Program | Stanford Online
OpenCV is a highly optimized library with focus on real-time computer vision applications. The C++, Python, and Java interfaces support Linux, MacOS, Windows, iOS, and Android.
Microsoft Computer Vision Recipes is a project that provides examples and best practice guidelines for building computer vision systems. This allows people to build a comprehensive set of tools and examples that leverage recent advances in Computer Vision algorithms, neural architectures, and operationalizing such systems. Creatin from existing state-of-the-art libraries and build additional utility around loading image data, optimizing and evaluating models, and scaling up to the cloud.
Microsoft Cognitive Toolkit (CNTK) is an open-source toolkit for commercial-grade distributed deep learning. It describes neural networks as a series of computational steps via a directed graph. CNTK allows the user to easily realize and combine popular model types such as feed-forward DNNs, convolutional neural networks (CNNs) and recurrent neural networks (RNNs/LSTMs). CNTK implements stochastic gradient descent (SGD, error backpropagation) learning with automatic differentiation and parallelization across multiple GPUs and servers.
Scikit-Learn is a Python module for machine learning built on top of SciPy, NumPy, and matplotlib, making it easier to apply robust and simple implementations of many popular machine learning algorithms.
NVIDIA cuDNN is a GPU-accelerated library of primitives for deep neural networks. cuDNN provides highly tuned implementations for standard routines such as forward and backward convolution, pooling, normalization, and activation layers. cuDNN accelerates widely used deep learning frameworks, including Caffe2, Chainer, Keras, MATLAB, MxNet, PyTorch, and TensorFlow.
Automated Driving Toolbox™ is a MATLAB tool that provides algorithms and tools for designing, simulating, and testing ADAS and autonomous driving systems. You can design and test vision and lidar perception systems, as well as sensor fusion, path planning, and vehicle controllers. Visualization tools include a bird's-eye-view plot and scope for sensor coverage, detections and tracks, and displays for video, lidar, and maps. The toolbox lets you import and work with HERE HD Live Map data and OpenDRIVE® road networks. It also provides reference application examples for common ADAS and automated driving features, including FCW, AEB, ACC, LKA, and parking valet. The toolbox supports C/C++ code generation for rapid prototyping and HIL testing, with support for sensor fusion, tracking, path planning, and vehicle controller algorithms.
LRSLibrary is a Low-Rank and Sparse Tools for Background Modeling and Subtraction in Videos. The library was designed for moving object detection in videos, but it can be also used for other computer vision and machine learning problems.
Image Processing Toolbox™ is a tool that provides a comprehensive set of reference-standard algorithms and workflow apps for image processing, analysis, visualization, and algorithm development. You can perform image segmentation, image enhancement, noise reduction, geometric transformations, image registration, and 3D image processing.
Computer Vision Toolbox™ is a tool that provides algorithms, functions, and apps for designing and testing computer vision, 3D vision, and video processing systems. You can perform object detection and tracking, as well as feature detection, extraction, and matching. You can automate calibration workflows for single, stereo, and fisheye cameras. For 3D vision, the toolbox supports visual and point cloud SLAM, stereo vision, structure from motion, and point cloud processing.
Statistics and Machine Learning Toolbox™ is a tool that provides functions and apps to describe, analyze, and model data. You can use descriptive statistics, visualizations, and clustering for exploratory data analysis; fit probability distributions to data; generate random numbers for Monte Carlo simulations, and perform hypothesis tests. Regression and classification algorithms let you draw inferences from data and build predictive models either interactively, using the Classification and Regression Learner apps, or programmatically, using AutoML.
Lidar Toolbox™ is a tool that provides algorithms, functions, and apps for designing, analyzing, and testing lidar processing systems. You can perform object detection and tracking, semantic segmentation, shape fitting, lidar registration, and obstacle detection. Lidar Toolbox supports lidar-camera cross calibration for workflows that combine computer vision and lidar processing.
Mapping Toolbox™ is a tool that provides algorithms and functions for transforming geographic data and creating map displays. You can visualize your data in a geographic context, build map displays from more than 60 map projections, and transform data from a variety of sources into a consistent geographic coordinate system.
UAV Toolbox is an application that provides tools and reference applications for designing, simulating, testing, and deploying unmanned aerial vehicle (UAV) and drone applications. You can design autonomous flight algorithms, UAV missions, and flight controllers. The Flight Log Analyzer app lets you interactively analyze 3D flight paths, telemetry information, and sensor readings from common flight log formats.
Parallel Computing Toolbox™ is a tool that lets you solve computationally and data-intensive problems using multicore processors, GPUs, and computer clusters. High-level constructs such as parallel for-loops, special array types, and parallelized numerical algorithms enable you to parallelize MATLAB® applications without CUDA or MPI programming. The toolbox lets you use parallel-enabled functions in MATLAB and other toolboxes. You can use the toolbox with Simulink® to run multiple simulations of a model in parallel. Programs and models can run in both interactive and batch modes.
Partial Differential Equation Toolbox™ is a tool that provides functions for solving structural mechanics, heat transfer, and general partial differential equations (PDEs) using finite element analysis.
ROS Toolbox is a tool that provides an interface connecting MATLAB® and Simulink® with the Robot Operating System (ROS and ROS 2), enabling you to create a network of ROS nodes. The toolbox includes MATLAB functions and Simulink blocks to import, analyze, and play back ROS data recorded in rosbag files. You can also connect to a live ROS network to access ROS messages.
Robotics Toolbox™ provides a toolbox that brings robotics specific functionality(designing, simulating, and testing manipulators, mobile robots, and humanoid robots) to MATLAB, exploiting the native capabilities of MATLAB (linear algebra, portability, graphics). The toolbox also supports mobile robots with functions for robot motion models (bicycle), path planning algorithms (bug, distance transform, D*, PRM), kinodynamic planning (lattice, RRT), localization (EKF, particle filter), map building (EKF) and simultaneous localization and mapping (EKF), and a Simulink model a of non-holonomic vehicle. The Toolbox also including a detailed Simulink model for a quadrotor flying robot.
Deep Learning Toolbox™ is a tool that provides a framework for designing and implementing deep neural networks with algorithms, pretrained models, and apps. You can use convolutional neural networks (ConvNets, CNNs) and long short-term memory (LSTM) networks to perform classification and regression on image, time-series, and text data. You can build network architectures such as generative adversarial networks (GANs) and Siamese networks using automatic differentiation, custom training loops, and shared weights. With the Deep Network Designer app, you can design, analyze, and train networks graphically. It can exchange models with TensorFlow™ and PyTorch through the ONNX format and import models from TensorFlow-Keras and Caffe. The toolbox supports transfer learning with DarkNet-53, ResNet-50, NASNet, SqueezeNet and many other pretrained models.
Reinforcement Learning Toolbox™ is a tool that provides an app, functions, and a Simulink® block for training policies using reinforcement learning algorithms, including DQN, PPO, SAC, and DDPG. You can use these policies to implement controllers and decision-making algorithms for complex applications such as resource allocation, robotics, and autonomous systems.
Deep Learning HDL Toolbox™ is a tool that provides functions and tools to prototype and implement deep learning networks on FPGAs and SoCs. It provides pre-built bitstreams for running a variety of deep learning networks on supported Xilinx® and Intel® FPGA and SoC devices. Profiling and estimation tools let you customize a deep learning network by exploring design, performance, and resource utilization tradeoffs.
Model Predictive Control Toolbox™ is a tool that provides functions, an app, and Simulink® blocks for designing and simulating controllers using linear and nonlinear model predictive control (MPC). The toolbox lets you specify plant and disturbance models, horizons, constraints, and weights. By running closed-loop simulations, you can evaluate controller performance.
Vision HDL Toolbox™ is a tool that provides pixel-streaming algorithms for the design and implementation of vision systems on FPGAs and ASICs. It provides a design framework that supports a diverse set of interface types, frame sizes, and frame rates. The image processing, video, and computer vision algorithms in the toolbox use an architecture appropriate for HDL implementations.
Data Acquisition Toolbox™ is a tool that provides apps and functions for configuring data acquisition hardware, reading data into MATLAB® and Simulink®, and writing data to DAQ analog and digital output channels. The toolbox supports a variety of DAQ hardware, including USB, PCI, PCI Express®, PXI®, and PXI Express® devices, from National Instruments® and other vendors.
Microsoft AirSim is a simulator for drones, cars and more, built on Unreal Engine (with an experimental Unity release). AirSim is open-source, cross platform, and supports software-in-the-loop simulation with popular flight controllers such as PX4 & ArduPilot and hardware-in-loop with PX4 for physically and visually realistic simulations. It is developed as an Unreal plugin that can simply be dropped into any Unreal environment. AirSim is being developed as a platform for AI research to experiment with deep learning, computer vision and reinforcement learning algorithms for autonomous vehicles.
Back to the Top
Natural Language Processing (NLP) is a branch of artificial intelligence (AI) focused on giving computers the ability to understand text and spoken words in much the same way human beings can. NLP combines computational linguistics rule-based modeling of human language with statistical, machine learning, and deep learning models.
Natural Language Processing With Python's NLTK Package
Cognitive Services—APIs for AI Developers | Microsoft Azure
Artificial Intelligence Services - Amazon Web Services (AWS)
Google Cloud Natural Language API
Top Natural Language Processing Courses Online | Udemy
Introduction to Natural Language Processing (NLP) | Udemy
Top Natural Language Processing Courses | Coursera
Natural Language Processing | Coursera
Natural Language Processing in TensorFlow | Coursera
Learn Natural Language Processing with Online Courses and Lessons | edX
Build a Natural Language Processing Solution with Microsoft Azure | pandangan jamak
Natural Language Processing (NLP) Training Courses | NobleProg
Natural Language Processing with Deep Learning Course | Standford Online
Advanced Natural Language Processing - MIT OpenCourseWare
Certified Natural Language Processing Expert Certification | IABAC
Natural Language Processing Course - Intel
Natural Language Toolkit (NLTK) is a leading platform for building Python programs to work with human language data. It provides easy-to-use interfaces to over 50 corpora and lexical resources such as WordNet, along with a suite of text processing libraries for classification, tokenization, stemming, tagging, parsing, and semantic reasoning, wrappers for industrial-strength NLP libraries.
spaCy is a library for advanced Natural Language Processing in Python and Cython. It's built on the very latest research, and was designed from day one to be used in real products. spaCy comes with pretrained pipelines and currently supports tokenization and training for 60+ languages. It also features neural network models for tagging, parsing, named entity recognition, text classification and more, multi-task learning with pretrained transformers like BERT.
CoreNLP is a set of natural language analysis tools written in Java. CoreNLP enables users to derive linguistic annotations for text, including token and sentence boundaries, parts of speech, named entities, numeric and time values, dependency and constituency parses, coreference, sentiment, quote attributions, and relations.
NLPnet is a Python library for Natural Language Processing tasks based on neural networks. It performs part-of-speech tagging, semantic role labeling and dependency parsing.
Flair is a simple framework for state-of-the-art Natural Language Processing (NLP) models to your text, such as named entity recognition (NER), part-of-speech tagging (PoS), special support for biomedical data, sense disambiguation and classification, with support for a rapidly growing number of languages.
Catalyst is a C# Natural Language Processing library built for speed. Inspired by spaCy's design, it brings pre-trained models, out-of-the box support for training word and document embeddings, and flexible entity recognition models.
Apache OpenNLP is an open-source library for a machine learning based toolkit used in the processing of natural language text. It features an API for use cases like Named Entity Recognition, Sentence Detection, POS(Part-Of-Speech) tagging, Tokenization Feature extraction, Chunking, Parsing, and Coreference resolution.
Microsoft Cognitive Toolkit (CNTK) is an open-source toolkit for commercial-grade distributed deep learning. It describes neural networks as a series of computational steps via a directed graph. CNTK allows the user to easily realize and combine popular model types such as feed-forward DNNs, convolutional neural networks (CNNs) and recurrent neural networks (RNNs/LSTMs). CNTK implements stochastic gradient descent (SGD, error backpropagation) learning with automatic differentiation and parallelization across multiple GPUs and servers.
NVIDIA cuDNN is a GPU-accelerated library of primitives for deep neural networks. cuDNN provides highly tuned implementations for standard routines such as forward and backward convolution, pooling, normalization, and activation layers. cuDNN accelerates widely used deep learning frameworks, including Caffe2, Chainer, Keras, MATLAB, MxNet, PyTorch, and TensorFlow.
TensorFlow is an end-to-end open source platform for machine learning. It has a comprehensive, flexible ecosystem of tools, libraries and community resources that lets researchers push the state-of-the-art in ML and developers easily build and deploy ML powered applications.
Tensorflow_macOS is a Mac-optimized version of TensorFlow and TensorFlow Addons for macOS 11.0+ accelerated using Apple's ML Compute framework.
Keras is a high-level neural networks API, written in Python and capable of running on top of TensorFlow, CNTK, or Theano.It was developed with a focus on enabling fast experimentation. It is capable of running on top of TensorFlow, Microsoft Cognitive Toolkit, R, Theano, or PlaidML.
PyTorch is a library for deep learning on irregular input data such as graphs, point clouds, and manifolds. Primarily developed by Facebook's AI Research lab.
Eclipse Deeplearning4J (DL4J) is a set of projects intended to support all the needs of a JVM-based(Scala, Kotlin, Clojure, and Groovy) deep learning application. This means starting with the raw data, loading and preprocessing it from wherever and whatever format it is in to building and tuning a wide variety of simple and complex deep learning networks.
Chainer is a Python-based deep learning framework aiming at flexibility. It provides automatic differentiation APIs based on the define-by-run approach (dynamic computational graphs) as well as object-oriented high-level APIs to build and train neural networks. It also supports CUDA/cuDNN using CuPy for high performance training and inference.
Anaconda is a very popular Data Science platform for machine learning and deep learning that enables users to develop models, train them, and deploy them.
PlaidML is an advanced and portable tensor compiler for enabling deep learning on laptops, embedded devices, or other devices where the available computing hardware is not well supported or the available software stack contains unpalatable license restrictions.
Scikit-Learn is a Python module for machine learning built on top of SciPy, NumPy, and matplotlib, making it easier to apply robust and simple implementations of many popular machine learning algorithms.
Caffe is a deep learning framework made with expression, speed, and modularity in mind. It is developed by Berkeley AI Research (BAIR)/The Berkeley Vision and Learning Center (BVLC) and community contributors.
Theano is a Python library that allows you to define, optimize, and evaluate mathematical expressions involving multi-dimensional arrays efficiently including tight integration with NumPy.
Apache Spark is a unified analytics engine for large-scale data processing. It provides high-level APIs in Scala, Java, Python, and R, and an optimized engine that supports general computation graphs for data analysis. It also supports a rich set of higher-level tools including Spark SQL for SQL and DataFrames, MLlib for machine learning, GraphX for graph processing, and Structured Streaming for stream processing.
Apache Spark Connector for SQL Server and Azure SQL is a high-performance connector that enables you to use transactional data in big data analytics and persists results for ad-hoc queries or reporting. The connector allows you to use any SQL database, on-premises or in the cloud, as an input data source or output data sink for Spark jobs.
Apache PredictionIO is an open source machine learning framework for developers, data scientists, and end users. It supports event collection, deployment of algorithms, evaluation, querying predictive results via REST APIs. It is based on scalable open source services like Hadoop, HBase (and other DBs), Elasticsearch, Spark and implements what is called a Lambda Architecture.
Apache Airflow is an open-source workflow management platform created by the community to programmatically author, schedule and monitor workflows. Airflow has a modular architecture and uses a message queue to orchestrate an arbitrary number of workers. Airflow is ready to scale to infinity.
Open Neural Network Exchange(ONNX) is an open ecosystem that empowers AI developers to choose the right tools as their project evolves. ONNX provides an open source format for AI models, both deep learning and traditional ML. It defines an extensible computation graph model, as well as definitions of built-in operators and standard data types.
BigDL is a distributed deep learning library for Apache Spark. With BigDL, users can write their deep learning applications as standard Spark programs, which can directly run on top of existing Spark or Hadoop clusters.
Numba is an open source, NumPy-aware optimizing compiler for Python sponsored by Anaconda, Inc. It uses the LLVM compiler project to generate machine code from Python syntax. Numba can compile a large subset of numerically-focused Python, including many NumPy functions. Additionally, Numba has support for automatic parallelization of loops, generation of GPU-accelerated code, and creation of ufuncs and C callbacks.
Back to the Top
Bioinformatics is a field of computational science that has to do with the analysis of sequences of biological molecules. This usually refers to genes, DNA, RNA, or protein, and is particularly useful in comparing genes and other sequences in proteins and other sequences within an organism or between organisms, looking at evolutionary relationships between organisms, and using the patterns that exist across DNA and protein sequences to figure out what their function is.
European Bioinformatics Institute
National Center for Biotechnology Information
Online Courses in Bioinformatics |ISCB - International Society for Computational Biology
Bioinformatics | Coursera
Top Bioinformatics Courses | Udemy
Biometrics Courses | Udemy
Learn Bioinformatics with Online Courses and Lessons | edX
Bioinformatics Graduate Certificate | Harvard Extension School
Bioinformatics and Biostatistics | UC San Diego Extension
Bioinformatics and Proteomics - Free Online Course Materials | MIT
Introduction to Biometrics course - Biometrics Institute
Bioconductor is an open source project that provides tools for the analysis and comprehension of high-throughput genomic data. Bioconductor uses the R statistical programming language, and is open source and open development. It has two releases each year, and an active user community. Bioconductor is also available as an AMI (Amazon Machine Image) and Docker images.
Bioconda is a channel for the conda package manager specializing in bioinformatics software. It has a repository of packages containing over 7000 bioinformatics packages ready to use with conda install.
UniProt is a freely accessible database that provide users with a comprehensive, high-quality and freely accessible set of protein sequences annotated with functional information.
Bowtie 2 is an ultrafast and memory-efficient tool for aligning sequencing reads to long reference sequences. It is particularly good at aligning reads of about 50 up to 100s or 1,000s of characters, and particularly good at aligning to relatively long (mammalian) genomes.
Biopython is a set of freely available tools for biological computation written in Python by an international team of developers. It is a distributed collaborative effort to develop Python libraries and applications which address the needs of current and future work in bioinformatics.
BioRuby is a toolkit that has components for sequence analysis, pathway analysis, protein modelling and phylogenetic analysis; it supports many widely used data formats and provides easy access to databases, external programs and public web services, including BLAST, KEGG, GenBank, MEDLINE and GO.
BioJava is a toolkit that provides an API to maintain local installations of the PDB, load and manipulate structures, perform standard analysis such as sequence and structure alignments and visualize them in 3D.
BioPHP is an open source project that provides a collection of open source PHP code, with classes for DNA and protein sequence analysis, alignment, database parsing, and other bioinformatics tools.
Avogadro is an advanced molecule editor and visualizer designed for cross-platform use in computational chemistry, molecular modeling, bioinformatics, materials science, and related areas. It offers flexible high quality rendering and a powerful plugin architecture.
Ascalaph Designer is a program for molecular dynamic simulations. Under a single graphical environment are represented as their own implementation of molecular dynamics as well as the methods of classical and quantum mechanics of popular programs.
Anduril is a workflow platform for analyzing large data sets. Anduril provides facilities for analyzing high-thoughput data in biomedical research, and the platform is fully extensible by third parties. Ready-made tools support data visualization, DNA/RNA/ChIP-sequencing, DNA/RNA microarrays, cytometry and image analysis.
Galaxy is an open source, web-based platform for accessible, reproducible, and transparent computational biomedical research. It allows users without programming experience to easily specify parameters and run individual tools as well as larger workflows. It also captures run information so that any user can repeat and understand a complete computational analysis.
PathVisio is a free open-source pathway analysis and drawing software which allows drawing, editing, and analyzing biological pathways. It is developed in Java and can be extended with plugins.
Orange is a powerful data mining and machine learning toolkit that performs data analysis and visualization.
Basic Local Alignment Search Tool is a tool that finds regions of similarity between biological sequences. The program compares nucleotide or protein sequences to sequence databases and calculates the statistical significance.
OSIRIS is public-domain, free, and open source STR analysis software designed for clinical, forensic, and research use, and has been validated for use as an expert system for single-source samples.
NCBI BioSystems is a Database that provides integrated access to biological systems and their component genes, proteins, and small molecules, as well as literature describing those biosystems and other related data throughout Entrez.
Back to the Top
CUDA Toolkit. Source: NVIDIA Developer CUDA
CUDA is a parallel computing platform and programming model developed by NVIDIA for general computing on graphical processing units (GPUs). With CUDA, developers are able to dramatically speed up computing applications by harnessing the power of GPUs. In GPU-accelerated applications, the sequential part of the workload runs on the CPU, which is optimized for single-threaded. The compute intensive portion of the application runs on thousands of GPU cores in parallel. When using CUDA, developers can program in popular languages such as C, C++, Fortran, Python and MATLAB.
CUDA Toolkit Documentation
CUDA Quick Start Guide
CUDA on WSL
CUDA GPU support for TensorFlow
NVIDIA Deep Learning cuDNN Documentation
NVIDIA GPU Cloud Documentation
NVIDIA NGC is a hub for GPU-optimized software for deep learning, machine learning, and high-performance computing (HPC) workloads.
NVIDIA NGC Containers is a registry that provides researchers, data scientists, and developers with simple access to a comprehensive catalog of GPU-accelerated software for AI, machine learning and HPC. These containers take full advantage of NVIDIA GPUs on-premises and in the cloud.
CUDA Toolkit is a collection of tools & libraries that provide a development environment for creating high performance GPU-accelerated applications. The CUDA Toolkit allows you can develop, optimize, and deploy your applications on GPU-accelerated embedded systems, desktop workstations, enterprise data centers, cloud-based platforms and HPC supercomputers. The toolkit includes GPU-accelerated libraries, debugging and optimization tools, a C/C++ compiler, and a runtime library to build and deploy your application on major architectures including x86, Arm and POWER.
NVIDIA cuDNN is a GPU-accelerated library of primitives for deep neural networks. cuDNN provides highly tuned implementations for standard routines such as forward and backward convolution, pooling, normalization, and activation layers. cuDNN accelerates widely used deep learning frameworks, including Caffe2, Chainer, Keras, MATLAB, MxNet, PyTorch, and TensorFlow.
CUDA-X HPC is a collection of libraries, tools, compilers and APIs that help developers solve the world's most challenging problems. CUDA-X HPC includes highly tuned kernels essential for high-performance computing (HPC).
NVIDIA Container Toolkit is a collection of tools & libraries that allows users to build and run GPU accelerated Docker containers. The toolkit includes a container runtime library and utilities to automatically configure containers to leverage NVIDIA GPUs.
Minkowski Engine is an auto-differentiation library for sparse tensors. It supports all standard neural network layers such as convolution, pooling, unpooling, and broadcasting operations for sparse tensors.
CUTLASS is a collection of CUDA C++ template abstractions for implementing high-performance matrix-multiplication (GEMM) at all levels and scales within CUDA. It incorporates strategies for hierarchical decomposition and data movement similar to those used to implement cuBLAS.
CUB is a cooperative primitives for CUDA C++ kernel authors.
Tensorman is a utility for easy management of Tensorflow containers by developed by System76.Tensorman allows Tensorflow to operate in an isolated environment that is contained from the rest of the system. This virtual environment can operate independent of the base system, allowing you to use any version of Tensorflow on any version of a Linux distribution that supports the Docker runtime.
Numba is an open source, NumPy-aware optimizing compiler for Python sponsored by Anaconda, Inc. It uses the LLVM compiler project to generate machine code from Python syntax. Numba can compile a large subset of numerically-focused Python, including many NumPy functions. Additionally, Numba has support for automatic parallelization of loops, generation of GPU-accelerated code, and creation of ufuncs and C callbacks.
Chainer is a Python-based deep learning framework aiming at flexibility. It provides automatic differentiation APIs based on the define-by-run approach (dynamic computational graphs) as well as object-oriented high-level APIs to build and train neural networks. It also supports CUDA/cuDNN using CuPy for high performance training and inference.
CuPy is an implementation of NumPy-compatible multi-dimensional array on CUDA. CuPy consists of the core multi-dimensional array class, cupy.ndarray, and many functions on it. It supports a subset of numpy.ndarray interface.
CatBoost is a fast, scalable, high performance Gradient Boosting on Decision Trees library, used for ranking, classification, regression and other machine learning tasks for Python, R, Java, C++. Supports computation on CPU and GPU.
cuDF is a GPU DataFrame library for loading, joining, aggregating, filtering, and otherwise manipulating data. cuDF provides a pandas-like API that will be familiar to data engineers & data scientists, so they can use it to easily accelerate their workflows without going into the details of CUDA programming.
cuML is a suite of libraries that implement machine learning algorithms and mathematical primitives functions that share compatible APIs with other RAPIDS projects. cuML enables data scientists, researchers, and software engineers to run traditional tabular ML tasks on GPUs without going into the details of CUDA programming. In most cases, cuML's Python API matches the API from scikit-learn.
ArrayFire is a general-purpose library that simplifies the process of developing software that targets parallel and massively-parallel architectures including CPUs, GPUs, and other hardware acceleration devices.
Thrust is a C++ parallel programming library which resembles the C++ Standard Library. Thrust's high-level interface greatly enhances programmer productivity while enabling performance portability between GPUs and multicore CPUs.
AresDB is a GPU-powered real-time analytics storage and query engine. It features low query latency, high data freshness and highly efficient in-memory and on disk storage management.
Arraymancer is a tensor (N-dimensional array) project in Nim. The main focus is providing a fast and ergonomic CPU, Cuda and OpenCL ndarray library on which to build a scientific computing ecosystem.
Kintinuous is a real-time dense visual SLAM system capable of producing high quality globally consistent point and mesh reconstructions over hundreds of metres in real-time with only a low-cost commodity RGB-D sensor.
GraphVite is a general graph embedding engine, dedicated to high-speed and large-scale embedding learning in various applications.
Back to the Top
MATLAB is a programming language that does numerical computing such as expressing matrix and array mathematics directly.
MATLAB Documentation
Getting Started with MATLAB
MATLAB and Simulink Training from MATLAB Academy
MathWorks Certification Program
MATLAB Online Courses from Udemy
MATLAB Online Courses from Coursera
MATLAB Online Courses from edX
Building a MATLAB GUI
MATLAB Style Guidelines 2.0
Setting Up Git Source Control with MATLAB & Simulink
Pull, Push and Fetch Files with Git with MATLAB & Simulink
Create New Repository with MATLAB & Simulink
PRMLT is Matlab code for machine learning algorithms in the PRML book.
MATLAB and Simulink Services & Applications List
MATLAB in the Cloud is a service that allows you to run in cloud environments from MathWorks Cloud to Public Clouds including AWS and Azure.
MATLAB Online™ is a service that allows to users to uilitize MATLAB and Simulink through a web browser such as Google Chrome.
Simulink is a block diagram environment for Model-Based Design. It supports simulation, automatic code generation, and continuous testing of embedded systems.
Simulink Online™ is a service that provides access to Simulink through your web browser.
MATLAB Drive™ is a service that gives you the ability to store, access, and work with your files from anywhere.
MATLAB Parallel Server™ is a tool that lets you scale MATLAB® programs and Simulink® simulations to clusters and clouds. You can prototype your programs and simulations on the desktop and then run them on clusters and clouds without recoding. MATLAB Parallel Server supports batch jobs, interactive parallel computations, and distributed computations with large matrices.
MATLAB Schemer is a MATLAB package makes it easy to change the color scheme (theme) of the MATLAB display and GUI.
LRSLibrary is a Low-Rank and Sparse Tools for Background Modeling and Subtraction in Videos. The library was designed for moving object detection in videos, but it can be also used for other computer vision and machine learning problems.
Image Processing Toolbox™ is a tool that provides a comprehensive set of reference-standard algorithms and workflow apps for image processing, analysis, visualization, and algorithm development. You can perform image segmentation, image enhancement, noise reduction, geometric transformations, image registration, and 3D image processing.
Computer Vision Toolbox™ is a tool that provides algorithms, functions, and apps for designing and testing computer vision, 3D vision, and video processing systems. You can perform object detection and tracking, as well as feature detection, extraction, and matching. You can automate calibration workflows for single, stereo, and fisheye cameras. For 3D vision, the toolbox supports visual and point cloud SLAM, stereo vision, structure from motion, and point cloud processing.
Statistics and Machine Learning Toolbox™ is a tool that provides functions and apps to describe, analyze, and model data. You can use descriptive statistics, visualizations, and clustering for exploratory data analysis; fit probability distributions to data; generate random numbers for Monte Carlo simulations, and perform hypothesis tests. Regression and classification algorithms let you draw inferences from data and build predictive models either interactively, using the Classification and Regression Learner apps, or programmatically, using AutoML.
Lidar Toolbox™ is a tool that provides algorithms, functions, and apps for designing, analyzing, and testing lidar processing systems. You can perform object detection and tracking, semantic segmentation, shape fitting, lidar registration, and obstacle detection. Lidar Toolbox supports lidar-camera cross calibration for workflows that combine computer vision and lidar processing.
Mapping Toolbox™ is a tool that provides algorithms and functions for transforming geographic data and creating map displays. You can visualize your data in a geographic context, build map displays from more than 60 map projections, and transform data from a variety of sources into a consistent geographic coordinate system.
UAV Toolbox is an application that provides tools and reference applications for designing, simulating, testing, and deploying unmanned aerial vehicle (UAV) and drone applications. You can design autonomous flight algorithms, UAV missions, and flight controllers. The Flight Log Analyzer app lets you interactively analyze 3D flight paths, telemetry information, and sensor readings from common flight log formats.
Parallel Computing Toolbox™ is a tool that lets you solve computationally and data-intensive problems using multicore processors, GPUs, and computer clusters. High-level constructs such as parallel for-loops, special array types, and parallelized numerical algorithms enable you to parallelize MATLAB® applications without CUDA or MPI programming. The toolbox lets you use parallel-enabled functions in MATLAB and other toolboxes. You can use the toolbox with Simulink® to run multiple simulations of a model in parallel. Programs and models can run in both interactive and batch modes.
Partial Differential Equation Toolbox™ is a tool that provides functions for solving structural mechanics, heat transfer, and general partial differential equations (PDEs) using finite element analysis.
ROS Toolbox is a tool that provides an interface connecting MATLAB® and Simulink® with the Robot Operating System (ROS and ROS 2), enabling you to create a network of ROS nodes. The toolbox includes MATLAB functions and Simulink blocks to import, analyze, and play back ROS data recorded in rosbag files. You can also connect to a live ROS network to access ROS messages.
Robotics Toolbox™ provides a toolbox that brings robotics specific functionality(designing, simulating, and testing manipulators, mobile robots, and humanoid robots) to MATLAB, exploiting the native capabilities of MATLAB (linear algebra, portability, graphics). The toolbox also supports mobile robots with functions for robot motion models (bicycle), path planning algorithms (bug, distance transform, D*, PRM), kinodynamic planning (lattice, RRT), localization (EKF, particle filter), map building (EKF) and simultaneous localization and mapping (EKF), and a Simulink model a of non-holonomic vehicle. The Toolbox also including a detailed Simulink model for a quadrotor flying robot.
Deep Learning Toolbox™ is a tool that provides a framework for designing and implementing deep neural networks with algorithms, pretrained models, and apps. You can use convolutional neural networks (ConvNets, CNNs) and long short-term memory (LSTM) networks to perform classification and regression on image, time-series, and text data. You can build network architectures such as generative adversarial networks (GANs) and Siamese networks using automatic differentiation, custom training loops, and shared weights. With the Deep Network Designer app, you can design, analyze, and train networks graphically. It can exchange models with TensorFlow™ and PyTorch through the ONNX format and import models from TensorFlow-Keras and Caffe. The toolbox supports transfer learning with DarkNet-53, ResNet-50, NASNet, SqueezeNet and many other pretrained models.
Reinforcement Learning Toolbox™ is a tool that provides an app, functions, and a Simulink® block for training policies using reinforcement learning algorithms, including DQN, PPO, SAC, and DDPG. You can use these policies to implement controllers and decision-making algorithms for complex applications such as resource allocation, robotics, and autonomous systems.
Deep Learning HDL Toolbox™ is a tool that provides functions and tools to prototype and implement deep learning networks on FPGAs and SoCs. It provides pre-built bitstreams for running a variety of deep learning networks on supported Xilinx® and Intel® FPGA and SoC devices. Profiling and estimation tools let you customize a deep learning network by exploring design, performance, and resource utilization tradeoffs.
Model Predictive Control Toolbox™ is a tool that provides functions, an app, and Simulink® blocks for designing and simulating controllers using linear and nonlinear model predictive control (MPC). The toolbox lets you specify plant and disturbance models, horizons, constraints, and weights. By running closed-loop simulations, you can evaluate controller performance.
Vision HDL Toolbox™ is a tool that provides pixel-streaming algorithms for the design and implementation of vision systems on FPGAs and ASICs. It provides a design framework that supports a diverse set of interface types, frame sizes, and frame rates. The image processing, video, and computer vision algorithms in the toolbox use an architecture appropriate for HDL implementations.
SoC Blockset™ is a tool that provides Simulink® blocks and visualization tools for modeling, simulating, and analyzing hardware and software architectures for ASICs, FPGAs, and systems on a chip (SoC). You can build your system architecture using memory models, bus models, and I/O models, and simulate the architecture together with the algorithms.
Wireless HDL Toolbox™ is a tool that provides pre-verified, hardware-ready Simulink® blocks and subsystems for developing 5G, LTE, and custom OFDM-based wireless communication applications. It includes reference applications, IP blocks, and gateways between frame and sample-based processing.
ThingSpeak™ is an IoT analytics service that allows you to aggregate, visualize, and analyze live data streams in the cloud. ThingSpeak provides instant visualizations of data posted by your devices to ThingSpeak. With the ability to execute MATLAB® code in ThingSpeak, you can perform online analysis and process data as it comes in. ThingSpeak is often used for prototyping and proof-of-concept IoT systems that require analytics.
SEA-MAT is a collaborative effort to organize and distribute Matlab tools for the Oceanographic Community.
Gramm is a complete data visualization toolbox for Matlab. It provides an easy to use and high-level interface to produce publication-quality plots of complex data with varied statistical visualizations. Gramm is inspired by R's ggplot2 library.
hctsa is a software package for running highly comparative time-series analysis using Matlab.
Plotly is a Graphing Library for MATLAB.
YALMIP is a MATLAB toolbox for optimization modeling.
GNU Octave is a high-level interpreted language, primarily intended for numerical computations. It provides capabilities for the numerical solution of linear and nonlinear problems, and for performing other numerical experiments. It also provides extensive graphics capabilities for data visualization and manipulation.
Back to the Top
C++ is a cross-platform language that can be used to build high-performance applications developed by Bjarne Stroustrup, as an extension to the C language.
C is a general-purpose, high-level language that was originally developed by Dennis M. Ritchie to develop the UNIX operating system at Bell Labs. It supports structured programming, lexical variable scope, and recursion, with a static type system. C also provides constructs that map efficiently to typical machine instructions, which makes it one was of the most widely used programming languages today.
Embedded C is a set of language extensions for the C programming language by the C Standards Committee to address issues that exist between C extensions for different embedded systems. The extensions hep enhance microprocessor features such as fixed-point arithmetic, multiple distinct memory banks, and basic I/O operations. This makes Embedded C the most popular embedded software language in the world.
C & C++ Developer Tools from JetBrains
Open source C++ libraries on cppreference.com
C++ Graphics libraries
C++ Libraries in MATLAB
C++ Tools and Libraries Articles
Google C++ Style Guide
Introduction C++ Education course on Google Developers
C++ style guide for Fuchsia
C and C++ Coding Style Guide by OpenTitan
Chromium C++ Style Guide
C++ Core Guidelines
C++ Style Guide for ROS
Learn C++
Learn C : An Interactive C Tutorial
C++ Institute
C++ Online Training Courses on LinkedIn Learning
C++ Tutorials on W3Schools
Learn C Programming Online Courses on edX
Learn C++ with Online Courses on edX
Learn C++ on Codecademy
Coding for Everyone: C and C++ course on Coursera
C++ For C Programmers on Coursera
Top C Courses on Coursera
C++ Online Courses on Udemy
Top C Courses on Udemy
Basics of Embedded C Programming for Beginners on Udemy
C++ For Programmers Course on Udacity
C++ Fundamentals Course on Pluralsight
Introduction to C++ on MIT Free Online Course Materials
Introduction to C++ for Programmers | Harvard
Online C Courses | Harvard University
AWS SDK for C++
Azure SDK for C++
Azure SDK for C
C++ Client Libraries for Google Cloud Services
Visual Studio is an integrated development environment (IDE) from Microsoft; which is a feature-rich application that can be used for many aspects of software development. Visual Studio makes it easy to edit, debug, build, and publish your app. By using Microsoft software development platforms such as Windows API, Windows Forms, Windows Presentation Foundation, and Windows Store.
Visual Studio Code is a code editor redefined and optimized for building and debugging modern web and cloud applications.
Vcpkg is a C++ Library Manager for Windows, Linux, and MacOS.
ReSharper C++ is a Visual Studio Extension for C++ developers developed by JetBrains.
AppCode is constantly monitoring the quality of your code. It warns you of errors and smells and suggests quick-fixes to resolve them automatically. AppCode provides lots of code inspections for Objective-C, Swift, C/C++, and a number of code inspections for other supported languages. All code inspections are run on the fly.
CLion is a cross-platform IDE for C and C++ developers developed by JetBrains.
Code::Blocks is a free C/C++ and Fortran IDE built to meet the most demanding needs of its users. It is designed to be very extensible and fully configurable. Built around a plugin framework, Code::Blocks can be extended with plugins.
CppSharp is a tool and set of libraries which facilitates the usage of native C/C++ code with the .NET ecosystem. It consumes C/C++ header and library files and generates the necessary glue code to surface the native API as a managed API. Such an API can be used to consume an existing native library in your managed code or add managed scripting support to a native codebase.
Conan is an Open Source Package Manager for C++ development and dependency management into the 21st century and on par with the other development ecosystems.
High Performance Computing (HPC) SDK is a comprehensive toolbox for GPU accelerating HPC modeling and simulation applications. It includes the C, C++, and Fortran compilers, libraries, and analysis tools necessary for developing HPC applications on the NVIDIA platform.
Thrust is a C++ parallel programming library which resembles the C++ Standard Library. Thrust's high-level interface greatly enhances programmer productivity while enabling performance portability between GPUs and multicore CPUs. Interoperability with established technologies such as CUDA, TBB, and OpenMP integrates with existing software.
Boost is an educational opportunity focused on cutting-edge C++. Boost has been a participant in the annual Google Summer of Code since 2007, in which students develop their skills by working on Boost Library development.
Automake is a tool for automatically generating Makefile.in files compliant with the GNU Coding Standards. Automake requires the use of GNU Autoconf.
Cmake is an open-source, cross-platform family of tools designed to build, test and package software. CMake is used to control the software compilation process using simple platform and compiler independent configuration files, and generate native makefiles and workspaces that can be used in the compiler environment of your choice.
GDB is a debugger, that allows you to see what is going on `inside' another program while it executes or what another program was doing at the moment it crashed.
GCC is a compiler Collection that includes front ends for C, C++, Objective-C, Fortran, Ada, Go, and D, as well as libraries for these languages.
GSL is a numerical library for C and C++ programmers. It is free software under the GNU General Public License. The library provides a wide range of mathematical routines such as random number generators, special functions and least-squares fitting. There are over 1000 functions in total with an extensive test suite.
OpenGL Extension Wrangler Library (GLEW) is a cross-platform open-source C/C++ extension loading library. GLEW provides efficient run-time mechanisms for determining which OpenGL extensions are supported on the target platform.
Libtool is a generic library support script that hides the complexity of using shared libraries behind a consistent, portable interface. To use Libtool, add the new generic library building commands to your Makefile, Makefile.in, or Makefile.am.
Maven is a software project management and comprehension tool. Based on the concept of a project object model (POM), Maven can manage a project's build, reporting and documentation from a central piece of information.
TAU (Tuning And Analysis Utilities) is capable of gathering performance information through instrumentation of functions, methods, basic blocks, and statements as well as event-based sampling. All C++ language features are supported including templates and namespaces.
Clang is a production quality C, Objective-C, C++ and Objective-C++ compiler when targeting X86-32, X86-64, and ARM (other targets may have caveats, but are usually easy to fix). Clang is used in production to build performance-critical software like Google Chrome or Firefox.
OpenCV is a highly optimized library with focus on real-time applications. Cross-Platform C++, Python and Java interfaces support Linux, MacOS, Windows, iOS, and Android.
Libcu++ is the NVIDIA C++ Standard Library for your entire system. It provides a heterogeneous implementation of the C++ Standard Library that can be used in and between CPU and GPU code.
ANTLR (ANother Tool for Language Recognition) is a powerful parser generator for reading, processing, executing, or translating structured text or binary files. It's widely used to build languages, tools, and frameworks. From a grammar, ANTLR generates a parser that can build parse trees and also generates a listener interface that makes it easy to respond to the recognition of phrases of interest.
Oat++ is a light and powerful C++ web framework for highly scalable and resource-efficient web application. It's zero-dependency and easy-portable.
JavaCPP is a program that provides efficient access to native C++ inside Java, not unlike the way some C/C++ compilers interact with assembly language.
Cython is a language that makes writing C extensions for Python as easy as Python itself. Cython is based on Pyrex, but supports more cutting edge functionality and optimizations such as calling C functions and declaring C types on variables and class attributes.
Spdlog is a very fast, header-only/compiled, C++ logging library.
Infer is a static analysis tool for Java, C++, Objective-C, and C. Infer is written in OCaml.
Back to the Top
Java is a popular programming language and development platform(JDK). It reduces costs, shortens development timeframes, drives innovation, and improves application services. With millions of developers running more than 51 billion Java Virtual Machines worldwide.
The Eclipse Foundation is home to a worldwide community of developers, the Eclipse IDE, Jakarta EE and over 375 open source projects, including runtimes, tools and frameworks for Java and other languages.
Getting Started with Java
Oracle Java certifications from Oracle University
Google Developers Training
Google Developers Certification
Java Tutorial by W3Schools
Building Your First Android App in Java
Getting Started with Java in Visual Studio Code
Google Java Style Guide
AOSP Java Code Style for Contributors
Chromium Java style guide
Get Started with OR-Tools for Java
Getting started with Java Tool Installer task for Azure Pipelines
Gradle User Manual
Java SE contains several tools to assist in program development and debugging, and in the monitoring and troubleshooting of production applications.
JDK Development Tools includes the Java Web Start Tools (javaws) Java Troubleshooting, Profiling, Monitoring and Management Tools (jcmd, jconsole, jmc, jvisualvm); and Java Web Services Tools (schemagen, wsgen, wsimport, xjc).
Android Studio is the official integrated development environment for Google's Android operating system, built on JetBrains' IntelliJ IDEA software and designed specifically for Android development. Availble on Windows, macOS, Linux, Chrome OS.
IntelliJ IDEA is an IDE for Java, but it also understands and provides intelligent coding assistance for a large variety of other languages such as Kotlin, SQL, JPQL, HTML, JavaScript, etc., even if the language expression is injected into a String literal in your Java code.
NetBeans is an IDE provides Java developers with all the tools needed to create professional desktop, mobile and enterprise applications. Creating, Editing, and Refactoring. The IDE provides wizards and templates to let you create Java EE, Java SE, and Java ME applications.
Java Design Patterns is a collection of the best formalized practices a programmer can use to solve common problems when designing an application or system.
Elasticsearch is a distributed RESTful search engine built for the cloud written in Java.
RxJava is a Java VM implementation of Reactive Extensions: a library for composing asynchronous and event-based programs by using observable sequences. It extends the observer pattern to support sequences of data/events and adds operators that allow you to compose sequences together declaratively while abstracting away concerns about things like low-level threading, synchronization, thread-safety and concurrent data structures.
Guava is a set of core Java libraries from Google that includes new collection types (such as multimap and multiset), immutable collections, a graph library, and utilities for concurrency, I/O, hashing, caching, primitives, strings, and more! It is widely used on most Java projects within Google, and widely used by many other companies as well.
okhttp is a HTTP client for Java and Kotlin developed by Square.
Retrofit is a type-safe HTTP client for Android and Java develped by Square.
LeakCanary is a memory leak detection library for Android develped by Square.
Apache Spark is a unified analytics engine for large-scale data processing. It provides high-level APIs in Scala, Java, Python, and R, and an optimized engine that supports general computation graphs for data analysis. It also supports a rich set of higher-level tools including Spark SQL for SQL and DataFrames, MLlib for machine learning, GraphX for graph processing, and Structured Streaming for stream processing.
Apache Flink is an open source stream processing framework with powerful stream- and batch-processing capabilities with elegant and fluent APIs in Java and Scala.
Fastjson is a Java library that can be used to convert Java Objects into their JSON representation. It can also be used to convert a JSON string to an equivalent Java object.
libGDX is a cross-platform Java game development framework based on OpenGL (ES) that works on Windows, Linux, Mac OS X, Android, your WebGL enabled browser and iOS.
Jenkins is the leading open-source automation server. Built with Java, it provides over 1700 plugins to support automating virtually anything, so that humans can actually spend their time doing things machines cannot.
DBeaver is a free multi-platform database tool for developers, SQL programmers, database administrators and analysts. Supports any database which has JDBC driver (which basically means - ANY database). EE version also supports non-JDBC datasources (MongoDB, Cassandra, Redis, DynamoDB, etc).
Redisson is a Redis Java client with features of In-Memory Data Grid. Over 50 Redis based Java objects and services: Set, Multimap, SortedSet, Map, List, Queue, Deque, Semaphore, Lock, AtomicLong, Map Reduce, Publish / Subscribe, Bloom filter, Spring Cache, Tomcat, Scheduler, JCache API, Hibernate, MyBatis, RPC, and local cache.
GraalVM is a universal virtual machine for running applications written in JavaScript, Python, Ruby, R, JVM-based languages like Java, Scala, Clojure, Kotlin, and LLVM-based languages such as C and C++.
Gradle is a build automation tool for multi-language software development. From mobile apps to microservices, from small startups to big enterprises, Gradle helps teams build, automate and deliver better software, faster. Write in Java, C++, Python or your language of choice.
Apache Groovy is a powerful, optionally typed and dynamic language, with static-typing and static compilation capabilities, for the Java platform aimed at improving developer productivity thanks to a concise, familiar and easy to learn syntax. It integrates smoothly with any Java program, and immediately delivers to your application powerful features, including scripting capabilities, Domain-Specific Language authoring, runtime and compile-time meta-programming and functional programming.
JaCoCo is a free code coverage library for Java, which has been created by the EclEmma team based on the lessons learned from using and integration existing libraries for many years.
Apache JMeter is used to test performance both on static and dynamic resources, Web dynamic applications. It also used to simulate a heavy load on a server, group of servers, network or object to test its strength or to analyze overall performance under different load types.
Junit is a simple framework to write repeatable tests. It is an instance of the xUnit architecture for unit testing frameworks.
Mockito is the most popular Mocking framework for unit tests written in Java.
SpotBugs is a program which uses static analysis to look for bugs in Java code.
SpringBoot is a great tool that helps you to create Spring-powered, production-grade applications and services with absolute minimum fuss. It takes an opinionated view of the Spring platform so that new and existing users can quickly get to the bits they need.
YourKit is a technology leader, creator of the most innovative and intelligent tools for profiling Java & .NET applications.
Back to the Top
Python is an interpreted, high-level programming language. Python is used heavily in the fields of Data Science and Machine Learning.
Python Developer's Guide is a comprehensive resource for contributing to Python – for both new and experienced contributors. It is maintained by the same community that maintains Python.
Azure Functions Python developer guide is an introduction to developing Azure Functions using Python. The content below assumes that you've already read the Azure Functions developers guide.
CheckiO is a programming learning platform and a gamified website that teaches Python through solving code challenges and competing for the most elegant and creative solutions.
Python Institute
PCEP – Certified Entry-Level Python Programmer certification
PCAP – Certified Associate in Python Programming certification
PCPP – Certified Professional in Python Programming 1 certification
PCPP – Certified Professional in Python Programming 2
MTA: Introduction to Programming Using Python Certification
Getting Started with Python in Visual Studio Code
Google's Python Style Guide
Google's Python Education Class
Piton asli
The Python Open Source Computer Science Degree by Forrest Knight
Intro to Python for Data Science
Intro to Python by W3schools
Codecademy's Python 3 course
Learn Python with Online Courses and Classes from edX
Python Courses Online from Coursera
Python Package Index (PyPI) is a repository of software for the Python programming language. PyPI helps you find and install software developed and shared by the Python community.
PyCharm is the best IDE I've ever used. With PyCharm, you can access the command line, connect to a database, create a virtual environment, and manage your version control system all in one place, saving time by avoiding constantly switching between windows.
Python Tools for Visual Studio(PTVS) is a free, open source plugin that turns Visual Studio into a Python IDE. It supports editing, browsing, IntelliSense, mixed Python/C++ debugging, remote Linux/MacOS debugging, profiling, IPython, and web development with Django and other frameworks.
Pylance is an extension that works alongside Python in Visual Studio Code to provide performant language support. Under the hood, Pylance is powered by Pyright, Microsoft's static type checking tool.
Pyright is a fast type checker meant for large Python source bases. It can run in a “watch” mode and performs fast incremental updates when files are modified.
Django is a high-level Python Web framework that encourages rapid development and clean, pragmatic design.
Flask is a micro web framework written in Python. It is classified as a microframework because it does not require particular tools or libraries.
Web2py is an open-source web application framework written in Python allowing allows web developers to program dynamic web content. One web2py instance can run multiple web sites using different databases.
AWS Chalice is a framework for writing serverless apps in python. It allows you to quickly create and deploy applications that use AWS Lambda.
Tornado is a Python web framework and asynchronous networking library. Tornado uses a non-blocking network I/O, which can scale to tens of thousands of open connections.
HTTPie is a command line HTTP client that makes CLI interaction with web services as easy as possible. HTTPie is designed for testing, debugging, and generally interacting with APIs & HTTP servers.
Scrapy is a fast high-level web crawling and web scraping framework, used to crawl websites and extract structured data from their pages. It can be used for a wide range of purposes, from data mining to monitoring and automated testing.
Sentry is a service that helps you monitor and fix crashes in realtime. The server is in Python, but it contains a full API for sending events from any language, in any application.
Pipenv is a tool that aims to bring the best of all packaging worlds (bundler, composer, npm, cargo, yarn, etc.) to the Python world.
Python Fire is a library for automatically generating command line interfaces (CLIs) from absolutely any Python object.
Bottle is a fast, simple and lightweight WSGI micro web-framework for Python. It is distributed as a single file module and has no dependencies other than the Python Standard Library.
CherryPy is a minimalist Python object-oriented HTTP web framework.
Sanic is a Python 3.6+ web server and web framework that's written to go fast.
Pyramid is a small and fast open source Python web framework. It makes real-world web application development and deployment more fun and more productive.
TurboGears is a hybrid web framework able to act both as a Full Stack framework or as a Microframework.
Falcon is a reliable, high-performance Python web framework for building large-scale app backends and microservices with support for MongoDB, Pluggable Applications and autogenerated Admin.
Neural Network Intelligence(NNI) is an open source AutoML toolkit for automate machine learning lifecycle, including Feature Engineering, Neural Architecture Search, Model Compression and Hyperparameter Tuning.
Dash is a popular Python framework for building ML & data science web apps for Python, R, Julia, and Jupyter.
Luigi is a Python module that helps you build complex pipelines of batch jobs. It handles dependency resolution, workflow management, visualization etc. It also comes with Hadoop support built-in.
Locust is an easy to use, scriptable and scalable performance testing tool.
spaCy is a library for advanced Natural Language Processing in Python and Cython.
NumPy is the fundamental package needed for scientific computing with Python.
Pillow is a friendly PIL(Python Imaging Library) fork.
IPython is a command shell for interactive computing in multiple programming languages, originally developed for the Python programming language, that offers enhanced introspection, rich media, additional shell syntax, tab completion, and rich history.
GraphLab Create is a Python library, backed by a C++ engine, for quickly building large-scale, high-performance machine learning models.
Pandas is a fast, powerful, and easy to use open source data structrures, data analysis and manipulation tool, built on top of the Python programming language.
PuLP is an Linear Programming modeler written in python. PuLP can generate LP files and call on use highly optimized solvers, GLPK, COIN CLP/CBC, CPLEX, and GUROBI, to solve these linear problems.
Matplotlib is a 2D plotting library for creating static, animated, and interactive visualizations in Python. Matplotlib produces publication-quality figures in a variety of hardcopy formats and interactive environments across platforms.
Scikit-Learn is a simple and efficient tool for data mining and data analysis. It is built on NumPy,SciPy, and mathplotlib.
Back to the Top
Scala is a combination of object-oriented and functional programming in one concise, high-level language. Scala's static types help avoid bugs in complex applications, and its JVM and JavaScript runtimes let you build high-performance systems with easy access to huge ecosystems of libraries.
Scala Style Guide
Databricks Scala Style Guide
Data Science using Scala and Spark on Azure
Creating a Scala Maven application for Apache Spark in HDInsight using IntelliJ
Intro to Spark DataFrames using Scala with Azure Databricks
Using Scala to Program AWS Glue ETL Scripts
Using Flink Scala shell with Amazon EMR clusters
AWS EMR and Spark 2 using Scala from Udemy
Using the Google Cloud Storage connector with Apache Spark
Write and run Spark Scala jobs on Cloud Dataproc for Google Cloud
Scala Courses and Certifications from edX
Scala Courses from Coursera
Top Scala Courses from Udemy
Apache Spark is a unified analytics engine for large-scale data processing. It provides high-level APIs in Scala, Java, Python, and R, and an optimized engine that supports general computation graphs for data analysis. It also supports a rich set of higher-level tools including Spark SQL for SQL and DataFrames, MLlib for machine learning, GraphX for graph processing, and Structured Streaming for stream processing.
Apache Spark Connector for SQL Server and Azure SQL is a high-performance connector that enables you to use transactional data in big data analytics and persists results for ad-hoc queries or reporting. The connector allows you to use any SQL database, on-premises or in the cloud, as an input data source or output data sink for Spark jobs.
Azure Databricks is a fast and collaborative Apache Spark-based big data analytics service designed for data science and data engineering. Azure Databricks, sets up your Apache Spark environment in minutes, autoscale, and collaborate on shared projects in an interactive workspace. Azure Databricks supports Python, Scala, R, Java, and SQL, as well as data science frameworks and libraries including TensorFlow, PyTorch, and scikit-learn.
Apache PredictionIO is an open source machine learning framework for developers, data scientists, and end users. It supports event collection, deployment of algorithms, evaluation, querying predictive results via REST APIs. It is based on scalable open source services like Hadoop, HBase (and other DBs), Elasticsearch, Spark and implements what is called a Lambda Architecture.
Cluster Manager for Apache Kafka(CMAK) is a tool for managing Apache Kafka clusters.
BigDL is a distributed deep learning library for Apache Spark. With BigDL, users can write their deep learning applications as standard Spark programs, which can directly run on top of existing Spark or Hadoop clusters.
Eclipse Deeplearning4J (DL4J) is a set of projects intended to support all the needs of a JVM-based(Scala, Kotlin, Clojure, and Groovy) deep learning application. This means starting with the raw data, loading and preprocessing it from wherever and whatever format it is in to building and tuning a wide variety of simple and complex deep learning networks.
Play Framework is a web framework combines productivity and performance making it easy to build scalable web applications with Java and Scala.
Dotty is a research compiler that will become Scala 3.
AWScala is a tool that enables Scala developers to easily work with Amazon Web Services in the Scala way.
Scala.js is a compiler that converts Scala to JavaScript.
Polynote is an experimental polyglot notebook environment. Currently, it supports Scala and Python (with or without Spark), SQL, and Vega.
Scala Native is an optimizing ahead-of-time compiler and lightweight managed runtime designed specifically for Scala.
Gitbucket is a Git platform powered by Scala with easy installation, high extensibility & GitHub API compatibility.
Finagle is a fault tolerant, protocol-agnostic RPC system
Gatling is a load test tool. It officially supports HTTP, WebSocket, Server-Sent-Events and JMS.
Scalatra is a tiny Scala high-performance, async web framework, inspired by Sinatra.
Back to the Top
R is an open source software environment for statistical computing and graphics. It compiles and runs on a wide variety of platforms such as Windows and MacOS.
An Introduction to R
Google's R Style Guide
R developer's guide to Azure
Running R at Scale on Google Compute Engine
Running R on AWS
RStudio Server Pro for AWS
Learn R by Codecademy
Learn R Programming with Online Courses and Lessons by edX
R Language Courses by Coursera
Learn R For Data Science by Udacity
RStudio is an integrated development environment for R and Python, with a console, syntax-highlighting editor that supports direct code execution, and tools for plotting, history, debugging and workspace management.
Shiny is a newer package from RStudio that makes it incredibly easy to build interactive web applications with R.
Rmarkdown is a package helps you create dynamic analysis documents that combine code, rendered output (such as figures), and prose.
Rplugin is R Language supported plugin for the IntelliJ IDE.
Plotly is an R package for creating interactive web graphics via the open source JavaScript graphing library plotly.js.
Metaflow is a Python/R library that helps scientists and engineers build and manage real-life data science projects. Metaflow was originally developed at Netflix to boost productivity of data scientists who work on a wide variety of projects from classical statistics to state-of-the-art deep learning.
Prophet is a procedure for forecasting time series data based on an additive model where non-linear trends are fit with yearly, weekly, and daily seasonality, plus holiday effects. It works best with time series that have strong seasonal effects and several seasons of historical data.
LightGBM is a gradient boosting framework that uses tree based learning algorithms, used for ranking, classification and many other machine learning tasks.
Dash is a Python framework for building analytical web applications in Python, R, Julia, and Jupyter.
MLR is Machine Learning in R.
ML workspace is an all-in-one web-based IDE specialized for machine learning and data science. It is simple to deploy and gets you started within minutes to productively built ML solutions on your own machines. ML workspace is the ultimate tool for developers preloaded with a variety of popular data science libraries (Tensorflow, PyTorch, Keras, and MXnet) and dev tools (Jupyter, VS Code, and Tensorboard) perfectly configured, optimized, and integrated.
CatBoost is a fast, scalable, high performance Gradient Boosting on Decision Trees library, used for ranking, classification, regression and other machine learning tasks for Python, R, Java, C++. Supports computation on CPU and GPU.
Plumber is a tool that allows you to create a web API by merely decorating your existing R source code with special comments.
Drake is an R-focused pipeline toolkit for reproducibility and high-performance computing.
DiagrammeR is a package you can create, modify, analyze, and visualize network graph diagrams. The output can be incorporated into R Markdown documents, integrated with Shiny web apps, converted to other graph formats, or exported as image files.
Knitr is a general-purpose literate programming engine in R, with lightweight API's designed to give users full control of the output without heavy coding work.
Broom is a tool that converts statistical analysis objects from R into tidy format.
Back to the Top
Julia is a high-level, high-performance dynamic language for technical computing. Julia programs compile to efficient native code for multiple platforms via LLVM.
JuliaHub contains over 4,000 Julia packages for use by the community.
Julia Observer
Julia Manual
JuliaLang Essentials
Julia Style Guide
Julia By Example
JuliaLang Gitter
DataFrames Tutorial using Jupyter Notebooks
Julia Academy
Julia Meetup groups
Julia on Microsoft Azure
JuliaPro is a free and fast way to setup Julia for individual researchers, engineers, scientists, quants, traders, economists, students and others. Julia developers can build better software quicker and easier while benefiting from Julia's unparalleled high performance. It includes 2600+ open source packages or from a curated list of 250+ JuliaPro packages. Curated packages are tested, documented and supported by Julia Computing.
Juno is a powerful, free IDE based on Atom for the Julia language.
Debugger.jl is the Julia debuggin tool.
Profile (Stdlib) is a module provides tools to help developers improve the performance of their code. When used, it takes measurements on running code, and produces output that helps you understand how much time is spent on individual line's.
Revise.jl allows you to modify code and use the changes without restarting Julia. With Revise, you can be in the middle of a session and then update packages, switch git branches, and/or edit the source code in the editor of your choice; any changes will typically be incorporated into the very next command you issue from the REPL. This can save you the overhead of restarting Julia, loading packages, and waiting for code to JIT-compile.
JuliaGPU is a Github organization created to unify the many packages for programming GPUs in Julia. With its high-level syntax and flexible compiler, Julia is well positioned to productively program hardware accelerators like GPUs without sacrificing performance.
IJulia.jl is the Julia kernel for Jupyter.
AWS.jl is a Julia interface for Amazon Web Services.
CUDA.jl is a package for the main programming interface for working with NVIDIA CUDA GPUs using Julia. It features a user-friendly array abstraction, a compiler for writing CUDA kernels in Julia, and wrappers for various CUDA libraries.
XLA.jl is a package for compiling Julia to XLA for Tensor Processing Unit(TPU).
Nanosoldier.jl is a package for running JuliaCI services on MIT's Nanosoldier cluster.
Julia for VSCode is a powerful extension for the Julia language.
JuMP.jl is a domain-specific modeling language for mathematical optimization embedded in Julia.
Optim.jl is a univariate and multivariate optimization in Julia.
RCall.jl is a package that allows you to call R functions from Julia.
JavaCall.jl is a package that allows you to call Java functions from Julia.
PyCall.jl is a package that allows you to call Python functions from Julia.
MXNet.jl is the Apache MXNet Julia package. MXNet.jl brings flexible and efficient GPU computing and state-of-art deep learning to Julia.
Knet is the Koç University deep learning framework implemented in Julia by Deniz Yuret and collaborators. It supports GPU operation and automatic differentiation using dynamic computational graphs for models defined in plain Julia.
Distributions.jl is a Julia package for probability distributions and associated functions.
DataFrames.jl is a tool for working with tabular data in Julia.
Flux.jl is an elegant approach to machine learning. It's a 100% pure-Julia stack, and provides lightweight abstractions on top of Julia's native GPU and AD support.
IRTools.jl is a simple and flexible IR format, expressive enough to work with both lowered and typed Julia code, as well as external IRs.
Cassette.jl is a Julia package that provides a mechanism for dynamically injecting code transformation passes into Julia's just-in-time (JIT) compilation cycle, enabling post hoc analysis and modification of "Cassette-unaware" Julia programs without requiring manual source annotation or refactoring of the target code.
Back to the Top
Distributed under the Creative Commons Attribution 4.0 International (CC BY 4.0) Public License.
