Basic4AI

illustrate

Summary of basic knowledge of machine learning, deep learning, and natural language processing.

Currently, it mainly refers to Teacher Li Hang's book "Statistical Learning Methods", and some contents such as XGBoost , clustering , deep learning-related content , NLP-related content , etc. are not mentioned in the book.

Since github's markdown parser does not support latex, the notes need to be used locally to browse normally, and you can also directly access the blog link given below.

The Document folder is notes, the Code folder is code, the Data folder is the data set used by certain codes, and the Image folder is the pictures used in the Notes section.

Due to limited time and energy, some of the code comes from github open source projects, such as Seq2Seq, Transformer and other parts of the code, and some chapter codes are to be supplemented.

Machine Learning

• Linear Regression (Notes)
• Perception machine (notes + code)
• KNN (Notes + Code)
• Naive Bayes (notes + code)
• Decision Tree (Notes + Code)
• Logistic regression (notes + code)
• Maximum entropy (notes + code)
• SVM (notes + code)
• AdaBoost (notes + code)
• GBDT (notes + code)
• EM algorithm (notes + code)
• Hidden Markov model (notes + code)
• Conditional Random Field (Notes)
• Random Forest (Notes + Code)
• XGBoost (Notes)
• Clustering (notes)
• Feature selection of feature engineering (notes)
• Dimensional reduction algorithm for feature engineering (notes)

Deep Learning

• Neural Network (Notes + Code)
• RNN (Notes)
• LSTM and GRU (Notes)
• CNN (Notes)
• Optimization Methods in Deep Learning (Notes)

Natural Language Processing

• Word2Vec (Notes)
• GloVe (Notes)
• FastText (notes)
• TextCNN (Notes + Code)
• Seq2Seq (notes + code)
• Transformer (notes + code)
• BERT (Notes)
• LSTM+CRF for sequence annotation (notes)
• Theme model (notes)