Basic4AI

Why we included this project

This repo collects study notes and matching Python code for the core algorithms in machine learning, deep learning, and NLP. The machine learning half follows Li Hang's Statistical Learning Methods fairly closely, covering linear regression, SVM, AdaBoost, HMMs, conditional random fields, and clustering, with extra material like XGBoost and feature engineering that the book doesn't include. The deep learning and NLP sections go further, with notes on neural networks, RNN/LSTM/GRU, CNN, word embeddings such as Word2Vec and GloVe, and models like TextCNN, Seq2Seq, Transformer, and BERT. The notes are Markdown with LaTeX that renders properly in Typora, and each topic links to a companion blog post, so it reads best as a self-paced reference rather than something you'd install. Students prepping for interviews or coursework, and developers wanting a code-backed refresher on classic algorithms, will get the most out of it.