A complete, self-study learning path through core machine-learning and deep-learning algorithms. Each chapter is self-contained: theory notes (.md), from-scratch + library code (.py), exercises with answer keys, and the figures the code produces — read, run, and verify in one place.

Covers: fundamentals & feature engineering, linear/logistic regression, decision trees & random forests, KNN & SVM, clustering, neural networks, CNN/RNN/LSTM and Transformers.