ML Fundamentals

Andrew Ng's lecture notes and problem sets covering supervised learning, unsupervised learning, and the mathematical foundations.

The canonical ML reference: linear models, decision trees, SVMs, ensembles, and neural nets. Free PDF from the authors.

Free textbook building intuition for linear algebra, multivariate calculus, probability, and optimisation as ML foundations.

Top-down, code-first course covering the full ML stack from tabular data to deep learning. Excellent complement to bottom-up courses.

Official hands-on tutorials for classification, regression, clustering, cross-validation, and pipeline construction in scikit-learn.

Short, dense survey of 12 practical lessons from ML research — generalization, overfitting, the curse of dimensionality, and feature engineering.

The standard Python ML library: classification, regression, clustering, model selection, preprocessing. Consistent API and excellent documentation.

Experiment tracking, hyperparameter sweeps, and model visualization. Free for academic use. Integrates with PyTorch, scikit-learn, and HuggingFace.

The classic repository of 600+ datasets for benchmarking ML algorithms, covering classification, regression, and clustering tasks.

Built-in datasets (iris, diabetes, Boston, digits) for quick prototyping. Directly loadable with a single function call — no download required.

Open platform with 20,000+ datasets and benchmarking suites. Integrates directly with scikit-learn for reproducible ML experiments.