Stanford CS229 Machine Learning vs Machine Learning Specialization

Reviewers consistently praise the mathematical depth — full derivations of GLMs, SVMs, EM, factor analysis and learning theory. The honest caveat is that the curriculum predates the Transformer era and deep learning gets brief treatment.

Andrew Ng's blackboard teaching gets repeated praise — one HN reviewer specifically prefers it to the Coursera version because he uses the board. The lecture pacing is academic and unhurried, which some find rigorous and others find slow.

Completely free — full 2018 lecture series on YouTube, all lecture notes, problem sets and section materials at cs229.stanford.edu. No certificate, no grading, no paywall. Reviewers consistently call it the highest-value rigorous ML resource available.

Zero official support for the YouTube cohort — no forum, no grading, no TA office hours, no cs50.ai-style tutor. Self-learners rely on community GitHub repos for solutions. Honest weakness, not unique to CS229.

Theory transfers durably — gradient descent, GLMs, regularisation, EM and learning theory remain foundational. The honest gap is that CS229 was not designed as a practical-first course; deployment, modern frameworks and Transformers are out of scope.

Praised for intuitive explanations and the expanded neural networks unit, but reviewers note the new version trades depth for accessibility — backprop is brushed past, RL feels like a preview.

Andrew Ng's pedagogy gets near-universal praise across HN and blogs. Multiple commenters describe him as the best instructor they ever had; complaints are essentially absent.

Content is strong relative to cost, and auditing remains possible. The friction comes from Coursera's subscription gating around grading and certificates — a recurring HN gripe.

Browser-hosted Jupyter notebooks with auto-grading remove a major friction point from the original. The community forum is active but not deeply mentioned in reviews.

Builds a real foundation in ideas and Python tooling, but datasets are clean and deployment is out of scope. Reviewers flag the need to supplement with Kaggle or a portfolio project.