Stanford CS229 Machine Learning vs Deep 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 strong intuition-building and the NumPy-first implementation in Course 1, but reviewers note the curriculum predates Transformers and LLMs and the final Sequence Models course lands less cleanly than the earlier ones.

Andrew Ng's pedagogy gets near-universal praise across HN and blogs over an eight-year window. Multiple reviewers describe him as the clearest ML instructor they have ever had; critical comments are essentially absent.

Strong content per dollar at the $49/month Coursera price for learners who finish in 2-3 months, but the subscription model penalises slow learners and the paywall around graded assignments draws consistent complaints.

Browser-hosted Jupyter notebooks with auto-grading remove install friction, and the DeepLearning.AI community forum is active. Several reviewers flag homework infrastructure as occasionally flaky.

Builds a credible foundation and the bias/variance and error-analysis material in Course 3 transfers directly to real work. Reviewers consistently note you still need projects, Kaggle or a portfolio before the certificate matters to employers.