Stanford Center for Professional Development
Study Hub

Stanford SCPD
Interactive Course Materials

Deep dives, slide decks, and animated guides for XCS229 Machine Learning and XCS236 Deep Generative Models. Each page is a standalone interactive reference with diagrams, worked examples, and theme toggle.

XCS229 Machine Learning
Andrew Ng's foundational ML course covering supervised learning, unsupervised learning, and reinforcement learning. Theory-heavy with mathematical rigor and practical problem sets.
Overview
Overview XCS229 Course Overview deep dive
Lectures
Lecture 01 Linear Regression deep dive Lecture 02 Logistic Regression deep dive Lecture 03 Generalized Linear Models deep dive Lecture 04 Generative Algorithms deep dive Lecture 05 SVM & Kernel Methods deep dive Lecture 06 Decision Trees & Ensembles deep dive Lecture 07 Neural Networks deep dive Lecture 08 Unsupervised Learning deep dive Lecture 09 PCA & ICA deep dive Lecture 10 Bias-Variance Tradeoff deep dive Lecture 11 Reinforcement Learning deep dive
Problem Sets
Problem Set 1 Linear & Logistic Regression deep dive Problem Set 2 Bayesian & Kernel Methods deep dive Problem Set 3 Trees, Ensembles & NNs deep dive Problem Set 4 Unsupervised & EM deep dive Problem Set 5 RL & Review deep dive
Supplementary Topics
Supplement Linear Algebra Review deep dive Supplement Kernel Methods deep dive Supplement Autoencoders deep dive Supplement Transformers slides Supplement CNN & RNN slides Supplement KV Cache deep dive slides guide Supplement Problem Sets Overview deep dive
XCS236 Deep Generative Models
Comprehensive study of deep generative models — from autoregressive and latent variable models through normalizing flows, GANs, energy-based models, score-based models, and diffusion. Covers both theory and modern practice.
Overview
Overview XCS236 Course Overview deep dive
Lectures
Lecture 01 Introduction to Generative Models deep dive Lecture 02 Autoregressive Models deep dive Lecture 03 MLE & Latent Variables deep dive Lecture 04 Variational Autoencoders deep dive Lecture 05 Normalizing Flows deep dive Lecture 06 Generative Adversarial Networks deep dive Lecture 07 Energy-Based Models deep dive Lecture 08 Score-Based Models deep dive Lecture 09 Diffusion Models deep dive Lecture 10 Evaluation & Metrics deep dive
Problem Sets
Problem Set 1 Autoregressive & Latent Variable deep dive Problem Set 2 VAE, Flows & GANs deep dive Problem Set 3 EBMs, Score & Diffusion deep dive
Built with the nafSadh/scpd project