Machine Learning from First Principles

Appendix D

Course Map

Where each topic of three widely used Stanford courses (CS229 Machine Learning, CS231n Deep Learning for Computer Vision, and CS230 Deep Learning) is covered in this book.

This book is independent and not affiliated with Stanford University or its courses. The tables below map the topics listed on the public course pages (https://cs229.stanford.edu, https://cs231n.stanford.edu, https://cs230.stanford.edu) to the chapters, sections, and projects that cover them, so that a reader following one of these courses can find the matching material. Course syllabi change from year to year; the mapping follows the 2025 offerings.

D.1CS229: Machine Learning

Course topicWhere in this book
Supervised learning setupSection 1.3
Linear regression, normal equations, LMSChapter 4; Project 1
Probabilistic interpretation, locally weighted regressionSections 4.4 and 4.7
Logistic regression, perceptron, Newton’s methodChapter 6, Sections 6.6, 6.7, and 3.8
Exponential family and generalized linear modelsChapter 7
Generative learning: GDA, Naive Bayes, Laplace smoothingSections 8.5 and 8.4; Project 2
Kernels and support vector machinesChapter 9; Project 8
Neural networks and backpropagationChapter 15; Project 3
Bias–variance, regularization, model selection, cross-validationChapters 5 and 12
Learning theory: sample complexity, VC dimensionChapter 11
Double descent and the modern view of generalizationSections 5.6 and 11.7
Decision trees, bagging, boostingChapter 10
$k$-means, mixtures of Gaussians, EMChapter 13; Project 4
Factor analysisSection 13.8
PCA and ICAChapter 14, Section 14.8; Project 5
Self-supervised learning and foundation modelsChapters 26 and 24
MDPs, value iteration, policy iteration, model learningSections 27.1 and 27.2
Continuous states, fitted value iterationSection 27.3
LQR, DDP, LQGSection 27.4
Policy gradient (REINFORCE)Section 27.6
Advice for applying machine learningChapters 12 and 20

D.2CS231n: Deep Learning for Computer Vision

Course topicWhere in this book
Image classification, $k$-nearest neighborsSection 17.1, Chapter 8; Project 9
Linear classifiers, SVM and softmax lossesSections 17.2 and 9.8; Project 9
Regularization and optimizationChapters 3 and 5, Section 16.4
Neural networks and backpropagationChapter 15; Project 9
Convolutional networksSections 17.3, 17.4, and 17.5
CNN architectures and trainingSections 17.6 and 17.7, Chapter 16
Recurrent networks, LSTMs, image captioningChapter 18; Project 10
Attention and Transformers, Vision TransformersChapter 19, Section 19.9
Object detection and segmentationChapter 21; Project 11
Visualizing and understanding, adversarial examples, style transferChapter 22; Project 12
Video understandingSection 23.1
Large-scale distributed trainingSection 20.6
Self-supervised learningChapter 26
Generative models: VAEs, GANs, autoregressive, diffusion, flowsChapter 25; Project 7
3D vision: representations, NeRF, Gaussian splattingSections 23.2 and 23.3
Vision and languageSections 23.4 and 26.6
Robot learningSection 27.8, Chapter 27

D.3CS230: Deep Learning

Course topicWhere in this book
Neural network basics, vectorizationChapter 15, Appendix A
Initialization, regularization, batch normalizationSections 16.1, 16.3, and 16.4
Optimization algorithms, hyperparameter tuningChapter 3, Section 16.6
Structuring projects: metrics, splits, error analysisSections 20.1, 20.2, and 20.3
Mismatched data, transfer, multitask, end-to-end learningSections 20.4 and 20.5
Convolutional and recurrent networksChapters 17 and 18
Adversarial examples and GANsSection 22.4, Section 25.4
InterpretabilityChapter 22
Deep reinforcement learningSections 27.5 and 27.6
Deployment and efficient inferenceSection 20.7

D.4Reading Paths

  • A machine learning course (CS229-style). Parts I–III, then Chapter 15, Chapter 26, and Chapter 27, with Projects 1–5 and 8.
  • A computer vision course (CS231n-style). Chapters 3, 4, and 6 as needed, then Part IV and Part V, Chapters 25 and 26, and Section 27.8, with Projects 3, 9, 10, 11, and 12.
  • A practical deep learning course (CS230-style). Chapters 15, 16, 17, 18, 20, and 22, with Projects 3, 6, and 9.
Machine Learning from First Principles · Edition 2.0 · Companion site to the PDF book.