Lectures

Lecture topics calendar

This is a preliminary weekly topic plan adapted from a recent evening offering of CSEP 546. Topics and readings may shift during the quarter.
Lecture meets Monday, 6:30–9:20 PM in CSE2 G10. Class dates: October 5, 12, 19, 26; November 2, 9, 16, 23, 30; December 7. Slides will be added as the quarter progresses.
Eight quizzes: October 12, 19, 26; November 2, 9, 16, 23, 30. Each has three questions; the best six count. No quiz on December 7.
The UW registrar calendar has no Monday holidays during this schedule. November 23 and November 30 are class days. Regular instruction ends December 11; there is no regular lecture December 14.
Date Content Reading Slides Quiz
Introduction to ML, Maximum Likelihood, Linear Methods, Overfitting, Regularization, Optimization
10/05 Welcome/Overview, probability review, MLE through introductory Gaussian models Probability review: Murphy 2.1-2.4, 2.6, 2.8, 3.1-3.2
Statistics review: Murphy 4.2
Linear algebra review: Murphy 7.1-7.3
Matrix calculus review: Murphy 7.8
Maximum likelihood: Murphy 4.2 		Week 1 slides
Annotated slides		 No quiz
10/12 Linear regression with basis functions, Overfitting Linear regression: Murphy 11-11.2
Cross validation: Murphy 4.5.5, 5.4.1.2, 5.4.2 		Week 2 slides Quiz 1
10/19 Bias-variance, Ridge regression, Lasso Bias-variance trade-off: Murphy 4.7.6
Regularized linear regression: Murphy 11.3-11.4 		Week 3 slides Quiz 2
10/26 Prediction pitfalls, Gradient descent, Convexity, Logistic regression Gradient descent: Murphy 8-8.2.1
Logistic regression: Murphy 10-10.2.4, 10.3-10.3.3 		Quiz 3
11/02 SGD, Logistic regression, Prediction pitfalls Stochastic gradient descent: Murphy 8.4-8.4.4
Logistic regression: Murphy 10-10.2.4, 10.3-10.3.3
Neural networks: Murphy 13-13.4.3 		Quiz 4
11/09 Nearest neighbors, Bootstrap, SVMs, Kernels Nearest neighbors: Murphy 16.1
Bootstrap: Efron and Hastie 10.2, 11-11.2
Kernels: Bishop 6-6.2 		Quiz 5
11/16 Neural networks, Trees Neural networks: Murphy 13-13.4.3
Trees, random forests, gradient boosting trees: Murphy 18 		Quiz 6
Unsupervised learning, feature learning
11/23 Boosting and ensembling methods; PCA, SVD, and k-means Boosting and ensembles: Murphy 18
PCA and SVD: Murphy 20.1, 20.3
K-means: Murphy 21.3 		Quiz 7
11/30 CNNs, attention, transformers, and sequence models CNNs: ZLLS 7-8
Attention and transformers: ZLLS 9-11
Sequence models: ZLLS 9-11 		Quiz 8
12/07 Domain-specific models, online learning Self-supervised and transfer learning: Murphy 19
CNNs: ZLLS 7-8
Sequence models: ZLLS 9-11
Online learning: Shalev-Shwartz, Ben-David 		No quiz