Lecture dates and homework assignment dates are subject to change.

Dates Topics Homework and reading assignments
9/7 Overview HW0 (due 9/12); CML 1.1–1.2; ESL 1, 2.1–2.3
Non-parametric methods
9/7, 9/12 Nearest neighbors HW1 (due 9/21); CML 2.2–2.3, 2.5; ESL 2.4–2.6, 13.3
9/14 K-D and decision trees CML 1.3–1.9; ESL 9.2
Parametric methods
9/19, 9/21 Prob/stats & validation Grinstead & Snell 9.1; CML 4.6; ESL 7.10
9/21, 9/26 Generative models HW2 (due 10/3); CML 7.1–7.5; ESL 4.3 (optional: 4.3.1–4.3.3)
9/28 Linear classifiers CML 3, 6.1; ESL 4.4 (optional: 4.4.4), 4.5; (optional: voted-perceptron)
10/3 Features and kernels HW3 (due 10/13); CML 4.1–4.4, 9.1, 9.2, 9.4; notes on kernels 1.1
10/5 Support vector machines CML 6.1, 6.7; ESL 4.5.2, 12.1–12.3.4; SVM tutorial 3.1-3.7, 4.1-4.4
10/10 Convex optimization CML 6.2–6.4; CO 2.1–2.3, 3.1–3.2, 4.1–4.4
10/12 Optimization methods HW4 (due 10/31); CML 6.5, 12.2; CO 9.2–9.3; stochastic gradient tricks
10/17 Neural networks CML 8; efficient backprop paper; (optional: backprop derivation)
10/19 Exam 1 (501 NWC and 420 Pupin)
Reductions
10/24, 10/26 Ensemble methods introduction to Boosting book; CML 11.1–11.3; notes on AdaBoost
10/26, 10/31 Objectives CML 4.5, 5.1; notes on loss functions
10/31 Reductions CML 5.1-5.2; reductions survey; overview paper
Linear regression
11/2 Ordinary least squares HW5 (due 11/28); ESL 3.1, 3.2 (3.2.3–3.2.4 optional)
11/9 Societal consequences ML + privacy survey; bias in ML
11/14 Regularization ESL 3.4.1–3.4.3, 3.5.1
Representation learning
11/16 Dimension reduction CML 13.2; ESL 14.5.1; PCA notes 5.1, 5.2, 5.4
11/21 Collaborative filtering BellKor paper pages 42-45.
11/23 Clustering CML 2.4, 13.1
11/28, 11/30 Latent variable models CML 14.1, 14.2; ESL 8.5; annotation model paper
12/5, 12/7 Graphical models (Guest video lecture)
12/12 Exam 2 (501 NWC and 420 Pupin)