Calendar

Topics are subject to update.

Class schedule

Date

Event

Assignment

Reading

Sep/4

Lecture 1 Introduction and foundations

HW0 out

[M1]
Ch 1

Sep/9

Lecture 2 Empirical risk minimization, maximum likelihood

HW1 out

[M1]
Ch 4.2

Sep/11

Lecture 3 Bayesian learning

[M1]
Ch 4.6.1–4.6.4

Sep/16

Lecture 4 Linear regression

HW0 due
HW1 due
HW2 out

[M1]
Ch 11.1–11.3

Sep/18

Lecture 5 Uncertainty quantification, regularizers

[M1]
Ch 11.7.1–11.7.5

Sep/23

Lecture 6 Features, kernels

[M1]
Ch 2.1.2, 11.3–11.3.1, 17.1, 4.5–4.5.3

Sep/25

Lecture 7 Evaluation, hyperparameter learning

[JWHT] Ch 5.1 (best)

[M1] Ch 5.4.3 (brief)

[SB] Ch 11.2 (optional)

Sep/30

Lecture 8 Classification, intro to optimization

HW2 due
HW3 out

[M1] Ch 10

Oct/2

Lecture 9 Generalization I

[Ba] Ch 1.2.1, 5

[M1] Ch 8

Oct/7

Lecture 10 Generalization II

HW3 due
MP1 out

[Ba] Ch 5.4

[M1] Ch 8.4

[SB]/[SSS] Ch 2.3, 3.1-3.2, 4.1-4.2

Oct/9

Lecture 11 Boosting

[SB]/[SSS] Ch 6, 28

Oct/14

Lecture 12 Neural networks I: intuition, activations, depth, and width

Oct/16

Lecture 13 Neural networks II: optimization

MP1 due

Oct/21

Lecture 14 Neural networks III: kernels versus feature learning

HW4 out

Oct/23

Midterm 7PM–9PM (No lecture)

Oct/28

Lecture 15 Neural networks IV: other architectures

Oct/30

Lecture 16 Neural networks V: overparameterization

Nov/4

Lecture 17 Temporal and spatial learning

HW4 due
HW5 out

Nov/6

Lecture 18 Missing data

Nov/11

Holiday! No lecture

Nov/13

Lecture 19 Dimensionality reduction I

Nov/18

Lecture 20 Dimensionality reduction II

HW5 due
HW6 out

Nov/20

Lecture 21 Attention & transformers

Nov/25

Lecture 22 Representation learning I

HW6 due
MP2 out

Nov/27

Holiday! No lecture

Dec/2

Lecture 23 Representation learning II

MP2 due
HW7 out

Dec/4

Lecture 24 Some ways to do machine learning wrong

Dec/9

Review