Lecture |
Date |
Topic |
Reading
(textbook) |
1 |
May 1 |
Introduction (Lecture slides) | [RN2] Chapt. 1 and 2 [RN3] Chapt. 1 and 2 |
2 |
May 3 |
Uninformed Search (Lecture slides) | [RN2] Sect. 3.1-3.5 [RN3] Sect. 3.1-3.4 |
3 |
May 8 |
Informed Search (Lecture slides) | [RN2] Sect. 4.1-4.2 (except
RBFS) [RN3] Sect. 3.5-3.6 (except RBFS) |
4 |
May 10 |
Constraint Satisfaction Problems (Lecture slides) | [RN2] Sect. 5.1-5.2 [RN3] Sect. 6.1-6.3 |
5 |
May 15 |
Local Search (Lecture slides) | [RN2] Sect. 4.3 [RN3] Sect. 4.1 |
6 |
May 17 |
Uncertainty (Lecture slides) | [RN2] Sect. 13.1-13.6 [RN3] Sect. 13.1-13.5 |
May 19 |
Assignment 1 due (11:59 pm) | ||
7 |
May 23 |
Bayesian Networks (Lecture slides) | [RN2] Sect. 14.1-14.2 [RN3] Sect. 14.1-14.2 |
8 |
May 24 |
Bayesian Networks (Lecture slides (Slide 24 revised June 12)) | [RN2] Sect. 14.4 (except
clustering algorithms) [RN3] Sect. 14.4 (except clustering algorithms) |
9 |
May 29 |
Decision Theory (Lecture slides) | [RN2] Sect. 16.1-16.3 [RN3] Sect. 16.1-16.3 |
10 |
May 31 |
Decision Networks (Lecture slides) | [RN2] Sect. 16.5-16.6 [RN3] Sect. 16.5-16.6 |
Jun 2 |
Assignment 2 due (11:59 pm) | ||
11 |
Jun 5 |
Probabilistic reasoning over time (Lecture slides) | [RN2] Sect. 15.1-15.3, 15.5
(except approximate inference) [RN3] Sect. 15.1-15.3, 15.5 (except approximate inference) |
12 |
Jun 7 |
Markov Decision Processes (Lecture slides (Slide 11 revised June 12)) | [RN2] Sect. 17.1-17.2,
17.4-17.5 [RN3] Sect. 17.1-17.2, 17.4 |
13 |
Jun 12 |
Decision tree learning (Lecture slides (Slide 28 revised July 27)) | [RN2] Sect. 18.1-18.4 [RN3] Sect. 18.1-18.4 |
14 |
Jun 14 |
Review and QA session to
prepare for midterm |
|
Jun 16 |
Midterm 6:30 - 8:00 pm
|
||
15 |
Jun 19 |
No new material |
|
16 |
Jun 21 |
Statistical Learning (Lecture slides) | [RN2] Sect. 20.1-20.2 (up to
p. 718) [RN3] Sect. 20.1-20.2 (up to p. 809) |
Jun 23 |
Project proposal due (11:59 pm) |
||
17 |
Jun 26 |
Neural networks (Lecture slides (revised
July 28)) |
[RN2] Sect. 20.5 [RN3] Sect. 18.7 |
18 |
Jun 28 |
Deep
neural networks (Lecture
slides) |
[GBC] Chap. 6, 7, 8 |
Jun 30 |
Assignment 3 due (11:59 pm) | ||
19 |
Jul 5 |
Reinforcement Learning (Lecture slides) |
[RN2] Sect. 21.1-21.3 [RN3] Sect. 21.1-21.3 |
20 |
Jul 10 |
Deep
reinforcement learning (Lecture
slides (revised July 26)) |
[Human-Level Control through Deep
Reinforcement Learning, Nature 2015] |
21 |
Jul 12 |
Deep reinforcement learning (Lecture slides) |
[Mastering the Game of Go with Deep Neural
Networks and Tree Search, Nature 2016] |
22 |
Jul 17 |
Multi-armed Bandits (Lecture
slides, video) |
[Sutton and Barto, Reinforcement Learning,
2nd edition, Chapter 2] Supplementary lecture slides, supplementary video |
23 |
Jul 19 |
Sum-product
networks (Lecture
slides, video) |
Supplementary
lecture slides, supplementary video |
Jul 21 |
Assignment 4 due (11:59 pm) | ||
24 |
Jul 24 |
Course wrap up (Lecture slides) |
|
Jul 30 |
Project report due (11:59 pm) |