CS165A: Artificial Intelligence (Winter 2019)
|
Announcements
[
link
]
Instructor:
Prof. Yu-Xiang Wang
TA1:
Chong Liu, Office Hour: Tuesday 2:00-3:00pm, Trailer 936.
TA2: Lei Xu, Office Hour: Thursday 3:00-4:00pm, Trailer 936.
Lecture Section: Tuesday/Thursday 12:30-1:45pm Location: GIRV 2128
Discussion Section 1: Fri 11:00-11:50am, Location: PHELP 1444
Discussion Section 2: Fri 12:00-12:50pm, Location: PHELP 1444
Piazza: piazza.com/ucsb/winter2019/cs165a
Piazza is our main channel of communication. Questions should be posted here.
Office hours:
Instructor Office Hour: Thursday
2:00-3:00pm, HFH 2121
TA1: Chong Liu, Office Hour: Tuesday 2:00-3:00pm, Trailer 936.
TA2: Lei Xu, Office Hour: Thursday 3:00-4:00pm, Trailer 936.
Textbook:
Stuart Russell and Peter Norvig, Artificial Intelligence:
A Modern Approach, Prentice Hall, Third Edition, 2010
Other reference books:
Sutton and Barto. Reinforcement learning: An introduction, MIT press, Second Edition, 2018.
Hastie, Tibshirani and Friedman. The Elements of Statistical Learning, Springer, Second Edition, 2009.
Jordan. An Introduction to Probabilistic Graphical Models, Unpublished , 2003. [Available here]
Zhang, Lipton, Li, Smola. Dive into Deep Learning, Web Edition, 2017. [Available here]
Shalev-Shwartz, Ben-David. Understanding Machine Learning:
From Theory to Algorithms, Cambridge University Press, 2014. [link]
Course Schedule / Lecture Notes
| Week |
Date |
Topic |
Reading |
Assignment |
| 1 |
8-Jan |
Introduction and Course Overview |
Ch.1 |
|
|
10-Jan |
AI Problem Solving and Intelligent Agents |
Ch. 2, Ch. 26 |
|
| 2 |
15-Jan |
Quantifying uncertainty |
Ch. 13 |
|
|
17-Jan |
Probabilistic Reasoning: Bayes Network |
Ch. 14 |
HW #1 out |
|
18-Jan |
Discussion 1 |
|
|
| 3 |
22-Jan |
Probabilistic Reasoning: d-separation, MRF |
Ch. 14 |
MP1 out |
|
24-Jan |
Machine Learning: Supervised Learning
|
Ch. 18 |
|
| 4 |
29-Jan |
Machine Learning: Unsupervised Learning
|
Ch. 18 |
HW #1 due |
|
31-Jan |
Machine Learning: Continuous optimization
|
Reading:( Bottou, Robbins-Monro)
|
HW #2 out |
|
1-Feb |
Discussion 3 |
|
|
| 5 |
5-Feb |
Machine Learning: Statistical Learning Theory
|
Section 2.1, 3.2 & 4.2 of Shalev-Shwartz & Ben-David |
|
|
7-Feb |
Search: Solving problems with Search
|
Ch. 3 |
MP2 out |
| 6 |
12-Feb |
Midterm review, Search: Uninformed search
|
Ch. 3 |
HW #2 due |
|
14-Feb |
Midterm |
|
|
| 7 |
19-Feb |
Search: Informed Search / Games / Adversarial search
|
Ch. 3, Ch. 5 |
MP1 due |
|
21-Feb |
Search: Adversarial search
RL: Overview
|
AIMA: Ch. 5, Ch 17.1, Ch 21, Sutton and Barto: Ch 1 |
HW#3 out |
|
22-Feb |
Discussion 5
|
|
|
| 8 |
26-Feb |
RL: Multi-arm Bandits
|
Sutton and Barto: Ch 2 |
|
|
28-Feb |
RL: Contextual Bandits, Off-Policy Evaluation
|
Sutton and Barto: Ch 2.9, Ch 5.5. Also: Here .
|
|
| 9 |
5-Mar |
RL: Reinforcement learning and MDP
|
Ch. 17, Sutton and Barto: Ch 3-6, Ch 13 |
|
|
7-Mar |
Logic: Propositional Logic
|
Ch. 7 |
HW#3 due / HW#4 out |
| 10 |
12-Mar |
Logic: First order logic
|
Ch. 8, Ch. 9 |
|
|
14-Mar |
Review session
|
|
HW#4 due / MP2 due |
| 11 |
18-Mar |
Final Exam. 12:00 PM - 3:00 PM |
|
|
Other Course Material