CS 188 | Introduction to Artificial Intelligence

Fall 2019

Lectures: Tu/Th 2:00–3:30 pm, Wheeler 150

CS188 Robot Waving

Description

This course will introduce the basic ideas and techniques underlying the design of intelligent computer systems. A specific emphasis will be on the statistical and decision-theoretic modeling paradigm.

By the end of this course, you will have built autonomous agents that efficiently make decisions in fully informed, partially observable and adversarial settings. Your agents will draw inferences in uncertain environments and optimize actions for arbitrary reward structures. Your machine learning algorithms will classify handwritten digits and photographs. The techniques you learn in this course apply to a wide variety of artificial intelligence problems and will serve as the foundation for further study in any application area you choose to pursue.

See the syllabus for slides, deadlines, and the lecture schedule. Readings refer to AIMA unless otherwise specified.


Syllabus

Slides from fall 2018 are available before lectures - official slides will be uploaded following each lecture.
W Date Lecture Topic Readings Section Homework Project
0 Th 8/29 1. Intro to AI
pptx, pdf, fa18
Ch. 1 & 2 N/A HW0 Math Diagnostic
Electronic
(Due 9/3 11:59 pm)
P0 Tutorial
(Due 9/3 11:59 pm)

1 Tu 9/3 2. Uninformed Search
pptx, pdf, fa18
Ch. 3.1–3.4
Note 1
Section 1 (Solns, Recording) HW1 Search
Electronic
(Due 9/11 11:59 pm)
P1 Search
(Due 9/13 11:59 pm)

Mini-Contest 1
(Due 9/16 11:59 pm)
Th 9/5 3. A* Search and Heuristics
pptx, pdf, fa18
Ch. 3.5–3.6
2 Tu 9/10 4. CSP I
pptx, pdf, fa18
Ch 6.1
Note 2
Section 2 (Solns, Recording)
Exam prep 1 (Solns, Recording)
HW2 CSPs
Electronic
(Due 9/18 11:59 pm)

HW1 Written
(Due 9/27 11:59 pm)
Th 9/12 5. CSP II
pptx, pdf, fa18
Ch 6.2-6.5
3 Tu 9/17 6. Game trees: Minimax
fa18
Ch. 5.2-5.5
Note 3
Section 3
Exam prep 2
P2 Games
(Due 9/27 11:59 pm)

Mini-Contest 2
(Due 10/14 11:59 pm)
Th 9/19 7. Game trees: Expectimax, Utilities
fa18
Ch. 5.2-5.5,
Ch. 16.1-16.3
4 Tu 9/24 8. MDPs I Ch 17.1-3
Note 4
Section 1
Th 9/26 9. MDPs II Ch 17.1-3,
Sutton and Barto Ch. 3 & 4
5 Tu 10/1 10. RL I Ch. 21,
Sutton and Barto Ch. 6.1, 6.2 & 6.5
Note 5
Section 2 P3 RL
(Due 10/11 11:59 pm)
Th 10/3 11. RL II Ch. 21
6 Tu 10/8 12. RL III Ch. 21 Section 3
Th 10/10 13. Probability + BN: Intro Ch 13.1-13.5
Note 6
7 Tu 10/15 14. BN: Representation Ch. 14.1, 14.2, 14.4 Section 4
Th 10/17 Midterm (8 - 10pm)
8 Tu 10/22 15. BN: Independence Ch. 14.1, 14.2, 14.4 Section 5
Wed 10/24 16. BNs: Inference Ch. 14.4
9 Tu 10/29 17. BN: Sampling Ch. 14.4–14.5 Section 6
Th 10/31 18. Decision Networks / VPI Ch. 16.5-16.6
Note 7
10 Tu 11/5 19. HMMs Ch. 15.2-15.6
Note 8
Section 7 P4 BNs and HMMs
(Due 11/15 11:59 pm)
Th 11/7 20. Particle Filtering Ch. 15.2, 15.6
11 Tu 11/12 21. ML: Naive Bayes Ch. 20.1-20.2.2
Note 9
Section 8

Final Contest
(Due 12/13 11:59 pm)
Thu 11/14 22. ML: Perceptrons and Logistic Regression Ch. 18.6.3 & 18.8
12 Tu 11/19 23. ML: Optimization and Neural Networks Ch. 18.6.3 & 18.8
Note 10
Section 9 P5 Machine Learning
(Due 12/6 11:59 pm)
Th 11/21 24. ML: Neural Networks II and Decision Trees Ch 18.3, 18.7
13 Tu 11/26 Thanksgiving Break N/A
Th 11/28 Thanksgiving Break
14 Tu 12/3 25. Advanced Topics N/A Section 10
Th 12/5 26. Advanced Topics N/A
15 Tu 12/10 27. RRR Week N/A
Th 12/12 28. RRR Week
16 Tu 12/17 Final Exam (8 - 11am) N/A
Th 12/19 29. Finals Week