CS 188 | Introduction to Artificial Intelligence

Spring 2019

Lecture: M/W 5:00-6:30 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


Wk Date Lecture Topic Readings Section Homework Project
0 1/23 Wed Intro to AI
(Slides: PDF — Video)
Ch. 1 & 2
Note 1
N/A HW0 Math Diagnostic
[Electronic]
(Due 1/28 11:59 pm)
P0 Tutorial
(Due 1/28 4 pm)
1 1/28 Mon Uninformed Search
(Slides: PDFPPTX — Video)
Ch. 3.1-3.4 Section 1 (video) (without solutions) HW1 Search
[Electronic] [Written]
(Due 2/4 11:59 pm)
[Written solutions]
1/30 A* Search and Heuristics
(Slides: PDFPPTX — Video)
Ch. 3.5-3.6
2 2/4 Mon Game Trees
(Slides: PDFPPTX — Video)
Ch. 5.2-5.5, Ch. 16.1-16.3
Note 2
Section 2 (video) (without solutions) HW2 Game Trees
[Electronic] [Written]
(Due 2/11 11:59 pm)
[Written solutions]
P1 Search
(Due 2/8 4 pm)

Mini-Contest 1 (Due 2/11 11:59 pm)
2/6 Wed MDPs I
(Slides: PDFPPTX — Video)
Ch. 17.1-17.3
Note 3
3 2/11 Mon MDPs II
(Slides: PDFPPTX — Video)
Ch. 17.1-17.3, Sutton and Barto Ch. 3 & 4 Section 3 (video) (without solutions) HW3 MDPs
[Electronic] [Written]
(Due 2/18 11:59 pm)
[Written solutions]
2/13 Wed RL I
(Slides: PDFPPTX — Video)
Ch. 21, Sutton and Barto Ch. 6.1, 6.2 & 6.5
Note 4
4 2/18 Mon Holiday Section 4 (video) (without solutions) HW4 RL
[Electronic] [Written]
(Due 2/25 11:59 pm)
[Written solutions]
P2 Games
(Due 2/22 4 pm)

Mini-Contest 2 (Due 3/11 11:59 pm)
2/20 Wed RL II
(Slides: PDF — Video)
Ch. 21
5 2/25 Mon CSPs I
(Slides: PDFPPTX — Video)
Ch 6.1
Note 5
Section 5 (video) (without solutions) HW5 CSPs
[Electronic] [Written]
(Due 3/4 11:59 pm)
[Written solutions]
2/27 Wed CSPs II
(Slides: PDFPPTX — Video)
Ch 6.2-6.5
6 3/4 Mon Propositional Logic
(Slides: PDFPPTX — Video)
Ch 7 (7.5.2 and 7.6.2 are optional)
Note 11
Section 6 (video) (without solutions) HW6 Logic
[Electronic] [Written]
(Due 3/11 11:59 pm)
[Written solutions]
P3 RL
(Due 3/8 4 pm)
3/6 Wed First-Order Logic
(Slides: PDFPPTX — Video)
Ch 8.1-8.3, 9.1-9.3
7 3/11 Mon Probability
(Slides: PDFPPTX — Video)
Ch 13.1-13.5 Midterm Review
CSP (no soln
) Games (no soln
) Logic (no soln
) RL (no soln
) Search (no soln
)
HW7 Probability
[Electronic] [Written]
(Due 4/1 11:59 pm)
[Written solutions]
3/13 Wed Bayesian Networks: Representation
(Slides: PDFPPTX — Video)
Ch 14.1, 14.2 & 14.4
Note 6
8 3/18 Mon Bayesian Networks: Inference
(Slides: PDFPPTX — Video)
Ch 14.4 Section 7 (video) (without solutions) HW8 Bayes Nets
[Electronic] [Written]
(Due 4/8 11:59 pm)
[Written solutions]
3/20 Wed Midterm (7 - 9 pm) (Midterm Prep) (Practice Midterm, no soln)
9 3/25 Mon Spring Break N/A
3/27 Wed Spring Break
10 4/1 Mon Bayesian Networks: Sampling
(Slides: PDFPPTX — Video)
Ch 14.4-14.5 Section 8 (video) (without solutions) P4 Bayesian Networks and Hidden Markov Models
(Due 4/12 4 pm)
4/3 Wed Hidden Markov Models
(Slides: PDFPPTX — Video)
Ch. 15.2-15.6
Note 8
11 4/8 Mon Particle Filtering
(Slides: PDFPPTX — Video)
Ch. 15.2-15.6
Note 8
Section 9 (video) (without solutions) HW9 Bayes Nets and HMMs
[Electronic] [Written]
(Due 4/15 11:59 pm)
[Written solutions]
4/10 Wed Decision Networks / Value of Perfect Information
(Slides: PDFPPTX — Video)
Ch. 16.5-16.6
Note 7
12 4/15 Mon Machine Learning: Naive Bayes
(Slides: PDFPPTX — Video)
Ch. 20.1-20.2.2
Note 9
Section 10 (video) (without solutions) HW10 Particle Filtering and Naive Bayes
[Electronic] [Written]
(Due 4/22 11:59 pm)
[Written solutions]
4/17 Wed Machine Learning: Perceptrons
(Slides: PDFPPTX — Video)
Ch. 18.6.3
13 4/22 Mon Machine Learning: Logistic Regression and Neural Networks
(Slides: PDFPPTX — Video)
Ch 18.8 Section 11 (video) (without solutions) HW11 Perceptrons
[Electronic] [Written]
(Due 4/29 11:59 pm)
[Written solutions]
4/24 Wed Machine Learning: Neural Networks and Decision Trees
(Slides: PDFPPTX — Video)
Ch 18.3 & 18.7
Note 10
14 4/29 Mon Robotics / Language / Vision
(Slides: PDF — Video)
N/A Final Review
Bayes Networks (no soln
) Search (no soln
) Logic (no soln
) MDP/RL (no soln
) ML (no soln
)
Practice ML
Questions, solutions.
P5 Classification
(Due 5/3 4 pm)
5/1 Wed Advance Topics and Final Contest
(Slides: PDFPPTX — Video)
N/A
15 5/6 Mon RRR Week N/A
5/8 Wed RRR Week
16 5/13 Mon Finals Week N/A
5/16 Thu Final Exam (7 - 10 pm) (Final Prep) (Practice Final, no soln)