CS 188 | Introduction to Artificial Intelligence

Fall 2021

Lectures: Tu/Th 5:00–6:29 pm, Online

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 fourth edition of AIMA unless otherwise specified.

Lecture reference materials

We make lecture recordings available as links to Google Drive, which you can find posted together with other materials on the Syllabus page of this website shortly after the lecture. These links will work only if you are signed into your UC Berkeley Google account.

Slides from the Fall 2020 version of the course have been posted for each lecture at the start of semester, as a reference. After lectures, they will be replaced by updated slides. Similarly, notes have been posted from the Fall 2020 version of the course, and will be updated to reflect actual course content.


Syllabus

W Date Lecture Topic Readings Section Homework Project
0 Th 8/26 1 - Intro to AI
[pdf] [pptx] [recording]
Ch. 1, 2 N/A HW0 - Math, diagnostic (optional)
'due' 8/27 10:59 pm.
Project 0
due 8/30 10:59 pm.
1 Tu 8/31 2 - Uninformed Search
[pdf] [pptx] [recording]
Ch. 3.1-4
Note 1 - fa20
Section 1, solutions, walkthrough.
Exam prep 1, solutions, walkthrough.
HW1 - Search and Heuristics
Main HW, challenge question pdf and submission link,
due 9/7 10:59 pm.
Challenge question solutions.
Challenge question reflection due 9/14 10:59 pm.
Project 1
due 9/10 10:59 pm.
Th 9/2 3 - UCS, A*, and Heuristics
[pdf] [pptx] [recording]
Ch. 3.5-6
2 Tu 9/7 4 - Constraint Satisfaction Problems I
[pdf] [pptx] [recording]
Ch. 6.1
Note 2
CSP applet
Section 2, solutions, walkthrough.
Exam prep 2, solutions, walkthrough.
HW2 - Constraint Satisfaction Problems
Main HW, challenge question pdf and submission link,
due 9/14 10:59 pm.
Challenge question solutions.
Challenge question reflection due 9/21 10:59 pm.
Mini-Contest 1
due 9/24 11:59 pm.
Th 9/9 5 - Constraint Satisfaction Problems II
[pdf] [pptx] [recording]
Ch. 6.2-5
3 Tu 9/14 6 - Search with Other Agents I
[pdf] [pptx] [recording]
Ch. 5.2-5
Note 3 - fa20
Section 3, solutions, walkthrough.
Exam prep 3, solutions, walkthrough.
HW3 - Games
Main HW, challenge question pdf and submission link,
due 9/21 10:59 pm.
Challenge question solutions.
Challenge question reflection due 9/28 10:59 pm.
Project 2
due 9/24 10:59 pm.
Th 9/16 7 - Search with Other Agents II
[pdf] [pptx] [recording]
Ch. 16.1-3
4 Tu 9/21 8 - Markov Decision Processes I
[pdf] [pptx] [recording]
17.1-3
Note 4 - fa20
Section 4, solutions, walkthrough.
Exam prep 4, solutions, walkthrough.
HW4 - Markov Decision Processes
Main HW, challenge question pdf and submission link,
due 9/28 10:59 pm.
Challenge question solutions.
Challenge question reflection due 10/5 10:59 pm.
Mini-Contest 2
due 10/22 11:59 pm.
Th 9/23 9 - Markov Decision Processes II
[pdf] [pptx] [recording]
Ch. 17.1-3
5 Tu 9/28 10 - Reinforcement Learning I
[pdf] [pptx] [recording]
Ch. 21
Note 5 - fa20
Section 5, solutions, walkthrough.
Exam prep 5, solutions, walkthrough.
HW5 - Reinforcement Learning
Main HW, challenge question pdf and submission link,
due 10/5 10:59 pm.
Challenge question solutions.
Challenge question reflection due 10/19 10:59 pm.
Project 3
due 10/8 10:59 pm.
Th 9/30 11 - Reinforcement Learning II
[pdf] [pptx] [recording]
Ch. 21
6 Tu 10/5 12 - Probability
[pdf] [pptx] [recording]
Ch. 13.1-5
Note 6 - fa20
Midterm review
Search worksheet, solutions.
CSPs worksheet, solutions.
Games worksheet, solutions.
MDPs worksheet, solutions.
Reinforcement learning worksheet, solutions.
Th 10/7 13 - Bayesian Networks: Representation
[pdf] [pptx] [recording]
Ch. 14.1-2, 14.4
7 Tu 10/12 14 - Bayesian Networks: Inference
[pdf] [pptx] [recording]
Ch. 14.4 Section 6, solutions, walkthrough.
Exam prep 6, solutions, walkthrough.
HW6 - Probability and Bayesian Networks
Main HW, challenge question pdf and submission link,
due 10/19 10:59 pm.
Challenge question solutions.
Challenge question reflection due 10/26 10:59 pm.
Th 10/14 Midterm 7-9 pm PT  
8 Tu 10/19 15 - Bayesian Networks: Independence
[pdf] [pptx] [recording]
Ch. 14.1-2, 14.4 Section 7, solutions, walkthrough.
Exam prep 7, solutions, walkthrough.
HW7 - Bayesian Networks
Main HW, challenge question pdf and submission link,
due 10/26 10:59 pm.
Challenge question solutions.
Challenge question reflection due 11/2 10:59 pm.
Project 4
due 11/12 10:59 pm.
Th 10/21 16 - Bayesian Networks: Sampling
[pdf] [pptx] [recording]
Ch. 14.4-5
8 Tu 10/26 17 - Decision Networks and VPI
[pdf] [pptx] [recording]
Ch. 16.5-6
Note 7 - fa20
Section 8, solutions, walkthrough.
Exam prep 8, solutions, walkthrough.
HW8 - Decision Networks, Hidden Markov Models, and Particle Filtering
Main HW, challenge question pdf and submission link,
due 11/9 10:59 pm.
Challenge question solutions.
Challenge question reflection due 11/16 10:59 pm.
Th 10/28 18 - Hidden Markov Models
[pdf] [pptx] [recording]
Ch. 15.2-6
Note 8 - fa20
10 Tu 11/2 19 - Particle filtering
[pdf] [pptx] [recording]
Ch. 15.2-6 Section 9, solutions, walkthrough.
Exam prep 9, solutions, walkthrough.
Th 11/4 20 - Machine Learning: Naïve Bayes
[pdf] [pptx] [recording]
Ch. 20.1-2
Note 9 - fa20
11 Tu 11/9 21 - Machine Learning: Perceptrons and Logistic Regression
[pdf] [pptx] [recording]
Ch. 18.6.3, 18.8 Section 10, solutions, walkthrough.
Exam prep 10, solutions, walkthrough.
HW9 - HMMs and Machine Learning
Main HW, challenge question pdf and submission link,
due 11/16 10:59 pm.
Challenge question solutions.
Challenge question reflection due 11/23 at 10:59 pm.
Th 11/11 Veterans Day
12 Tu 11/16 22 - Machine Learning: Optimization
[pdf] [pptx] [recording]
Ch. 18.6.3, 18.8
Note 10 - fa20
Section 11, solutions, walkthrough.
Exam prep 11, solutions, walkthrough.
HW10 - Machine Learning
Main HW, challenge question pdf and submission link, due 11/30 10:59 pm.
Challenge question solutions.
Challenge question reflection due 12/9 at 10:59 pm.
Project 5
due 12/3 10:59 pm.
Th 11/18 23 - Machine Learning: Neural Networks
[pdf] [pptx] [recording]
13 Tu 11/23 Thanksgiving break
Th 11/25 Thanksgiving break
14 Tu 11/30 24 - Advanced Applications: Games and Robotics
[pdf] [pptx] [recording]
Finals review
Search and CSPs, solutions
Games and utilities, solutions
MDPs and RL, solutions
Bayes nets, solutions
HMMs, solutions
ML I - Naïve Bayes, Perceptron, and Logistic Regression,
solutions
ML II - Optimization and Neural Networks, solutions
Th 12/2 25 - Conclusion
[pdf] [pptx] [recording]
 
15 Tu 12/7 RRR  
Th 12/9 RRR
16 Tu 12/14 N/A (Finals Week)  
Th 12/16 Final 11:30 am - 2:30 pm PT