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 decisiontheoretic 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.
We make lecture and Q&A 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. The recordings are also available on Kaltura, which is a service that UC Berkeley partners with that facilitates the cloud recordings of Zoom meetings. All recordings on Kaltura have automaticallygenerated captions available by default alongside some other useful controls, such as playback speed adjustment.
To access the channel with recordings for this course, please go to this website and create an account if you don’t have one already: https://kaltura.berkeley.edu
Once you have the account, you should be able to access and subscribe to videos in the channel by following this link.
W  Date  Lecture Topic  Readings  Section  Homework  Project 

0  W 1/20  Intro to AI [pdf] [pptx] [lecture]  Ch. 1 
N/A  HW0  Math, diagnostic
Electronic due 1/25 10:59 pm 
Project 0 due 1/22 11:59pm 
F 1/22  Agents + Environments, part 1 [pdf] [pptx] [lecture] [q&a]  Ch. 2  
1  M 1/25  Agents + Environments, part 2 [pdf] [pptx] [lecture]  Ch. 2 
Section 1, solutions, recording Exam prep 1, solutions, recording 
HW1  Uninformed search Electronic due 2/1 10:59 pm Written HW1  Probability, uninformed search, and heuristics due 2/10 10:59 pm on gradescope. Piazza post on WHW1 selfgrading, due 2/22 10:59 pm. Gradescope link. 
Project 1 due 2/5 11:59 pm 
W 1/27  Uninformed Search [pdf] [pptx] [lecture] [supplementary lecture] [q&a]  Ch. 3.14  
F 1/29  Informed Search [pdf] [pptx] [lecture] [supplementary lecture] [q&a]  Ch. 3.56 Note 1 

2  M 2/1  Local Search [pdf] [pptx] [lecture] [supplementary lecture] [q&a]  Ch. 4.12 
Section 2, solutions, recording Exam prep 2, solutions, recording 
HW2  Informed search and game trees Electronic due 2/8 10:59 pm 

W 2/3  Games: minimax, alphabeta [pdf] [pptx] [lecture] [q&a]  Ch. 5.13  
F 2/5  Games: MCTS, chance [pdf] [pptx] [lecture] [q&a]  Ch. 5.45 Note 2 

3  M 2/8  Propositional Logic [pdf] [pptx] [lecture] [q&a]  Ch. 7.14 
Section 3, solutions, recording Exam prep 3, solutions, recording 
HW3  Propositional logic and local search Electronic due 2/16 10:59 pm Written HW2  Games and logic due 2/24 10:59 pm on gradescope. Piazza post on WHW2 selfgrading, due 3/8 10:59 pm. 
Project 2 due 2/19 11:59 pm 
W 2/10  Logical Inference: theorem proving, model checking [pdf] [pptx] [lecture] [q&a]  Ch. 7.56  
F 2/12  Propositional Planning [pdf] [pptx] [lecture] [q&a]  Ch. 7.7  
4  M 2/15  Presidents' Day  Section 4, solutions, recording Exam prep 4, solutions, recording 
HW4  First order logic and probability Electronic due 2/22 10:59 pm 

W 2/17  FOL: Syntax, Semantics, Inference [pdf] [pptx] [lecture] [q&a]  Ch. 8.12, skim 9.14 Note 3 

F 2/19  Probability, Independence, Naive Bayes [pdf] [pptx] [lecture] [q&a]  Ch. 12.16  
5  M 2/22  Bayes nets: syntax, semantics, examples [pdf] [pptx] [lecture] [q&a]  Ch. 13.12  Section 5, solutions, recording Exam prep 5, solutions, recording 
HW5  Probability and Bayes Nets Electronic due 3/2 10:59 pm 

W 2/24  Bayes nets: exact inference [pdf] [pptx] [lecture] [q&a]  Ch. 13.3  
F 2/26  Bayes nets: stochastic inference (rejection, importance) [pdf] [pptx] [lecture] [q&a]  Ch. 13.4  
6  M 3/1  Bayes nets: stochastic inference (Gibbs) [pdf] [pptx] [lecture] [q&a] [supp lecture pdf] [supp lecture pptx] [supp lecture recording]  Ch. 13.4 Note 4 
Section 6, solutions, recording Exam prep 6, solutions, recording 
HW6  Bayes Net Sampling and HMMs Electronic due 3/8 10:59 pm Written HW3  Bayes nets and HMMs due 3/19 10:59 pm on gradescope: links for written component and coding component. Piazza post on WHW3 selfgrading, due 4/5 10:59 pm. 
Project 3 due 3/15 11:59 pm 
W 3/3  Markov models and filtering [pdf] [pptx] [lecture] [q&a]  Ch. 14.12  
F 3/5  Inference in Markov models [pdf] [pptx] [lecture] [q&a]  Ch. 14.3 Note 5 

7  M 3/8  DBNs, particle filtering [pdf] [pptx] [lecture] [q&a]  Ch. 14.5  Search review, solutions, Games review, solutions, Logic review, solutions, Bayes nets review, solutions, HMMs review, solutions. Piazza post with recordings of review sessions 

W 3/10  Midterm 57 pm PT  
F 3/12  Rationality, utility theory [pdf] [pptx] [lecture]  Ch. 16.13  
8  M 3/15  Decision nets, VPI, unknown preferences [pdf] [pptx] [lecture]  Ch. 16.57 Note 6 
Section 8, solutions, recording Exam prep 8, solutions, recording 
HW7  Utility theory and HMMs Electronic due 3/30 10:59 pm 
Project 4 due 4/2 11:59 pm 
W 3/17  MDPs: V/Q/pi [pdf] [pptx] [lecture]  Ch. 17.1  
F 3/19  MDPs: Value/Policy Iter (part 1) [pdf] [pptx] [lecture]  Ch. 17.2  
9  M 3/22  Spring Break  
W 3/24  Spring Break  
F 3/26  Spring Break  
10  M 3/29  MDPs: Value/Policy Iter (part 2) [pdf] [pptx] [lecture]  Ch. 17.2 Note 7 
Section 9, solutions, recording Exam prep 9, solutions, recording 
HW8  MDPs Electronic due 4/5 10:59 pm 

W 3/31  ML: Decision Trees (1) [pdf] [pptx] [lecture]  Ch. 19.13  
F 4/2  ML: Decision Trees (2) [pdf] [pptx] [lecture]  Ch. 19.13  
11  M 4/5  ML: Linear Regression and Perceptrons [pdf] [pptx] [lecture]  Ch. 19.6  Section 10, solutions, recording Exam prep 10, solutions, recording 
HW9  Machine learning Electronic due 4/13 10:59 pm 
Project 5 due 4/16 11:59 pm 
W 4/7  ML: Statistical Learning, Naïve Bayes [pdf] [pptx] [lecture]  Ch. 20.12 Note 8 

F 4/9  No lecture  
12  M 4/12  ML: Neural Networks [pdf] [pptx] [lecture]  Ch. 21.15  Section 11 Exam prep 11 
Written HW4  Machine learning and reinforcement learning due 4/28 10:59 pm on gradescope: links for written component and coding component. 

W 4/14  Backpropagation and Reinforcement Learning [pdf] [pptx] [lecture]  Ch. 22.12  
F 4/16  No lecture  
13  M 4/19  RL: Q learning [pdf] [pptx] [lecture]  Ch. 22.3  Section 12 Exam prep 12 

W 4/21  RL: Policy search, applications [pdf] [pptx] [lecture]  Ch. 22.5, 22.7  
F 4/23  Fairness and ethics in AI [pdf] [pptx] [lecture]  Ch. 27.3  
14  M 4/26  Advanced topics I  Nicholas Carlini on Adversarial Machine Learning [pdf] [pptx] [lecture]  
W 4/28  Advanced topics II [pdf] [pptx] [lecture]  
F 4/30  Future + wrapup [pdf] [pptx] [lecture]  
15  M 5/3  RRR  
W 5/5  RRR  
F 5/7  RRR  
16  M 5/10  
W 5/12  Final 710 pm PT  
F 5/14 