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.
All lecture recordings are posted to Kaltura. This link will work only if you are signed into your UC Berkeley bCourses (Canvas) account.
W  Date  Lecture Topic  Readings  Section  Homework  Project 

1  Tuesday, Jan 18  1  Intro to AI, Rational Agents [pdf] [pptx]  Ch. 1, 2  Section 1 Recording Solutions 
HW0  Math Diagnostic
Electronic
due Wed, Jan 26, 10:59 pm. 
Project 0 due Mon, Jan 24, 10:59 pm. 
Thursday, Jan 20  2  State Spaces, Uninformed Search [pdf] [pptx]  Ch. 3.1  3.4 Note 1  Exam Prep 1 Recording Solutions  
2  Jan 25  3  Informed Search: A* and Heuristics [pdf] [pptx]  Ch. 3.5  3.6  Section 2 Recording Solutions 
HW1  Search
Electronic
Written
LaTeX template
Solutions
due Wed, Feb 2, 10:59 pm. 
Project 1 due Thu, Feb 3, 10:59 pm. 
Jan 27  4  Local Search [pdf] [pptx]  Ch. 4.1  4.2 Note 2  Exam Prep 2 Recording Solutions  
3  Feb 1  5  Games: Trees, Minimax, Pruning [pdf] [pptx]  Ch. 5.1  5.3 Note 3  Section 3 Recording Solutions 
HW2  Games
Electronic
Written
LaTeX template
Solutions
due Wed, Feb 9, 10:59 pm. 
Project 2 due Mon, Feb 14, 10:59 pm. 
Feb 3  6  Games: Expectimax, Monte Carlo Tree Search [pdf] [pptx]  Ch. 5.4  5.5  Exam Prep 3 Recording Solutions  
4  Feb 8  7  Propositional Logic and Planning [pdf] [pptx]  Ch. 7.1  7.4 Note 4  Section 4 Recording Solutions 
HW3  Logic
Electronic
Written
LaTeX template
Solutions
due Fri, Feb 18, 10:59 pm. 

Feb 10  8  Logical Inference, Theorem Proving [pdf] [pptx]  Ch. 7.5  7.7  Exam Prep 4 Recording Solutions  
5  Feb 15  9  Boolean Satisfiability, DPLL  Ch. 8.1  8.2  Section 5 Recording Solutions 
HW4  Probability Review Electronic Written LaTeX template Solutions due Wed, Feb 23, 10:59 pm. 
Project 3 due Fri, Feb 25, 10:59 pm. 
Feb 17  10  First Order Logic [pdf] [pptx]  skim Ch. 9.1  9.4  Exam Prep 5 Recording Solutions  
6  Feb 22  11  Probability Review, Bayesian Networks [pdf] [pptx]  Ch. 13.1 Note 5  Section 6 Recording Solutions  HW5  Bayesian Networks
Electronic
Written
LaTeX template
Solutions
due Fri, Mar 4, 10:59 pm. 

Feb 24  12  Bayes Nets: Syntax and Semantics [pdf] [pptx]  Ch. 13.2  Exam Prep 6 Recording Solutions  
7  Mar 1  13  Bayes Nets: Variable Elimination [pdf] [pptx]  Ch. 13.3  Section 7 Recording Solutions  Study for Midterm  
Mar 3  14  Bayes Nets: Sampling [pdf] [pptx]  Ch. 13.4  Midterm Review: SearchSolutions, GamesSolutions, LogicSolutions, Bayes NetsSolutions 

8  Mar 8 Midterm 810pm Past Exams  15  Markov Chains, HMMs [pdf] [pptx]  Ch. 14.1  14.2 Note 6  Section 8 Recording Solutions 
HW6  Markov Models Electronic Written LaTeX template Solutions due Fri, Mar 18, 10:59 pm. 

Mar 10  16  Forward Algorithm, Viterbi Algorithm  Ch. 14.3  14.5  Exam Prep 8 Recording Solutions  
9  Mar 15  17  Dynamic Bayes Nets, Particle Filtering. Utility Theory, Rationality, Decisions [pdf] [pptx]  Ch. 16.1  16.3 Note 7  Section 9 Solutions 
HW7  Utilities, Decision Nets, VPI Electronic Written LaTeX template Solutions due Wed, Mar 30, 10:59 pm. 
Project 4 due Fri, April 1, 10:59 pm. 
Mar 17  18  Decision Networks and VPI [pdf] [pptx]  Ch. 16.5  16.7  Exam Prep 9 Recording Solutions  
10  Mar 22  Spring Break  
Mar 24  Spring Break  
11  Mar 29  19  Markov Decision Processes: States, Values, Policies, Qvalues [pdf]  Ch. 17.1 Note 8  Section 11 Recording Solutions 
HW8  MDPs Electronic Written LaTeX template Solutions due Wed, Apr 6, 10:59 pm. 

Mar 31  20  MDPs: Dynamic Programming [pdf]  Ch. 17.2  Exam Prep 11 Recording Solutions  
12  Apr 5  21  Machine Learning I [pdf]  Ch 19.1  19.3 Note 9  Section 12 Recording Solutions 
HW9  Machine Learning Electronic Written LaTeX template Solutions due Fri, Apr 15, 10:59 pm. 
Project 5 due Fri, April 22, 10:59 pm. 
Apr 7  22  Machine Learning II  Ch. 20.1  20.6  Exam Prep 12 Recording Solutions  
13  Apr 12  23  Neural Networks [pdf] [pptx]  Ch. 21.1  21.5 Note 10  Section 13 Recording Solutions 
HW10  Neural Networks Electronic Written LaTeX template Solutions due Fri, Apr 22, 10:59 pm. 

Apr 14  24  Reinforcement Learning [pdf] [pptx]  Ch. 22.1  22.6 Note 11  Exam Prep 13 Recording Solutions  
14  Apr 19  Advanced Topics 1: Deep RL and AI Robotics (Mostafa Rohaninejad)  Section 14 Recording Solutions 
HW11  RL Electronic Written LaTeX template Solutions due Fri, Apr 29, 10:59 pm. 
Project 6 due Fri, April 29, 10:59 pm. 

Apr 21  Advanced Topics 2: Adversarial Deep Learning (Nicholas Carlini)  Exam Prep 14 Recording Solutions  
15  Apr 26  Advanced Topics 3: Program Synthesis via Learning (Xinyun Chen)  Section 15 Recording Solutions 
MiniContest due Wed, May 4, 10:59 pm. 

Apr 28  Advanced Topics 4: AI Ethics [pdf] [pptx]  Exam Prep 15 Recording Solutions  
16  May 3  RRR 
Search Solutions Games Solutions Logic Solutions Bayes Nets Solutions HMMs/VPI Solutions MDPs/RL Solutions Machine learning Solutions 

May 5  RRR  
17  Mon, May 9  Final Exam: Mon, May 9, 11:30am  2:30pm  Past Exams 