CS221: Artificial Intelligence: Principles and Techniques
Autumn 2012-2013
[Calendar] [Syllabus]

Course Information
Instructor: Percy Liang
Course assistants:
Contact: Please use Piazza for all questions related to lectures, homeworks, and projects. For private questions, email cs221-aut1213-staff@lists.stanford.edu.
Calendar: look here for dates/times of all lectures, sections, office hours, due dates.
Course description: Problems in game playing, natural language processing, computer vision, robotics are challenging due to the inherent noise/uncertainty and computational complexity. This course provides the mathematical and algorithmic framework for tackling these sorts of problems. Topics include search, decision theory, graphical models, machine learning, and various applications.
Book: Russell and Norvig. Artificial Intelligence: A Modern Approach, 3rd. edition.
Prerequisites: a good grasp of basic data structures and algorithms, probability, linear algebra; solid programming skills.
Coursework and grading:
Collaboration policy: we encourage students to form study groups and discuss homeworks and projects. However, students must write up homeworks and code from scratch independently without referring to any notes from the joint session.
All lectures are taped and can be watched online for SCPD students and full-time students.

Note: the dates listed here are preliminary and subject to change.

Day Topic Reading Slides Assignment

Tue Sep 25 Overview 1.1-1.4, 2.1-2.4 html one pdf HW 0.1 (due Oct 1)
HW 1.1 1.2 1.3 [solutions] (due Oct 3)
P0: Python tutorial (due Oct 4)

[State space models]
Thu Sep 27 Search: deterministic state space models 3.1-3.4 html one pdf
Tue Oct 2 Search: algorithms, A* heuristics, relaxation 3.5-3.6, 10.1-10.2 html one pdf HW 2.1 2.2 2.3 2.4 (due Oct 8)
Thu Oct 4 Games: Markov decision processes 17.1-17.3 html one pdf
Tue Oct 9 Games: Markov decision processes 17.1-17.3 html one pdf HW3 (due Oct 19) [solutions]
P1: Multi-Agent (due Oct 20)
Thu Oct 11 Games: minimax, evaluation functions 5.1-5.5 html one pdf

[Variable-based models]
Tue Oct 16 Constraints: constraint satisfaction problems, factor graphs 6.1-6.5 html one pdf HW4 (due Oct 24)
Thu Oct 18 Constraints: independence, variable elimination 14.4 html one pdf
Tue Oct 23 Constraints: Markov networks 14.5,15.1-15.5 html one pdf HW5 (due Nov 1)
P2: Probabilistic Inference (due Nov 6)
Thu Oct 25 Constraints: Gibbs sampling, particle filtering 14.5,15.1-15.5 html one pdf demo
Tue Oct 30 Generative: Markov models, Bayesian networks, HMMs 14.1-14.3 html one pdf HW6 (due Nov 7)

[Machine learning]
Thu Nov 1 Learning: supervised learning, linear models 18.1-18.2, 18.6, 18.8 html one pdf demo
Tue Nov 6 Learning: loss minimization html one pdf HW7 + code (due Nov 16)
Thu Nov 8 Learning: loss minimization, maximum likelihood 20.2.1, 20.2.2 html one pdf
Tue Nov 13 Learning: unsupervised learning, reinforcement learning 21.1-21.6 html one pdf
P3: abstract (1 paragraph) due

Thu Nov 15 Logic: propositional logic 7.3-7.6 html one pdf demo HW8 (due Nov 30)
Tue Nov 27 Logic: propositional logic 8.1-8.3,9.1-9.5 html one pdf P3: progress report (1 page) due
Thu Nov 29 Logic: first-order logic html one pdf

Tue Dec 4 Language, vision, summary html one pdf
Thu Dec 6 Robotics (guest lecture by Oussama Khatib) P3: report (3 pages max + appendix) due