#
Artificial Intelligence Prelim Syllabus

*(Fall 2000)*
As undergraduate material, students are expected to be familiar with S.
Russell and P. Norvig's Artificial
Intelligence: A Modern Approach (second edition).

Graduate material that students are expected to be familiar with is
in
three areas:

- Learning and Probabilistic Inference
- Vision
- Natural Language and Speech.

**(1) Learning and Probabilistic Inference**

- R. Sutton and A. Barto, Reinforcement
Learning, Chapters 1-6, 8, 11

- Shawe-Taylor, J. & Cristianini, N.

Kernel Methods for Pattern Analysis

Cambridge University Press, 2004.

Chapters 2, 3, 5, 6 and 7

A selection of chapters from Jordan are available from
www.cs.berkeley.edu/~jordan/prelims:

Chap 2: Conditional Independence and Factorization

Chap 3: The Elimination Algorithm

Chap 4: Probability Propagation and Factor Graphs

Chap 5: Statistical Concepts

Chap 6: Linear Regression and the LMS Algorithm

Chap 7: Linear Classification

Chap 10: Mixtures and Conditional Mixtures

Chap 11: The EM Algorithm

Chap 12: Hidden Markov Models

Chap 17: The Junction Tree Algorithm

**(2) Vision**

- D. Forsyth and J. Ponce, Computer Vision --A Modern Approach, Chapters 1, 4, 7, 8, 9, 14, 18, 22.

**(3) Natural Language and Speech**