Princeton University
Computer Science Department

Computer Science 402
Artificial Intelligence

Rob Schapire

Fall 2005

General Information | Schedule & Readings | Assignments | Whiteboard

Schedule and readings

Numbers in brackets under "readings" refer to chapters or sections of Russell & Norvig.  If you come across other cool readings or links that you think would be of interest to others, please send them to Melissa (mkc@cs) and she'll post them here.




Readings (required)

Other (optional) readings and links

1 Th 9/15 General introduction to AI. [1]

AI Growing Up by James Allen (but skip or skim page 19 to end).

AAAI website with LOTS of readings on AI in general, AI in the news, etc.

Robocup website.  The simulation league movies can be found here.  (Click on "results", and then on the "F" next to any match.)  Four-legged robot league movies can be found here.

Videos of autonomous helicopter.

2 Tu 9/20 Uninformed (blind) search [3.1-3.5]  
3 Th 9/22 Informed (heuristic) search [4.1-4.2] The Centipede Game: a thought experiment that provides an argument against the so-called "common knowledge of rationality" assumption which underlies almost all of game theory (submitted by Glen Weyl) (submitted by Glen Weyl)

4 Tu 9/27 Local search; searching in games [4.3], [6] (but okay to skip [6.5])  
5 Th 9/29 Propositional logic [7.1-7.4]  
6 Tu 10/4 Guest lecture: Gilbert Harman, Professor of Philosophy, on "Philosophy of Artificial Intelligence" [26]
7 Th 10/6 More propositional logic [7.5]  
8 Tu 10/11 Other methods and uses of solving CNF sentences, including planning [7.6; 11.1, 11.5]  
9 Tu 10/11(8-9:30pm)
Th 10/13 (5-6:30pm)
Cursory look at first-order logic;
Uncertainty and basics of probability
[8.1-8.3] (okay to skim these);
Princeton Psychology professor and Nobel Prize winner Daniel Kahneman researches human reasoning about probability:

Max Bazerman's Judgement in Managerial Decision Making summarizes these results (thanks to Glen Weyl for both of the above).


10 Tu 10/18 Independence and Bayes rule [13.5-13.6]  
11 Th 10/20 Bayesian networks: semantics and exact inference [14.1-14.4] A Reading List on Bayesian Methods:

A Brief Introduction to Graphical Models and Bayesian Networks:

12 Tu 10/25 Approximate inference with Bayesian networks [14.5]  
Th 10/27
Tu 11/8
Uncertainty over time (temporal models; HMM's) [15.1-15.3]
formal derivations (optional)
15 Th 11/10 Kalman filters; DBN's; particle filters; speech recognition [15.4-15.6] The particle filtering demo came from here on Sebastian Thrun's website

"I'm sorry Dave, I'm afraid I can't do that" (article on natural language processing by L. Lee)

16 Tu 11/15 Decision theory; Markov decision processes  [16.1-16.3]; [17.1] Time Discounting and Time Preference:: A Critical Review (see link below this table: thanks to Glen Weyl for submitting)
17 Th 11/17 More MDP's (value iteration; Bellman equations) [17.2]  
18 Tu 11/22 Finish MDP's (policy iteration)
Machine Learning
19 Tu 11/29 Decision trees [18.3]  
20 Th 12/1 Computational learning theory [18.5] original "Occam's Razor" paper
21 Tu 12/6 Boosting [18.4]
boosting slides
face slide
training error proof
boosting overview paper
22 Th 12/8 Support-vector machines [20.6]  
23 Tu 12/13 Neural networks
Learning Bayes net and HMM parameters
A demo of LeNet, a neural network for optical-character recognition, is available here.  Click the links on the left to see how it does on various inputs.  The figure shows the activations of various layers of the network, where layer-1 is the deepest.  (For more detail, see the papers on the LeNet website, such as this one.)
24 Th 12/15 Learning in MDP's [21.1-21.4] Sutton & Barto's excellent book on reinforcement learning

Learning to play keepaway in robocup soccer using reinforcement learning.  Scroll down to find flash demos.

Statistical Data Mining Tutorials by Andrew Moore


Time Discounting and Time Preference: A Critical Review

Stuart Russell's AI on the Web links: