## Computer Science 402 Artificial IntelligenceRob Schapire

### Fall 2010

Directory
General Information | Schedule & Readings | Assignments | blackboard

Chapters or sections of the Russell & Norvig text ("R&N") are listed for both the 3rd and 2nd editions.  Take care to do the appropriate reading for the edition that you are using.  Other additional required or optional readings and links are also listed below.

This syllabus is constantly evolving as the semester progresses, so check back often (and let me know if it seems not to be up to date).

### Topic

#### other

1 Th 9/16 General introduction to AI. 1 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, and the humanoid league.  The video shown in class is here.

Videos of autonomous helicopter.

2 Tu 9/21 Uninformed (blind) search 3.1-3.4 3.1-3.5
3 Th 9/23 Informed (heuristic) search 3.5-3.6 4.1-4.2
4 Tu 9/28 Local search;
Searching in games
4.1
5 (ok to skip 5.5-5.6)
4.3
6 (ok to skip 6.5)
"The Chess Master and the Computer" by Garry Kasparov

play checkers with Chinook

5 Th 9/30 Propositional logic 7.1-7.4  7.1-7.4
6 Tu 10/5 Theorem proving and the resolution algorithm 7.5 7.5 handout on converting to CNF
7 Th 10/7 Practical methods of solving CNF sentences 7.6 7.6
8 Tu 10/12 Applications of solving CNF sentences, including planning;
Cursory look at first-order logic;
Uncertainty and basics of probability
7.7; 10.1; 10.4.1;
8.1-8.3 (ok to skim);
13.1-13.3
11.1; 11.5;
8.1-8.3 (ok to skim);
13.1-13.4

9 Th 10/14 Independence and Bayes rule 13.4-13.5 13.5-13.6   "What is the chance of an earthquake?"  (article on interpreting probability, by Freedman & Stark)
10 Tu 10/19 Bayesian networks: semantics and exact inference 14.1-14.4 14.1-14.4   brief tutorial on Bayes nets (and HMM's), with links for further reading
11 Th 10/21 Approximate inference with Bayesian networks 14.5 14.5
12
13
Tu 10/26
Th 10/28
Uncertainty over time (temporal models; HMM's);
Kalman filters
15.1-15.4 15.1-15.4 formal derivations (optional)
14 Tu 11/9 DBN's; particle filters; speech recognition 15.5;
15.6 in 2nd ed. (available on e-reserves via blackboard)
15.5-15.6   The particle filtering demo came from here on Sebastian Thrun's website
15 Th 11/11 Finish speech recognition; decision theory;
begin Markov decision processes
16.1-16.3 (ok to skim);
17.1
16.1-16.3 (ok to skim);
17.1

16
17
Tu 11/16
Th 11/18
Markov decision processes: Bellman equations, value iteration, policy iteration 17.2-17.4.1 17.2-17.4   Sutton & Barto's excellent book on reinforcement learning and MDP's
18 Tu 11/23 Machine Learning
Decision trees
18.1-18.4 18.1-18.3;
18.4 in 3rd ed. (available on e-reserves via blackboard)

19 Tu 11/30 Guest lecture:  Prof. Alain Kornhauser (ORFE) on Princeton Autonomous Vehicle Engineering (PAVE)     slides
20 Th 12/1 Theory of learning 18.5 18.5 generalization error theorem proved in class original "Occam's Razor" paper
21 Tu 12/7 Boosting 18.10 18.4 slides training error proof
boosting overview paper
22 Th 12/9 Support-vector machines 18.9 20.6   tutorial on SVM's
23 Tu 12/14 Neural networks
Learning Bayes net and HMM parameters
18.7
20.1-20.3
20.5
20.1-20.3
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 12/16 Reinforcement learning in MDP's 21.1-21.4 21.1-21.4   Sutton & Barto's excellent book on reinforcement learning and MDP's

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