Computer Science 246/446

Mathematical Foundations of Artificial Intelligence

Spring 2008

Instructor: Dan Gildea office hours Wed 1-2pm
TA: Mehdi Hafezi Manshadi office hours Tu/Th 5-6pm
Location: Tu/Th 11:05am-12:20pm, CSB 601

Homeworks

Required text: Christopher M. Bishop, Pattern Recognition and Machine Learning.

The following are useful references in addition to the reading material assigned for each class:

  • Stuart Russell and Peter Norvig, Artificial Intelligence, A Modern Approach.
  • Trevor Hastie, Robert Tibshirani, Jerome Friedman, The Elements of Statistical Learning: Data Mining, Inference, and Prediction.
  • Dana Ballard, Natural Computation.
Readings not taken from Bishop are available in the box in the CS mailroom.

Syllabus

Onwe will coverwhich means that after class you will understandif before class you have read
1/17 Probability Theory independence, bayes rule bishop 1.2
1/22 Information Theory entropy, kl-distance, coding bishop 1.6
1/24 Probabilistic Inference priors on continuous variables bishop 2.2
1/29 Probabilistic Inference priors: bayesian reasoning, MAP bishop 3.4
1/31 Perceptron, Backpropagation the chain rule bishop 5.1, 5.2, 5.3
2/5 Support Vectors the kernel trick bishop 6.1, 6.2
2/7 Support Vectors the wolfe dual bishop 7.1
2/12 Probabilistic Inference polytree bishop 8.4
2/14 Expectation Maximization latent variable clustering bishop 9
2/19 Sampling Markov Chain Monte Carlo bishop 11.2
2/21 Sampling Gibbs Sampling bishop 11.3
2/26 Learning Theory probably approximately correct kearns&vazirani 1
2/28 Learning Theory VC dimension kearns&vazirani 2, 3
3/4 Eigenvectors least squares, PCA bishop 12.1
3/6 Independent Component Analysis source separation bishop 12.4.1
3/18 Review
3/20 Midterm
3/25 Midterm Solutions
3/27 Logistic Regression maximum entropy bishop 4.3
4/1 Optimization conjugate gradient bishop (1995) 274-282
4/3 Hidden Markov Models forward-backward bishop 13.2
4/8 Particle Filters slam Thrun et al. ch 4
4/10 Reinforcement Learning q-learning ballard 11
4/15 Reinforcement Learning partial observability Thrun et al. ch 15, 16
4/17 Games nash equilibrium morris 115-131
4/22 Games learning to co-operate
4/24 Something Fun
4/29 Review come to class with questions!
Final Exam: Friday May 9, 8:30-11:30am.

Grading

  • Final exam: 35%
  • Homeworks: 35%
  • Midterm: 25%
  • Class participation: 5%
gildea @ cs rochester edu
April 10, 2008