Computer Science 246/446

Mathematical Foundations of Artificial Intelligence

Spring 2012

Instructor: Dan Gildea office hours Wed 2-3pm
TA: Darcey Riley (dystopiananomaly @ gmail com), office hours Wed 11am-12pm and Thurs 4-5pm, 7th floor software lab
Location: Tu/Th 11:05am-12:20pm, CSB 601

Homeworks

Lecture Notes

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.
  • Larry Wasserman, All of Statistics, 2004.
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
1/19 Probability Theory independence, bayes rule bishop 1.2, 1.4, app E
1/24 Information Theory entropy, kl-distance, coding bishop 1.6
1/26 Probabilistic Inference priors on continuous variables bishop 2.2
1/31 Probabilistic Inference priors: bayesian reasoning, MAP bishop 3.4
2/2 Perceptron stochastic gradient descent bishop 3.1, 4.1
2/7 Backpropagation DP for gradient descent bishop 5.1, 5.2, 5.3
2/9 Support Vectors strong duality bishop 7.1
2/14 Support Vectors the kernel trick bishop 6.1, 6.2
2/16 Probabilistic Inference message passing bishop 8.4
2/21 Tree decomposition cyclic graphs koller and friedman
2/23 Expectation Maximization L = Q + H + D bishop 9
2/28 Expectation Maximization mixture of gaussians bishop 9
3/1 Sampling Markov Chain Monte Carlo bishop 11.2
3/6 Sampling Gibbs Sampling bishop 11.3
3/8 Learning Theory Error bounds vapnik ch 4
3/20 Review
3/22 Midterm
3/27 Midterm Solutions
3/29 Eigenvectors least squares, PCA bishop 12.1
4/3 Logistic Regression maximum entropy bishop 4.3
4/5 Hidden Markov Models forward-backward bishop 13.2
4/10 Optimization LBFGS Nocedal 8.1, 9.1
4/12 Particle Filters slam Thrun et al. ch 4
4/17 Reinforcement Learning q-learning ballard 11
4/19 Games nash equilibrium morris 115-131
4/24 Games learning to co-operate
4/26 Something Fun Thomas Cover cover 1968
5/1 Review come to class with questions!
Final Exam: Friday May 11, 8:30-11:30am, CSB 601.

Grading

  • Final exam: 35%
  • Homeworks: 35%
  • Midterm: 25%
  • Class participation: 5%
gildea @ cs rochester edu
April 24, 2012