Instructor:
Dan Gildea office hours Wed 23pm
TA: Darcey Riley (dystopiananomaly @ gmail com), office hours Wed 11am12pm and Thurs 45pm, 7th floor software lab
Location: Tu/Th 11:05am12:20pm, 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
On  we will cover  which means that after class you will understand  if before class you have read 
1/19 
Probability Theory 
independence, bayes rule
 bishop 1.2, 1.4, app E 
1/24 
Information Theory 
entropy, kldistance, 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 
forwardbackward
 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 
qlearning
 ballard 11 
4/19 
Games 
nash equilibrium
 morris 115131 
4/24 
Games 
learning to cooperate
 
4/26 
Something Fun 
Thomas Cover
 cover 1968 
5/1 
Review 
come to class with questions!
 
Final Exam: Friday May 11, 8:3011:30am, CSB 601.
Grading
 Final exam: 35%
 Homeworks: 35%
 Midterm: 25%
 Class participation: 5%
gildea @ cs rochester edu
April 24, 2012
