Graphical Models and Machine Learning

EE 639 Advanced Topics in Signal Processing and Communication

[Home] [Lectures] [Homework] [Related Links]

Dates	Lecture	Readings
1/9	Introduction to the course	MIJ ch 2 Hammersley-Clifford Theorem
1/10	Parameterization of Joint Probability
1/15	Equivalence between conditional independence and DAG parameterization
1/17	Bayes Ball Algorithm
1/22	Introduction to Undirected Graph
1/24	Examples of Undirected Graph
1/29	Inference with Elimination	MIJ ch 3 MIJ ch 4 MIJ ch 17
1/31	Belief Propagation
2/5	Clique Graphs and Junction Tree Properties
2/12	Junction Tree 1/3
2/14	Junction Tree 2/3
2/21	Junction Tree 3/3 [video 1 2]
2/25	Parameter learning [video 1 2]	CMB ch1,2 MIJ ch 5
2/26	ML and MAP estimators for density
2/28	Basic Decision Theory
3/4	Latent Parameter learning with Expectation Maximization	CMB ch 9 MIJ ch 10 (10.1), ch 11
3/6	Expectation Maximization and Model Selection	CMB ch 9 MIJ ch 10 (10.1), ch 11
3/18	Mid-term (everything up to 3/6)	Solution
3/25	Linear Classification	CMB ch. 2,4 MIJ ch 7
3/27	Logistic function and Exponential Family	CMB ch. 2,4 MIJ ch. 8
4/1	Logistic Regression with IRLS
4/3	Bayesian Logistic Regression
4/8	Kernel Method	CMB ch. 6 MIJ ch.13 (multivariate Guassian)
4/10	Kernel Engineering
4/15	Gaussian Process Regression
4/17	Support Vector Machine (1)	CMB ch.7 Appendix E