Note: in order to play the pencast files you need to download and install livescribe desktop.

Lecture Slides Chapter Extras
00 Introduction   Intro to Matlab
my_regress.m
CH01PR19.txt
plot_gpa_fit.m
01 Sum and Product Rules
Bayes Nets
   
02 cont.    
03 Computational Aspects of Discrete and Linear Gaussian Models 8.1  
04 Conditional Independence &
Markov Random Fields
8.2-3  
05 Inference in Graphical Models & Factor Graphs 8.4  
06 cont.    
07 Sum product Algorithm (Belief Propagation)    
08 cont.    
09 cont.    
10 K-means clustering and Gaussian Mixture Models 9.1  
11 Expectation Maximization for GMM’s 9.2  
12 cont.    
13 Generalized EM
9.4  
14 cont.    
15 EM for linear regression,(pencast)    
16 Variational Inference 10.1  
17 Variational Inference Cont. 10.1  
18 Variational GMM 10.2  
19 Variational Inference Usage 10.6  
20 Basic sampling methods 11.1  
21 Markov chain Monte Carlo 11.2 Neal tech. report
22 cont. 11.3  
23 PCA 12.1  
24 (Hidden) Markov Models 13.1  
25 Forward backward, Viterbi, Sum product again 13.2  
26 Linear dynamical systems, Kalman filter 13.3  
27 Particle filtering    
Term: Fall 2010
Time: Tu-Th, 6:10pm-7:25pm
Location : Hamilton Hall 603
Professor: Frank Wood
Email: fwood@stat.columbia.edu
Office:
Room 1017
School of Social Work
Office Hours:
11am-1pm Wed
TA: Nicholas Bartlett
Email: nsb2130@columbia.edu
Office:
Room 1023
School of Social Work
Hours:
Friday, 8:00am - 9:55am
Room 1025
School of Social Work