Machine Learning over Text & Images - Autumn School

Undirected Graphical Models for Text & Image

author: Eric Xing, Carnegie Mellon University

Categories

Top: Computer Science: Machine Learning: Graphical Models

You might be experiencing some problems with Your Video player.

*Slides*
0:00	Undirected Graphical Models for Test and Images
1:20	Overview
2:22	The Vector Space Model
4:01	The Corpora Matrix
4:53	Feature Vector Representation
6:27	Motivation for modeling latent t opical aspects
8:14	Latent Semantic Indexing
8:23	Singular Value Decomposition
13:01	Latent Semantic Structure
13:33	Two layer Bayesian network
14:54	Probabilistic LSI
15:55	Comparison of model semantics
18:11	Properties of Directed Networks (1)
19:44	Properties of Directed Networks (2)
21:34	Two-layer Markov Random Fields
24:06	The Undirected Alternative
24:36	Properties of Harmoniums
27:54	A Constructive Definition (1)
29:18	A Constructive Definition (2)
35:01	The Computational Trade-off
36:26	A Harmonium for IR
39:43	A Binomial Word-count Model
41:29	Comparison of model semantics
44:12	Comparison of text-models
46:26	Comparison of topic representation
47:09	Multi-Source Data
47:37	GM-mixture
48:25	The Harmonium Counterpart
48:55	Inter-Source Associations
49:05	Multi-wing Harmoniums
50:55	Examples of Latent Topics
52:55	Classification
55:11	Retrieval
55:36	Precision-recall
55:48	Annotation
57:02	Conclusions
57:41	Conclusions, con'd

Lecture rating

People found this lecture:
Worth seeing
because it is:
Valuable and informative
Well presented
Easily understandable
Acceptably recorded
You need to login to cast your vote.

Report a problem or upload files

If you have found a problem with this lecture or would like to send us extra material, articles, exercises, etc., please use our ticket system to describe your request and upload the data.
Enter your e-mail into the 'Cc' field, and we will keep you updated with your request's status.