Machine Learning over Text & Images - Autumn School

Generative Latent Space Models for Text and Image

author: Eric Xing, Carnegie Mellon University

Categories

Top: Computer Science: Image Analysis
Top: Computer Science: Text Mining
Top: Computer Science: Machine Learning: Graphical Models

You might be experiencing some problems with Your Video player.

*Slides*
0:00	Generative Latent Space Models for Text and Image - a probabilistic graphical overview
1:23	Outline
2:19	Apoptosis + Medicine
3:31	Apoptosis + Medicine 01
3:52	Apoptosis + Medicine 02
4:18	Probabilistic Graphical Model Primer
5:03	What is a graphical model?
6:37	Recap of Basic Prob. Concepts
8:13	Dependencies among variables
9:13	Graphical Models
12:16	Graphical Models, con'd
15:35	Two types of GMs
16:10	Directed Graphical Models
17:00	Bayesian Network
19:59	Conditional probability tables (CPTs)
20:31	Conditional probability density func. (CPDs)
21:11	Markov Random Fields
22:22	An (incomplete) genealogy of graphical models
23:20	GM application: Speech recognition
24:30	GM application: Evolution
25:26	GM application: Solid State Physics
26:10	Probabilistic Inference
30:14	Learning Graphical Models
33:47	A GM course
34:17	The Problem
36:32	Modeling document collections
37:34	Probabilistic Modeling of Text Documents
38:10	Questions of Interest
38:33	Connecting Probability Models to Data
39:36	Conditionally Independent Observations
40:14	“Plate” Notation
40:28	Example: Gaussian Model
41:43	Example: Bayesian Gaussian Model
41:59	Latent Semantic Structure
43:20	GENERATIVE PROCESS
46:14	A generative model for documents
46:40	Probabilistic LSI
48:43	Probabilistic LSI01
49:58	Latent Dirichlet Allocation
50:46	LDA
50:53	Correlated Topic Model
54:08	Inference Tasks
54:20	Bayesian inference
55:16	Approximate Inference
57:00	Bayesian model selection
57:10	Bayesian model selection 01
57:32	Bayesian model selection 02
57:33	The desired LL curve
57:46	Integrating Topics and Syntax
58:45	Topic Hierarchies
59:51	Modeling Topic Evolution
60:30	Latent Space Models for Images
61:25	Image representation
62:46	Exchangeability
63:43	Corr-LDA
65:05	Automatic annotation
66:08	Text-based image retrieval
66:28	Appendix: approximate inference

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.