EPSRC Winter School in Mathematics for Data Modelling

Graphical models

author: Zoubin Ghahramani, University of Cambridge

Description

This presentations provide an introduction to graphical models together with more advanced topics on inference, propagation and learning structure.

Categories

Top: Computer Science: Machine Learning: Graphical Models

You might be experiencing some problems with Your Video player.

*Slides*
0:00	Lecture 1: Introduction to Graphical Models
2:43	Three Main Kinds of Graphical Models
3:36	Why Do We Need Graphical Models?
6:03	Conditional Independence
7:44	Conditional and Marginal Independence (Examples)
9:37	Factor Graphs - 1
11:29	Factor Graphs - 2
15:00	Directed Acyclic Graphical Models (Bayesian Networks) - 1
16:47	Directed Acyclic Graphical Models (Bayesian Networks) - 2
20:25	Examples of D-Separation in DAGs
21:51	Directed Graphs for Statistical Models: Plate Notation
23:13	Summary
23:42	Lecture 2: Inference and Propagation Algorithms
24:11	Inference in a Graphical Model - 1
26:47	Inference in a Graphical Model - 2
29:04	- Questions
31:48	- Questions
36:52	Belief Propagation
39:17	Belief Propagation (cont.)
39:57	Factor Graph Propagation
40:18	Factor Graphs
41:26	Propagation in Factor Graphs - 1
43:02	Propagation in Factor Graphs - 2
43:49	Propagation in Factor Graphs - 3
44:42	Propagation in Factor Graphs - 2
44:50	Propagation in Factor Graphs - 3
46:29	Propagation in Factor Graphs - 4
48:50	Inference in Hidden Markov Models and Linear Gaussian State-Space Models
51:57	- Questions
58:36	- Questions
60:02	Lecture 3: Learning Parameters and Structure
60:23	Learning Parameters - 1
63:10	Learning Parameters - 2
67:19	Maximum Likelihood Learning with Hidden Variables: The EM Algorithm - 1
68:22	Maximum Likelihood Learning with Hidden Variables: The EM Algorithm - 2
69:02	Maximum Likelihood Learning with Hidden Variables: The EM Algorithm - 3
69:42	Maximum Likelihood Learning with Hidden Variables: The EM Algorithm - 4
70:40	Bayesian Parameter Learning with No Hidden Variables
70:45	Maximum Likelihood Learning with Hidden Variables: The EM Algorithm - 4
70:55	Bayesian Parameter Learning with No Hidden Variables
73:35	Dirichlet Distribution - 1
73:42	Dirichlet Distribution - 2
74:15	Example
75:10	Bayesian Parameter Learning with Hidden Variables
75:25	Bayesian Parameter Learning with No Hidden Variables
75:28	Bayesian Parameter Learning with Hidden Variables
75:37	Summary of Parameter Learning
76:31	Structure Learning - 1
78:00	Structure Learning - 2
78:48	Score-Based Structure Learning for Complete Data
78:52	Bayesian Structural EM for Incomplete Data
78:53	Score-Based Structure Learning for Complete Data
79:51	Bayesian Structural EM for Incomplete Data
80:02	Directed Graphical Models and Causality
80:05	Learning Parameters and Structure in Undirected Graphs
80:06	Summary
80:06	Learning Parameters and Structure in Undirected Graphs
80:20	Summary

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.