CSC321: Neural Networks
 
Lecture 19: Boltzmann Machines as Probabilistic Models

Modeling binary data

A naïve model for binary data

A mixture of naïve models

Limitations of mixture models

Dealing with compositional structure

How a Boltzmann Machine models data

The Energy of a joint configuration

Using energies to define probabilities

An example of how weights define a distribution

Getting a sample from the model

Getting a sample from the posterior distribution over distributed representations
for a given data vector