CIAR Summer School
Tutorial
Lecture 1b
Sigmoid Belief Nets
Discovering causal structure as a goal for unsupervised learning
Bayes Nets:
Directed Acyclic Graphical models
Ways to define the conditional probabilities
What is easy and what is hard in a DAG?
The learning rule for sigmoid belief nets
The derivatives of the log prob
The cost of sending a complete configuration
Sampling from the posterior distribution
Computing the posterior for i given the rest
A trade-off between how well the model fits the data and the tractability of inference