CIAR Second Summer School Tutorial
Lecture 2a
Learning a Deep Belief Net
A neural network model of digit recognition
Why its hard to learn belief nets one layer at a time
Using complementary priors to eliminate explaining away
An example of a complementary prior
Inference in a DAG with replicated weights
A picture of the Boltzmann machine learning algorithm for an RBM
Multilayer contrastive divergence
A simplified version with all hidden layers the same size
Learning a deep causal network
"Then freeze the bottom layer..."
"Then freeze the bottom two..."
Why the hidden configurations should be treated as data when learning the next layer of weights
Examples of correctly recognized MNIST test digits (the 49 closest calls)
The flaws in the wake-sleep algorithm
A contrastive divergence version of wake-sleep
A different way to capture low-dimensional manifolds
Learning with realistic labels
Some problems with
backpropagation
(again!)