What kind of a Graphical Model
is the Brain?
Two types of unsupervised neural network
The learning rule for sigmoid belief nets
Why learning is hard in a sigmoid belief net.
How a Boltzmann Machine models data
The Energy of a joint configuration
Using energies to define probabilities
Four reasons why learning is
impractical
in Boltzmann Machines
A picture of the Boltzmann machine learning algorithm for an RBM
Contrastive divergence
learning:
A quick way to learn an RBM
Using an RBM to learn a model of a digit class
The weights learned by the 100 hidden units
A surprising relationship between Boltzmann Machines and Sigmoid Belief Nets
Using complementary priors to eliminate explaining away
An example of a complementary prior
Inference in a DAG with replicated weights
Learning by dividing and conquering
Another way to divide and conquer
Pro’s and con’s of replicating the weights
Multilayer contrastive divergence
A simplified version with all hidden layers the same size
Why the hidden configurations should be treated as data when learning the next layer of weights
A neural network model of digit recognition
Examples of correctly recognized MNIST test digits (the 49 closest calls)
Learning with realistic labels
A different way to capture low-dimensional manifolds
The flaws in the wake-sleep algorithm
The up-down algorithm:
A contrastive divergence version of wake-sleep
The receptive fields of the first hidden layer
The generative fields of the first hidden layer
Independence relationships
of hidden variables
in three types of model