Redwood Neuroscience
Title: “Learning Lateral Connections between Hidden
Units”
Computer Science Department
Abstract:
I shall show how to approximate maximum likelihood
learning in a generative model that consists of a hidden Markov Random Field
with causal connections to the observed data. After choosing a hidden code to
represent a datavector, the MRF runs for a few more
iterations ignoring the likelihood term. This provides the statistics it needs
to construct a complicated prior over code vectors. The prior uses lateral
interactions, instead of independence, to squeeze the redundancy out of the
code vectors, so the hidden units naturally form population codes.