The Helmholtz Machine

The Helmholtz Machine (1995)

Cached

Download Links

by Peter Dayan , Geoffrey E. Hinton , Radford M. Neal , Richard S. Zemel

Citations:

165 - 22 self

Versions

Version History

Metadata Version 1

User correction supplied by mph

Datum	Value	Source
TITLE	The Helmholtz Machine	user correction
AUTHOR NAME	Peter Dayan	user correction
AUTHOR AFFIL	Department of Computer Science, University of Toronto,; 6 King’s College Road	user correction
AUTHOR ADDR	Toronto, Ontario M5S 1A4, Canada	user correction
AUTHOR NAME	Geoffrey E. Hinton	user correction
AUTHOR AFFIL	Department of Computer Science, University of Toronto,; 6 King’s College Road	user correction
AUTHOR ADDR	Toronto, Ontario M5S 1A4, Canada	user correction
AUTHOR NAME	Radford M. Neal	user correction
AUTHOR AFFIL	Department of Computer Science, University of Toronto,; 6 King’s College Road	user correction
AUTHOR ADDR	Toronto, Ontario M5S 1A4, Canada	user correction
AUTHOR NAME	Richard S. Zemel	user correction
AUTHOR AFFIL	CNL, The Salk Institute	user correction
AUTHOR ADDR	PO Box 85800, San Diego, CA 92186-5800 USA	user correction
ABSTRACT	Discovering the structure inherent in a set of patterns is a fundamental aim of statistical inference or learning. One fruitful approach is to build a parameterized stochastic generative model, independent draws from which are likely to produce the patterns. For all but the simplest generative models, each pattern can be generated in exponentially many ways. It is thus intractable to adjust the parameters to maximize the probability of the observed patterns. We describe a way of finessing this combinatorial explosion by maximizing an easily computed lower bound on the probability of the observations. Our method can be viewed as a form of hierarchical self-supervised learning that may relate to the function of bottom-up and top-down cortical processing pathways.	user correction
YEAR	1995	user correction
CITATIONS	28 found	ParsCit 1.0