VARIETIES OF HELMHOLTZ MACHINE

Authors
DAYAN P HINTON GE
Citation
P. Dayan et Ge. Hinton, VARIETIES OF HELMHOLTZ MACHINE, Neural networks, 9(8), 1996, pp. 1385-1403
Citations number
65
Categorie Soggetti
Mathematical Methods, Biology & Medicine","Computer Sciences, Special Topics","Computer Science Artificial Intelligence",Neurosciences,"Physics, Applied
Journal title
Neural networks → ACNP
ISSN journal
08936080
Volume
9
Issue
8
Year of publication
1996
Pages
1385 - 1403
Database
ISI
SICI code
0893-6080(1996)9:8<1385:VOHM>2.0.ZU;2-K
Abstract
The Helmholtz machine is a new unsupervised learning architecture that uses top-down connections to build probability density models of inpu t and bottom-up connections to build inverses to those models. The wak e-sleep learning algorithm for the machine involves just the purely lo cal delta rule. This paper suggests a number of different varieties of Helmholtz machines, each with its own strengths and weaknesses. and r elates them to cortical information processing. Copyright (C) 1996 Els evier Science Ltd.