Varieties of Helmholtz machine

被引：71

作者：

Dayan, P ^{[1
]}

Hinton, GE ^{[1
]}

机构：

[1] UNIV TORONTO, TORONTO, ON M5S 1A1, CANADA

来源：

NEURAL NETWORKS | 1996年 / 9卷 / 08期

基金：

加拿大自然科学与工程研究理事会;

关键词：

expectation-maximization; unsupervised learning; feedback connections;

D O I：

10.1016/S0893-6080(96)00009-3

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

The Helmholtz machine is a new unsupervised learning architecture that uses top-down connections to build probability density models of input and bottom-up connections to build inverses to those models. The wake-sleep learning algorithm for the machine involves just the purely local delta rule. This paper suggests a number of different varieties of Helmholtz machines, each with its own strengths and weaknesses. and relates them to cortical information processing. Copyright (C) 1996 Elsevier Science Ltd.

引用

收藏

页码：1385 / 1403

页数：19

相关论文

共 65 条

[1] THE EM ALGORITHM AND INFORMATION GEOMETRY IN NEURAL-NETWORK LEARNING [J].

AMARI, S .

NEURAL COMPUTATION, 1995, 7 (01) :13-18

[2]

ANTONINI A, 1993, J NEUROSCI, V13, P3549

[3] DIFFERENT VOLTAGE-DEPENDENT THRESHOLDS FOR INDUCING LONG-TERM DEPRESSION AND LONG-TERM POTENTIATION IN SLICES OF RAT VISUAL-CORTEX [J].

ARTOLA, A ;

BROCHER, S ;

SINGER, W .

NATURE, 1990, 347 (6288) :69-72

[4] Unsupervised Learning [J].

Barlow, H. B. .

NEURAL COMPUTATION, 1989, 1 (03) :295-311

[5] PATTERN-RECOGNIZING STOCHASTIC LEARNING AUTOMATA [J].

BARTO, AG ;

ANANDAN, P .

IEEE TRANSACTIONS ON SYSTEMS MAN AND CYBERNETICS, 1985, 15 (03) :360-375

[6] AN INEQUALITY WITH APPLICATIONS TO STATISTICAL ESTIMATION FOR PROBABILISTIC FUNCTIONS OF MARKOV PROCESSES AND TO A MODEL FOR ECOLOGY [J].

BAUM, LE ;

EAGON, JA .

BULLETIN OF THE AMERICAN MATHEMATICAL SOCIETY, 1967, 73 (03) :360-&

[7] A MAXIMIZATION TECHNIQUE OCCURRING IN STATISTICAL ANALYSIS OF PROBABILISTIC FUNCTIONS OF MARKOV CHAINS [J].

BAUM, LE ;

PETRIE, T ;

SOULES, G ;

WEISS, N .

ANNALS OF MATHEMATICAL STATISTICS, 1970, 41 (01) :164-&

[8] SELF-ORGANIZING NEURAL NETWORK THAT DISCOVERS SURFACES IN RANDOM-DOT STEREOGRAMS [J].

BECKER, S ;

HINTON, GE .

NATURE, 1992, 355 (6356) :161-163

[9] THEORY OF ORIENTATION TUNING IN VISUAL-CORTEX [J].

BENYISHAI, R ;

BAROR, RL ;

SOMPOLINSKY, H .

PROCEEDINGS OF THE NATIONAL ACADEMY OF SCIENCES OF THE UNITED STATES OF AMERICA, 1995, 92 (09) :3844-3848

[10] A MASSIVELY PARALLEL ARCHITECTURE FOR A SELF-ORGANIZING NEURAL PATTERN-RECOGNITION MACHINE [J].

CARPENTER, GA ;

GROSSBERG, S .

COMPUTER VISION GRAPHICS AND IMAGE PROCESSING, 1987, 37 (01) :54-115

← 1 2 3 4 5 6 7 →