Stochastic bidirectional training

Author

Gedeon, T.D.

Author_Institution

Dept. of Inf. Eng., New South Wales Univ., Sydney, NSW, Australia

Volume

2

fYear

1998

fDate

11-14 Oct 1998

Firstpage

1968

Abstract

We consider connectionist compression schemes using auto-associative networks, demonstrate the advantages gained by imposing different constraints on allowed network weights, and give a comparison with pruning of the unconstrained auto-associative network. In this paper we demonstrate the advantages for generalisation performance of constraining weights symmetrically using weight sharing, and by constraining functional symmetry by the use of enhanced backpropagation networks trained bidirectionally. In the process, we derive the stochastic bidirectional training algorithm

Keywords

backpropagation; feedforward neural nets; generalisation (artificial intelligence); network topology; auto-associative networks; backpropagation networks; bidirectional learning; feedforward neural networks; functional symmetry; generalisation; network weights; pruning; topology; weight sharing; Backpropagation algorithms; Computer science; Costs; Electronic mail; Image coding; Network topology; Neural networks; Neurons; Stochastic processes; Switches;

fLanguage

English

Publisher

ieee

Conference_Titel

Systems, Man, and Cybernetics, 1998. 1998 IEEE International Conference on

Conference_Location

San Diego, CA

ISSN

1062-922X

Print_ISBN

0-7803-4778-1

Type

conf

DOI

10.1109/ICSMC.1998.728185

Filename

728185