Complexity of block-sequential update for symmetric neural networks

Eric Goles, Martin Matamala

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

2 Scopus citations

Abstract

We prove that the dynamics of arbitrary neural networks (non necessarily symmetric) of size n can be simulated by symmetric neural nets of size 3n updated in a block-sequential mode. As a particular case we prove that the class of symmetric neural nets with arbitrary diagonal elements updated sequentially is universal i. e. it simulates any non-symmetric neural networks dynamics.

Original languageEnglish
Title of host publicationProceedings of the International Joint Conference on Neural Networks
Editors Anon
PublisherPubl by IEEE
Pages1469-1472
Number of pages4
ISBN (Print)0780314212
StatePublished - 1993
Externally publishedYes
EventProceedings of 1993 International Joint Conference on Neural Networks. Part 2 (of 3) - Nagoya, Jpn
Duration: 25 Oct 199329 Oct 1993

Publication series

NameProceedings of the International Joint Conference on Neural Networks
Volume2

Conference

ConferenceProceedings of 1993 International Joint Conference on Neural Networks. Part 2 (of 3)
CityNagoya, Jpn
Period25/10/9329/10/93

Fingerprint

Dive into the research topics of 'Complexity of block-sequential update for symmetric neural networks'. Together they form a unique fingerprint.

Cite this