Retrieval process of an associative memory with non-monotonic input-output function

Hidetoshi Nishimori, Ioan Opris

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Citation (Scopus)

Abstract

The retrieval process of an associative memory with a general input-output function is studied by means of a signal-to-noise ratio analysis. We derive a set of recursion relations for macroscopic variables to describe the time development of the network. By taking equilibrium limit of the recursion relations, we find that a certain type of non-monotonic input-output relation of a single neuron yields an enhanced memory capacity than the conventional monotonic relation. This result combined with Monte Carlo simulations confirms the prediction of Morita et al and reveals new aspects in the retrieval process.

Original languageEnglish (US)
Title of host publication1993 IEEE International Conference on Neural Networks
Editors Anon
PublisherPubl by IEEE
Pages353-358
Number of pages6
ISBN (Print)0780312007
StatePublished - Jan 1 1993
Externally publishedYes
Event1993 IEEE International Conference on Neural Networks - San Francisco, CA, USA
Duration: Mar 28 1993Apr 1 1993

Other

Other1993 IEEE International Conference on Neural Networks
CitySan Francisco, CA, USA
Period3/28/934/1/93

Fingerprint

Data storage equipment
Neurons
Signal to noise ratio
Monte Carlo simulation

ASJC Scopus subject areas

  • Engineering(all)

Cite this

Nishimori, H., & Opris, I. (1993). Retrieval process of an associative memory with non-monotonic input-output function. In Anon (Ed.), 1993 IEEE International Conference on Neural Networks (pp. 353-358). Publ by IEEE.

Retrieval process of an associative memory with non-monotonic input-output function. / Nishimori, Hidetoshi; Opris, Ioan.

1993 IEEE International Conference on Neural Networks. ed. / Anon. Publ by IEEE, 1993. p. 353-358.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Nishimori, H & Opris, I 1993, Retrieval process of an associative memory with non-monotonic input-output function. in Anon (ed.), 1993 IEEE International Conference on Neural Networks. Publ by IEEE, pp. 353-358, 1993 IEEE International Conference on Neural Networks, San Francisco, CA, USA, 3/28/93.
Nishimori H, Opris I. Retrieval process of an associative memory with non-monotonic input-output function. In Anon, editor, 1993 IEEE International Conference on Neural Networks. Publ by IEEE. 1993. p. 353-358
Nishimori, Hidetoshi ; Opris, Ioan. / Retrieval process of an associative memory with non-monotonic input-output function. 1993 IEEE International Conference on Neural Networks. editor / Anon. Publ by IEEE, 1993. pp. 353-358
@inproceedings{8327cb2e3f0d4e5e983f16f38cd4e9d9,
title = "Retrieval process of an associative memory with non-monotonic input-output function",
abstract = "The retrieval process of an associative memory with a general input-output function is studied by means of a signal-to-noise ratio analysis. We derive a set of recursion relations for macroscopic variables to describe the time development of the network. By taking equilibrium limit of the recursion relations, we find that a certain type of non-monotonic input-output relation of a single neuron yields an enhanced memory capacity than the conventional monotonic relation. This result combined with Monte Carlo simulations confirms the prediction of Morita et al and reveals new aspects in the retrieval process.",
author = "Hidetoshi Nishimori and Ioan Opris",
year = "1993",
month = "1",
day = "1",
language = "English (US)",
isbn = "0780312007",
pages = "353--358",
editor = "Anon",
booktitle = "1993 IEEE International Conference on Neural Networks",
publisher = "Publ by IEEE",

}

TY - GEN

T1 - Retrieval process of an associative memory with non-monotonic input-output function

AU - Nishimori, Hidetoshi

AU - Opris, Ioan

PY - 1993/1/1

Y1 - 1993/1/1

N2 - The retrieval process of an associative memory with a general input-output function is studied by means of a signal-to-noise ratio analysis. We derive a set of recursion relations for macroscopic variables to describe the time development of the network. By taking equilibrium limit of the recursion relations, we find that a certain type of non-monotonic input-output relation of a single neuron yields an enhanced memory capacity than the conventional monotonic relation. This result combined with Monte Carlo simulations confirms the prediction of Morita et al and reveals new aspects in the retrieval process.

AB - The retrieval process of an associative memory with a general input-output function is studied by means of a signal-to-noise ratio analysis. We derive a set of recursion relations for macroscopic variables to describe the time development of the network. By taking equilibrium limit of the recursion relations, we find that a certain type of non-monotonic input-output relation of a single neuron yields an enhanced memory capacity than the conventional monotonic relation. This result combined with Monte Carlo simulations confirms the prediction of Morita et al and reveals new aspects in the retrieval process.

UR - http://www.scopus.com/inward/record.url?scp=0027233203&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0027233203&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:0027233203

SN - 0780312007

SP - 353

EP - 358

BT - 1993 IEEE International Conference on Neural Networks

A2 - Anon, null

PB - Publ by IEEE

ER -