Lamarckian evolution of associative memory

Akira Imada, Keijiro Araki

Research output: Contribution to conferencePaper

6 Citations (Scopus)

Abstract

There have been a lot of researches which apply evolutionary techniques to layered neural networks. However, their applications to Hopfield neural networks remain few so far. We are applying genetic algorithms to fully connected associative memory model of Hopfield. In an earlier paper, we reported that random weight matrices were evolved to store some number of patterns only by means of a simple genetic algorithm. In this paper we present that the storage capacity can be enlarged by incorporating Lamarckian inheritance to the genetic algorithm.

Original languageEnglish
Pages676-680
Number of pages5
Publication statusPublished - Jan 1 1996
EventProceedings of the 1996 IEEE International Conference on Evolutionary Computation, ICEC'96 - Nagoya, Jpn
Duration: May 20 1996May 22 1996

Other

OtherProceedings of the 1996 IEEE International Conference on Evolutionary Computation, ICEC'96
CityNagoya, Jpn
Period5/20/965/22/96

Fingerprint

Genetic algorithms
Data storage equipment
Hopfield neural networks
Neural networks

All Science Journal Classification (ASJC) codes

  • Engineering(all)

Cite this

Imada, A., & Araki, K. (1996). Lamarckian evolution of associative memory. 676-680. Paper presented at Proceedings of the 1996 IEEE International Conference on Evolutionary Computation, ICEC'96, Nagoya, Jpn, .

Lamarckian evolution of associative memory. / Imada, Akira; Araki, Keijiro.

1996. 676-680 Paper presented at Proceedings of the 1996 IEEE International Conference on Evolutionary Computation, ICEC'96, Nagoya, Jpn, .

Research output: Contribution to conferencePaper

Imada, A & Araki, K 1996, 'Lamarckian evolution of associative memory', Paper presented at Proceedings of the 1996 IEEE International Conference on Evolutionary Computation, ICEC'96, Nagoya, Jpn, 5/20/96 - 5/22/96 pp. 676-680.
Imada A, Araki K. Lamarckian evolution of associative memory. 1996. Paper presented at Proceedings of the 1996 IEEE International Conference on Evolutionary Computation, ICEC'96, Nagoya, Jpn, .
Imada, Akira ; Araki, Keijiro. / Lamarckian evolution of associative memory. Paper presented at Proceedings of the 1996 IEEE International Conference on Evolutionary Computation, ICEC'96, Nagoya, Jpn, .5 p.
@conference{b215d6645e9d4c75874ad66de590f495,
title = "Lamarckian evolution of associative memory",
abstract = "There have been a lot of researches which apply evolutionary techniques to layered neural networks. However, their applications to Hopfield neural networks remain few so far. We are applying genetic algorithms to fully connected associative memory model of Hopfield. In an earlier paper, we reported that random weight matrices were evolved to store some number of patterns only by means of a simple genetic algorithm. In this paper we present that the storage capacity can be enlarged by incorporating Lamarckian inheritance to the genetic algorithm.",
author = "Akira Imada and Keijiro Araki",
year = "1996",
month = "1",
day = "1",
language = "English",
pages = "676--680",
note = "Proceedings of the 1996 IEEE International Conference on Evolutionary Computation, ICEC'96 ; Conference date: 20-05-1996 Through 22-05-1996",

}

TY - CONF

T1 - Lamarckian evolution of associative memory

AU - Imada, Akira

AU - Araki, Keijiro

PY - 1996/1/1

Y1 - 1996/1/1

N2 - There have been a lot of researches which apply evolutionary techniques to layered neural networks. However, their applications to Hopfield neural networks remain few so far. We are applying genetic algorithms to fully connected associative memory model of Hopfield. In an earlier paper, we reported that random weight matrices were evolved to store some number of patterns only by means of a simple genetic algorithm. In this paper we present that the storage capacity can be enlarged by incorporating Lamarckian inheritance to the genetic algorithm.

AB - There have been a lot of researches which apply evolutionary techniques to layered neural networks. However, their applications to Hopfield neural networks remain few so far. We are applying genetic algorithms to fully connected associative memory model of Hopfield. In an earlier paper, we reported that random weight matrices were evolved to store some number of patterns only by means of a simple genetic algorithm. In this paper we present that the storage capacity can be enlarged by incorporating Lamarckian inheritance to the genetic algorithm.

UR - http://www.scopus.com/inward/record.url?scp=0029712943&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0029712943&partnerID=8YFLogxK

M3 - Paper

AN - SCOPUS:0029712943

SP - 676

EP - 680

ER -