Intersection learning for bidirectional associative memory

Motonobu Hattori, Masafumi Hagiwara

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

4 Citations (Scopus)

Abstract

In this paper, we propose Intersection Learning for Bidirectional Associative Memory (ILBAM). The proposed ILBAM is based on a novel relaxation method. A number of computer simulations show the following effectiveness of the proposed ILBAM: (1) It can guarantee the recall of all training pairs. (2) It requires much less weights renewal times than the conventional methods. (3) It becomes more effective in case there are many training pairs to be stored. (4) It is insensitive to the correlation of training pairs. (5) It contributes to the noise reduction effect of the BAM.

Original languageEnglish
Title of host publicationIEEE International Conference on Neural Networks - Conference Proceedings
PublisherIEEE
Pages555-560
Number of pages6
Volume1
Publication statusPublished - 1996
EventProceedings of the 1996 IEEE International Conference on Neural Networks, ICNN. Part 1 (of 4) - Washington, DC, USA
Duration: 1996 Jun 31996 Jun 6

Other

OtherProceedings of the 1996 IEEE International Conference on Neural Networks, ICNN. Part 1 (of 4)
CityWashington, DC, USA
Period96/6/396/6/6

Fingerprint

Data storage equipment
Noise abatement
Computer simulation

ASJC Scopus subject areas

  • Software

Cite this

Hattori, M., & Hagiwara, M. (1996). Intersection learning for bidirectional associative memory. In IEEE International Conference on Neural Networks - Conference Proceedings (Vol. 1, pp. 555-560). IEEE.

Intersection learning for bidirectional associative memory. / Hattori, Motonobu; Hagiwara, Masafumi.

IEEE International Conference on Neural Networks - Conference Proceedings. Vol. 1 IEEE, 1996. p. 555-560.

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

Hattori, M & Hagiwara, M 1996, Intersection learning for bidirectional associative memory. in IEEE International Conference on Neural Networks - Conference Proceedings. vol. 1, IEEE, pp. 555-560, Proceedings of the 1996 IEEE International Conference on Neural Networks, ICNN. Part 1 (of 4), Washington, DC, USA, 96/6/3.
Hattori M, Hagiwara M. Intersection learning for bidirectional associative memory. In IEEE International Conference on Neural Networks - Conference Proceedings. Vol. 1. IEEE. 1996. p. 555-560
Hattori, Motonobu ; Hagiwara, Masafumi. / Intersection learning for bidirectional associative memory. IEEE International Conference on Neural Networks - Conference Proceedings. Vol. 1 IEEE, 1996. pp. 555-560
@inproceedings{60bc43dee7f041aba300f036b68b933e,
title = "Intersection learning for bidirectional associative memory",
abstract = "In this paper, we propose Intersection Learning for Bidirectional Associative Memory (ILBAM). The proposed ILBAM is based on a novel relaxation method. A number of computer simulations show the following effectiveness of the proposed ILBAM: (1) It can guarantee the recall of all training pairs. (2) It requires much less weights renewal times than the conventional methods. (3) It becomes more effective in case there are many training pairs to be stored. (4) It is insensitive to the correlation of training pairs. (5) It contributes to the noise reduction effect of the BAM.",
author = "Motonobu Hattori and Masafumi Hagiwara",
year = "1996",
language = "English",
volume = "1",
pages = "555--560",
booktitle = "IEEE International Conference on Neural Networks - Conference Proceedings",
publisher = "IEEE",

}

TY - GEN

T1 - Intersection learning for bidirectional associative memory

AU - Hattori, Motonobu

AU - Hagiwara, Masafumi

PY - 1996

Y1 - 1996

N2 - In this paper, we propose Intersection Learning for Bidirectional Associative Memory (ILBAM). The proposed ILBAM is based on a novel relaxation method. A number of computer simulations show the following effectiveness of the proposed ILBAM: (1) It can guarantee the recall of all training pairs. (2) It requires much less weights renewal times than the conventional methods. (3) It becomes more effective in case there are many training pairs to be stored. (4) It is insensitive to the correlation of training pairs. (5) It contributes to the noise reduction effect of the BAM.

AB - In this paper, we propose Intersection Learning for Bidirectional Associative Memory (ILBAM). The proposed ILBAM is based on a novel relaxation method. A number of computer simulations show the following effectiveness of the proposed ILBAM: (1) It can guarantee the recall of all training pairs. (2) It requires much less weights renewal times than the conventional methods. (3) It becomes more effective in case there are many training pairs to be stored. (4) It is insensitive to the correlation of training pairs. (5) It contributes to the noise reduction effect of the BAM.

UR - http://www.scopus.com/inward/record.url?scp=0029728312&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0029728312&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:0029728312

VL - 1

SP - 555

EP - 560

BT - IEEE International Conference on Neural Networks - Conference Proceedings

PB - IEEE

ER -