New results of quick learning for bidirectional associative memory having high capacity

Motonobu Hattori, Masafumi Hagiwara, Masao Nakagawa

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

5 Citations (Scopus)

Abstract

Several important characteristics of Quick Learning for Bidirectional Associative Memory (QLBAM) are introduced. QLBAM uses two stages learning. In the first stage, the BAM is trained by Hebbian learning and then by Pseudo-Relaxation Learning Algorithm for BAM (PRLAB). The following features of the QLBAM are made clear: 1) it is insensitive to correlation of training pairs; 2) it is robust for noisy inputs; 3) the minimum absolute value of net inputs indexes a noise margin; 4) the memory capacity is greatly improved: the maximum capacity in our simulation is about 2.2N.

Original languageEnglish
Title of host publicationIEEE International Conference on Neural Networks - Conference Proceedings
PublisherIEEE
Pages1080-1085
Number of pages6
Volume2
Publication statusPublished - 1994
EventProceedings of the 1994 IEEE International Conference on Neural Networks. Part 1 (of 7) - Orlando, FL, USA
Duration: 1994 Jun 271994 Jun 29

Other

OtherProceedings of the 1994 IEEE International Conference on Neural Networks. Part 1 (of 7)
CityOrlando, FL, USA
Period94/6/2794/6/29

Fingerprint

Data storage equipment
Learning algorithms

ASJC Scopus subject areas

  • Software

Cite this

Hattori, M., Hagiwara, M., & Nakagawa, M. (1994). New results of quick learning for bidirectional associative memory having high capacity. In IEEE International Conference on Neural Networks - Conference Proceedings (Vol. 2, pp. 1080-1085). IEEE.

New results of quick learning for bidirectional associative memory having high capacity. / Hattori, Motonobu; Hagiwara, Masafumi; Nakagawa, Masao.

IEEE International Conference on Neural Networks - Conference Proceedings. Vol. 2 IEEE, 1994. p. 1080-1085.

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

Hattori, M, Hagiwara, M & Nakagawa, M 1994, New results of quick learning for bidirectional associative memory having high capacity. in IEEE International Conference on Neural Networks - Conference Proceedings. vol. 2, IEEE, pp. 1080-1085, Proceedings of the 1994 IEEE International Conference on Neural Networks. Part 1 (of 7), Orlando, FL, USA, 94/6/27.
Hattori M, Hagiwara M, Nakagawa M. New results of quick learning for bidirectional associative memory having high capacity. In IEEE International Conference on Neural Networks - Conference Proceedings. Vol. 2. IEEE. 1994. p. 1080-1085
Hattori, Motonobu ; Hagiwara, Masafumi ; Nakagawa, Masao. / New results of quick learning for bidirectional associative memory having high capacity. IEEE International Conference on Neural Networks - Conference Proceedings. Vol. 2 IEEE, 1994. pp. 1080-1085
@inproceedings{8fc5188a70564340b8645e1dbbe6e7c4,
title = "New results of quick learning for bidirectional associative memory having high capacity",
abstract = "Several important characteristics of Quick Learning for Bidirectional Associative Memory (QLBAM) are introduced. QLBAM uses two stages learning. In the first stage, the BAM is trained by Hebbian learning and then by Pseudo-Relaxation Learning Algorithm for BAM (PRLAB). The following features of the QLBAM are made clear: 1) it is insensitive to correlation of training pairs; 2) it is robust for noisy inputs; 3) the minimum absolute value of net inputs indexes a noise margin; 4) the memory capacity is greatly improved: the maximum capacity in our simulation is about 2.2N.",
author = "Motonobu Hattori and Masafumi Hagiwara and Masao Nakagawa",
year = "1994",
language = "English",
volume = "2",
pages = "1080--1085",
booktitle = "IEEE International Conference on Neural Networks - Conference Proceedings",
publisher = "IEEE",

}

TY - GEN

T1 - New results of quick learning for bidirectional associative memory having high capacity

AU - Hattori, Motonobu

AU - Hagiwara, Masafumi

AU - Nakagawa, Masao

PY - 1994

Y1 - 1994

N2 - Several important characteristics of Quick Learning for Bidirectional Associative Memory (QLBAM) are introduced. QLBAM uses two stages learning. In the first stage, the BAM is trained by Hebbian learning and then by Pseudo-Relaxation Learning Algorithm for BAM (PRLAB). The following features of the QLBAM are made clear: 1) it is insensitive to correlation of training pairs; 2) it is robust for noisy inputs; 3) the minimum absolute value of net inputs indexes a noise margin; 4) the memory capacity is greatly improved: the maximum capacity in our simulation is about 2.2N.

AB - Several important characteristics of Quick Learning for Bidirectional Associative Memory (QLBAM) are introduced. QLBAM uses two stages learning. In the first stage, the BAM is trained by Hebbian learning and then by Pseudo-Relaxation Learning Algorithm for BAM (PRLAB). The following features of the QLBAM are made clear: 1) it is insensitive to correlation of training pairs; 2) it is robust for noisy inputs; 3) the minimum absolute value of net inputs indexes a noise margin; 4) the memory capacity is greatly improved: the maximum capacity in our simulation is about 2.2N.

UR - http://www.scopus.com/inward/record.url?scp=0028745037&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0028745037&partnerID=8YFLogxK

M3 - Conference contribution

VL - 2

SP - 1080

EP - 1085

BT - IEEE International Conference on Neural Networks - Conference Proceedings

PB - IEEE

ER -