Quick learning for multidirectional associative memories

Motonobu Hattori, Masafumi Hagiwara

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

8 Citations (Scopus)

Abstract

In this paper, Quick Learning algorithm for Multidirectional Associative Memories (MAMs) is proposed. Owing to the Quick Learning algorithm, not only the storage capacity of the MAMs can be improved, but also the recall of all training data can be guaranteed. In addition, several important characteristics of the MAMs such as the relation between the required learning epochs and the number of layers and the relation between the noise reduction effect and the number of layers are introduced.

Original languageEnglish
Title of host publicationIEEE International Conference on Neural Networks - Conference Proceedings
PublisherIEEE
Pages1949-1954
Number of pages6
Volume4
Publication statusPublished - 1995
EventProceedings of the 1995 IEEE International Conference on Neural Networks. Part 1 (of 6) - Perth, Aust
Duration: 1995 Nov 271995 Dec 1

Other

OtherProceedings of the 1995 IEEE International Conference on Neural Networks. Part 1 (of 6)
CityPerth, Aust
Period95/11/2795/12/1

Fingerprint

Data storage equipment
Learning algorithms
Noise abatement

ASJC Scopus subject areas

  • Software

Cite this

Hattori, M., & Hagiwara, M. (1995). Quick learning for multidirectional associative memories. In IEEE International Conference on Neural Networks - Conference Proceedings (Vol. 4, pp. 1949-1954). IEEE.

Quick learning for multidirectional associative memories. / Hattori, Motonobu; Hagiwara, Masafumi.

IEEE International Conference on Neural Networks - Conference Proceedings. Vol. 4 IEEE, 1995. p. 1949-1954.

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

Hattori, M & Hagiwara, M 1995, Quick learning for multidirectional associative memories. in IEEE International Conference on Neural Networks - Conference Proceedings. vol. 4, IEEE, pp. 1949-1954, Proceedings of the 1995 IEEE International Conference on Neural Networks. Part 1 (of 6), Perth, Aust, 95/11/27.
Hattori M, Hagiwara M. Quick learning for multidirectional associative memories. In IEEE International Conference on Neural Networks - Conference Proceedings. Vol. 4. IEEE. 1995. p. 1949-1954
Hattori, Motonobu ; Hagiwara, Masafumi. / Quick learning for multidirectional associative memories. IEEE International Conference on Neural Networks - Conference Proceedings. Vol. 4 IEEE, 1995. pp. 1949-1954
@inproceedings{012a321370f846dfb32d91e9ffcfaa2a,
title = "Quick learning for multidirectional associative memories",
abstract = "In this paper, Quick Learning algorithm for Multidirectional Associative Memories (MAMs) is proposed. Owing to the Quick Learning algorithm, not only the storage capacity of the MAMs can be improved, but also the recall of all training data can be guaranteed. In addition, several important characteristics of the MAMs such as the relation between the required learning epochs and the number of layers and the relation between the noise reduction effect and the number of layers are introduced.",
author = "Motonobu Hattori and Masafumi Hagiwara",
year = "1995",
language = "English",
volume = "4",
pages = "1949--1954",
booktitle = "IEEE International Conference on Neural Networks - Conference Proceedings",
publisher = "IEEE",

}

TY - GEN

T1 - Quick learning for multidirectional associative memories

AU - Hattori, Motonobu

AU - Hagiwara, Masafumi

PY - 1995

Y1 - 1995

N2 - In this paper, Quick Learning algorithm for Multidirectional Associative Memories (MAMs) is proposed. Owing to the Quick Learning algorithm, not only the storage capacity of the MAMs can be improved, but also the recall of all training data can be guaranteed. In addition, several important characteristics of the MAMs such as the relation between the required learning epochs and the number of layers and the relation between the noise reduction effect and the number of layers are introduced.

AB - In this paper, Quick Learning algorithm for Multidirectional Associative Memories (MAMs) is proposed. Owing to the Quick Learning algorithm, not only the storage capacity of the MAMs can be improved, but also the recall of all training data can be guaranteed. In addition, several important characteristics of the MAMs such as the relation between the required learning epochs and the number of layers and the relation between the noise reduction effect and the number of layers are introduced.

UR - http://www.scopus.com/inward/record.url?scp=0029514614&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0029514614&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:0029514614

VL - 4

SP - 1949

EP - 1954

BT - IEEE International Conference on Neural Networks - Conference Proceedings

PB - IEEE

ER -