Analysis of hysteresis in Hopfield and T-model neural networks

Zheng Tang; Okihiko Ishizuka; Masakazu Sakai; Hiroki Matsumoto

Analysis of hysteresis in Hopfield and T-model neural networks

Zheng Tang^*, Okihiko Ishizuka, Masakazu Sakai, Hiroki Matsumoto

^*Corresponding author for this work

Intellectual Information Engineering

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

1 Scopus citations

Abstract

We report on an experimental hysteresis in the Hopfield network and give a detail mathematical description of the hysteresis phenomenon. It is the hysteresis that makes the Hopfield network difficult to reach the global minimum. This paper presents a T-Model network approach to overcoming the hysteresis phenomenon. Theoretical analysis of the T-Model network is also given. The hysteresis phenomenon in the Hopfield and the T-Model networks is illustrated through experiments and simulations. The experiments agree with the theoretical analysis very well.

Original language	English
Title of host publication	Proceedings of the International Joint Conference on Neural Networks
Editors	Anon
Publisher	Publ by IEEE
Pages	1477-1480
Number of pages	4
ISBN (Print)	0780314212
State	Published - 1993
Event	Proceedings of 1993 International Joint Conference on Neural Networks. Part 2 (of 3) - Nagoya, Jpn Duration: 1993/10/25 → 1993/10/29

Publication series

Name	Proceedings of the International Joint Conference on Neural Networks
Volume	2

Conference

Conference	Proceedings of 1993 International Joint Conference on Neural Networks. Part 2 (of 3)
City	Nagoya, Jpn
Period	1993/10/25 → 1993/10/29

ASJC Scopus subject areas

Software
Artificial Intelligence

Cite this

@inproceedings{9bd6bdd8a990441eb5badd88762210e0,

title = "Analysis of hysteresis in Hopfield and T-model neural networks",

abstract = "We report on an experimental hysteresis in the Hopfield network and give a detail mathematical description of the hysteresis phenomenon. It is the hysteresis that makes the Hopfield network difficult to reach the global minimum. This paper presents a T-Model network approach to overcoming the hysteresis phenomenon. Theoretical analysis of the T-Model network is also given. The hysteresis phenomenon in the Hopfield and the T-Model networks is illustrated through experiments and simulations. The experiments agree with the theoretical analysis very well.",

author = "Zheng Tang and Okihiko Ishizuka and Masakazu Sakai and Hiroki Matsumoto",

year = "1993",

language = "英語",

isbn = "0780314212",

series = "Proceedings of the International Joint Conference on Neural Networks",

publisher = "Publ by IEEE",

pages = "1477--1480",

editor = "Anon",

booktitle = "Proceedings of the International Joint Conference on Neural Networks",

note = "Proceedings of 1993 International Joint Conference on Neural Networks. Part 2 (of 3) ; Conference date: 25-10-1993 Through 29-10-1993",

}

Tang, Z, Ishizuka, O, Sakai, M & Matsumoto, H 1993, Analysis of hysteresis in Hopfield and T-model neural networks. in Anon (ed.), Proceedings of the International Joint Conference on Neural Networks. Proceedings of the International Joint Conference on Neural Networks, vol. 2, Publ by IEEE, pp. 1477-1480, Proceedings of 1993 International Joint Conference on Neural Networks. Part 2 (of 3), Nagoya, Jpn, 1993/10/25.

Analysis of hysteresis in Hopfield and T-model neural networks. / Tang, Zheng; Ishizuka, Okihiko; Sakai, Masakazu et al.
Proceedings of the International Joint Conference on Neural Networks. ed. / Anon. Publ by IEEE, 1993. p. 1477-1480 (Proceedings of the International Joint Conference on Neural Networks; Vol. 2).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Analysis of hysteresis in Hopfield and T-model neural networks

AU - Tang, Zheng

AU - Ishizuka, Okihiko

AU - Sakai, Masakazu

AU - Matsumoto, Hiroki

PY - 1993

Y1 - 1993

N2 - We report on an experimental hysteresis in the Hopfield network and give a detail mathematical description of the hysteresis phenomenon. It is the hysteresis that makes the Hopfield network difficult to reach the global minimum. This paper presents a T-Model network approach to overcoming the hysteresis phenomenon. Theoretical analysis of the T-Model network is also given. The hysteresis phenomenon in the Hopfield and the T-Model networks is illustrated through experiments and simulations. The experiments agree with the theoretical analysis very well.

AB - We report on an experimental hysteresis in the Hopfield network and give a detail mathematical description of the hysteresis phenomenon. It is the hysteresis that makes the Hopfield network difficult to reach the global minimum. This paper presents a T-Model network approach to overcoming the hysteresis phenomenon. Theoretical analysis of the T-Model network is also given. The hysteresis phenomenon in the Hopfield and the T-Model networks is illustrated through experiments and simulations. The experiments agree with the theoretical analysis very well.

UR - http://www.scopus.com/inward/record.url?scp=0027814128&partnerID=8YFLogxK

M3 - 会議への寄与

AN - SCOPUS:0027814128

SN - 0780314212

T3 - Proceedings of the International Joint Conference on Neural Networks

SP - 1477

EP - 1480

BT - Proceedings of the International Joint Conference on Neural Networks

A2 - Anon, null

PB - Publ by IEEE

T2 - Proceedings of 1993 International Joint Conference on Neural Networks. Part 2 (of 3)

Y2 - 25 October 1993 through 29 October 1993

ER -

Analysis of hysteresis in Hopfield and T-model neural networks

Abstract

Publication series

Conference

ASJC Scopus subject areas

Fingerprint

Cite this