Improved chaotic neuro-computer with output-coding for quadratic assignment problems

Koji Mori; Yoshihiko Horio; Kazuyuki Aihara

doi:10.1109/IJCNN.2005.1556459

Improved chaotic neuro-computer with output-coding for quadratic assignment problems

Koji Mori, Yoshihiko Horio, Kazuyuki Aihara

RIEC - Human and Bio Information Systems Division

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

1 Citation (Scopus)

Abstract

In this paper, we improve performance of a chaotic neuro-computer in solving quadratic assignment problems (QAPs) by adopting an output-coding which constructs a feasible solution from analog internal-states of neurons at each iteration. Through measurements from the chaotic neuro-computer hardware, we show that we constantly obtain the optimum solution for size-10 QAPs. Furthermore, chaotic search dynamics through chaotic itinerancy is confirmed from time evolutions of a cost function and an energy function. Moreover, we observe internal states of arbitrary three neurons in a network to extract useful information on network dynamics that is effective in solving the QAPs.

Original language	English
Title of host publication	Proceedings of the International Joint Conference on Neural Networks, IJCNN 2005
Pages	3312-3317
Number of pages	6
DOIs	https://doi.org/10.1109/IJCNN.2005.1556459
Publication status	Published - 2005
Event	International Joint Conference on Neural Networks, IJCNN 2005 - Montreal, QC, Canada Duration: 2005 Jul 31 → 2005 Aug 4

Publication series

Name	Proceedings of the International Joint Conference on Neural Networks
Volume	5

Conference

Conference	International Joint Conference on Neural Networks, IJCNN 2005
Country/Territory	Canada
City	Montreal, QC
Period	05/7/31 → 05/8/4

Access to Document

10.1109/IJCNN.2005.1556459

Cite this

@inproceedings{7acd8be7ec7845ed88074d6ca0ad029f,

title = "Improved chaotic neuro-computer with output-coding for quadratic assignment problems",

abstract = "In this paper, we improve performance of a chaotic neuro-computer in solving quadratic assignment problems (QAPs) by adopting an output-coding which constructs a feasible solution from analog internal-states of neurons at each iteration. Through measurements from the chaotic neuro-computer hardware, we show that we constantly obtain the optimum solution for size-10 QAPs. Furthermore, chaotic search dynamics through chaotic itinerancy is confirmed from time evolutions of a cost function and an energy function. Moreover, we observe internal states of arbitrary three neurons in a network to extract useful information on network dynamics that is effective in solving the QAPs.",

author = "Koji Mori and Yoshihiko Horio and Kazuyuki Aihara",

year = "2005",

doi = "10.1109/IJCNN.2005.1556459",

language = "English",

isbn = "0780390482",

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

pages = "3312--3317",

booktitle = "Proceedings of the International Joint Conference on Neural Networks, IJCNN 2005",

note = "International Joint Conference on Neural Networks, IJCNN 2005 ; Conference date: 31-07-2005 Through 04-08-2005",

}

Mori, K, Horio, Y & Aihara, K 2005, Improved chaotic neuro-computer with output-coding for quadratic assignment problems. in Proceedings of the International Joint Conference on Neural Networks, IJCNN 2005., 1556459, Proceedings of the International Joint Conference on Neural Networks, vol. 5, pp. 3312-3317, International Joint Conference on Neural Networks, IJCNN 2005, Montreal, QC, Canada, 05/7/31. https://doi.org/10.1109/IJCNN.2005.1556459

Improved chaotic neuro-computer with output-coding for quadratic assignment problems. / Mori, Koji; Horio, Yoshihiko; Aihara, Kazuyuki.
Proceedings of the International Joint Conference on Neural Networks, IJCNN 2005. 2005. p. 3312-3317 1556459 (Proceedings of the International Joint Conference on Neural Networks; Vol. 5).

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

TY - GEN

T1 - Improved chaotic neuro-computer with output-coding for quadratic assignment problems

AU - Mori, Koji

AU - Horio, Yoshihiko

AU - Aihara, Kazuyuki

PY - 2005

Y1 - 2005

N2 - In this paper, we improve performance of a chaotic neuro-computer in solving quadratic assignment problems (QAPs) by adopting an output-coding which constructs a feasible solution from analog internal-states of neurons at each iteration. Through measurements from the chaotic neuro-computer hardware, we show that we constantly obtain the optimum solution for size-10 QAPs. Furthermore, chaotic search dynamics through chaotic itinerancy is confirmed from time evolutions of a cost function and an energy function. Moreover, we observe internal states of arbitrary three neurons in a network to extract useful information on network dynamics that is effective in solving the QAPs.

AB - In this paper, we improve performance of a chaotic neuro-computer in solving quadratic assignment problems (QAPs) by adopting an output-coding which constructs a feasible solution from analog internal-states of neurons at each iteration. Through measurements from the chaotic neuro-computer hardware, we show that we constantly obtain the optimum solution for size-10 QAPs. Furthermore, chaotic search dynamics through chaotic itinerancy is confirmed from time evolutions of a cost function and an energy function. Moreover, we observe internal states of arbitrary three neurons in a network to extract useful information on network dynamics that is effective in solving the QAPs.

UR - http://www.scopus.com/inward/record.url?scp=33750130435&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=33750130435&partnerID=8YFLogxK

U2 - 10.1109/IJCNN.2005.1556459

DO - 10.1109/IJCNN.2005.1556459

M3 - Conference contribution

AN - SCOPUS:33750130435

SN - 0780390482

SN - 9780780390485

T3 - Proceedings of the International Joint Conference on Neural Networks

SP - 3312

EP - 3317

BT - Proceedings of the International Joint Conference on Neural Networks, IJCNN 2005

T2 - International Joint Conference on Neural Networks, IJCNN 2005

Y2 - 31 July 2005 through 4 August 2005

ER -

Improved chaotic neuro-computer with output-coding for quadratic assignment problems

Abstract

Publication series

Conference

Access to Document

Other files and links

Fingerprint

Cite this