Effects of the chaotic noise on the performance of a neural network model for optimization problems

Yoshinori Hayakawa; Atsushi Marumoto; Yasuji Sawada

doi:10.1103/PhysRevE.51.R2693

Effects of the chaotic noise on the performance of a neural network model for optimization problems

Yoshinori Hayakawa, Atsushi Marumoto, Yasuji Sawada

Center for Data-driven Science and Artificial Intelligence (CDS)

Tohoku University

Research output: Contribution to journal › Article › peer-review

83 Citations (Scopus)

Abstract

We studied effects of chaos added to the dynamics of a neural network model. By numerical simulations, we found the neural network with forcing by chaotic noise operated very efficiently to solve an optimization problem. We also showed that short time correlation of chaos was relevant to the dynamics of the network and it could work effectively for global minima search.

Original language	English
Pages (from-to)	R2693-R2696
Journal	Physical Review E
Volume	51
Issue number	4
DOIs	https://doi.org/10.1103/PhysRevE.51.R2693
Publication status	Published - 1995

Access to Document

10.1103/PhysRevE.51.R2693

Cite this

@article{97cf768af4444c3288ac028eaaa57f4a,

title = "Effects of the chaotic noise on the performance of a neural network model for optimization problems",

abstract = "We studied effects of chaos added to the dynamics of a neural network model. By numerical simulations, we found the neural network with forcing by chaotic noise operated very efficiently to solve an optimization problem. We also showed that short time correlation of chaos was relevant to the dynamics of the network and it could work effectively for global minima search.",

author = "Yoshinori Hayakawa and Atsushi Marumoto and Yasuji Sawada",

year = "1995",

doi = "10.1103/PhysRevE.51.R2693",

language = "English",

volume = "51",

pages = "R2693--R2696",

journal = "Physical Review E",

issn = "2470-0045",

publisher = "American Physical Society",

number = "4",

}

TY - JOUR

T1 - Effects of the chaotic noise on the performance of a neural network model for optimization problems

AU - Hayakawa, Yoshinori

AU - Marumoto, Atsushi

AU - Sawada, Yasuji

PY - 1995

Y1 - 1995

N2 - We studied effects of chaos added to the dynamics of a neural network model. By numerical simulations, we found the neural network with forcing by chaotic noise operated very efficiently to solve an optimization problem. We also showed that short time correlation of chaos was relevant to the dynamics of the network and it could work effectively for global minima search.

AB - We studied effects of chaos added to the dynamics of a neural network model. By numerical simulations, we found the neural network with forcing by chaotic noise operated very efficiently to solve an optimization problem. We also showed that short time correlation of chaos was relevant to the dynamics of the network and it could work effectively for global minima search.

UR - http://www.scopus.com/inward/record.url?scp=0000161130&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0000161130&partnerID=8YFLogxK

U2 - 10.1103/PhysRevE.51.R2693

DO - 10.1103/PhysRevE.51.R2693

M3 - Article

AN - SCOPUS:0000161130

SN - 2470-0045

VL - 51

SP - R2693-R2696

JO - Physical Review E

JF - Physical Review E

IS - 4

ER -

Effects of the chaotic noise on the performance of a neural network model for optimization problems

Abstract

Access to Document

Other files and links

Fingerprint

Cite this