On a chaotic neural network with decaying chaotic noise

Tianyi Ma; Ling Wang; Yingtao Jiang; Xiaozong Yang

doi:10.1007/11427391_79

On a chaotic neural network with decaying chaotic noise

Tianyi Ma^*
, Ling Wang
, Yingtao Jiang
, Xiaozong Yang

^*Corresponding author for this work

Faculty of Computing

Harbin Institute of Technology
University of Nevada, Las Vegas

Research output: Contribution to journal › Conference article › peer-review

Abstract

In this paper, we propose a novel chaotic Hopfield neural network (CHNN), which introduces chaotic noise to each neuron of a discrete-time Hopfield neural network (HNN), and the noise is gradually reduced to zero. The proposed CHNN has richer and more complex dynamics than HNN, and the transient chaos enables the network to escape from local energy minima and to settle down at the global optimal solution. We have applied this method to solve a few traveling salesman problems, and simulations show that the proposed CHNN can converge to the global or near global optimal solutions more efficiently than the HNN.

Original language	English
Pages (from-to)	497-502
Number of pages	6
Journal	Lecture Notes in Computer Science
Volume	3496
Issue number	I
DOIs	https://doi.org/10.1007/11427391_79
State	Published - 2005
Event	Second International Symposium on Neural Networks: Advances in Neural Networks - ISNN 2005 - Chongqing, China Duration: 30 May 2005 → 1 Jun 2005

Access to Document

10.1007/11427391_79

Cite this

@article{c6ed9c2564f94546bc61def7856597e9,

title = "On a chaotic neural network with decaying chaotic noise",

abstract = "In this paper, we propose a novel chaotic Hopfield neural network (CHNN), which introduces chaotic noise to each neuron of a discrete-time Hopfield neural network (HNN), and the noise is gradually reduced to zero. The proposed CHNN has richer and more complex dynamics than HNN, and the transient chaos enables the network to escape from local energy minima and to settle down at the global optimal solution. We have applied this method to solve a few traveling salesman problems, and simulations show that the proposed CHNN can converge to the global or near global optimal solutions more efficiently than the HNN.",

author = "Tianyi Ma and Ling Wang and Yingtao Jiang and Xiaozong Yang",

year = "2005",

doi = "10.1007/11427391\_79",

language = "英语",

volume = "3496",

pages = "497--502",

journal = "Lecture Notes in Computer Science",

issn = "0302-9743",

publisher = "Springer Science and Business Media Deutschland GmbH",

number = "I",

note = "Second International Symposium on Neural Networks: Advances in Neural Networks - ISNN 2005 ; Conference date: 30-05-2005 Through 01-06-2005",

}

TY - JOUR

T1 - On a chaotic neural network with decaying chaotic noise

AU - Ma, Tianyi

AU - Wang, Ling

AU - Jiang, Yingtao

AU - Yang, Xiaozong

PY - 2005

Y1 - 2005

N2 - In this paper, we propose a novel chaotic Hopfield neural network (CHNN), which introduces chaotic noise to each neuron of a discrete-time Hopfield neural network (HNN), and the noise is gradually reduced to zero. The proposed CHNN has richer and more complex dynamics than HNN, and the transient chaos enables the network to escape from local energy minima and to settle down at the global optimal solution. We have applied this method to solve a few traveling salesman problems, and simulations show that the proposed CHNN can converge to the global or near global optimal solutions more efficiently than the HNN.

AB - In this paper, we propose a novel chaotic Hopfield neural network (CHNN), which introduces chaotic noise to each neuron of a discrete-time Hopfield neural network (HNN), and the noise is gradually reduced to zero. The proposed CHNN has richer and more complex dynamics than HNN, and the transient chaos enables the network to escape from local energy minima and to settle down at the global optimal solution. We have applied this method to solve a few traveling salesman problems, and simulations show that the proposed CHNN can converge to the global or near global optimal solutions more efficiently than the HNN.

UR - https://www.scopus.com/pages/publications/24944587650

U2 - 10.1007/11427391_79

DO - 10.1007/11427391_79

M3 - 会议文章

AN - SCOPUS:24944587650

SN - 0302-9743

VL - 3496

SP - 497

EP - 502

JO - Lecture Notes in Computer Science

JF - Lecture Notes in Computer Science

IS - I

T2 - Second International Symposium on Neural Networks: Advances in Neural Networks - ISNN 2005

Y2 - 30 May 2005 through 1 June 2005

ER -

On a chaotic neural network with decaying chaotic noise

Abstract

Access to Document

Other files and links

Fingerprint

Cite this