A novel hysteretic chaotic neural network and its applications

Xiangdong Liu; Chunbo Xiu

doi:10.1016/j.neucom.2007.02.002

A novel hysteretic chaotic neural network and its applications

Xiangdong Liu
, Chunbo Xiu^*

^*Corresponding author for this work

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

30 Citations (Scopus)

Abstract

A model of single neuron with chaotic and hysteretic characteristics is proposed. Neural network coupled by such neurons exhibits complex dynamic behaviors. The network is also studied from the viewpoint of optimization. Chaos and hysteresis phenomena make the network have the characteristic of escaping from a local minimum of the energy function, so it can find a global minimum more easily as compared with others. The experimental results show that it has a higher average success rate of obtaining a global optimization solution.

Original language	English
Pages (from-to)	2561-2565
Number of pages	5
Journal	Neurocomputing
Volume	70
Issue number	13-15
DOIs	https://doi.org/10.1016/j.neucom.2007.02.002
Publication status	Published - Aug 2007
Externally published	Yes

Keywords

Chaos
Hysteresis
Neural network
Neurons
TSP

Access to Document

10.1016/j.neucom.2007.02.002

Cite this

@article{3b40a16438194ec08741e5e2a7900362,

title = "A novel hysteretic chaotic neural network and its applications",

abstract = "A model of single neuron with chaotic and hysteretic characteristics is proposed. Neural network coupled by such neurons exhibits complex dynamic behaviors. The network is also studied from the viewpoint of optimization. Chaos and hysteresis phenomena make the network have the characteristic of escaping from a local minimum of the energy function, so it can find a global minimum more easily as compared with others. The experimental results show that it has a higher average success rate of obtaining a global optimization solution.",

keywords = "Chaos, Hysteresis, Neural network, Neurons, TSP",

author = "Xiangdong Liu and Chunbo Xiu",

year = "2007",

month = aug,

doi = "10.1016/j.neucom.2007.02.002",

language = "English",

volume = "70",

pages = "2561--2565",

journal = "Neurocomputing",

issn = "0925-2312",

publisher = "Elsevier B.V.",

number = "13-15",

}

TY - JOUR

T1 - A novel hysteretic chaotic neural network and its applications

AU - Liu, Xiangdong

AU - Xiu, Chunbo

PY - 2007/8

Y1 - 2007/8

N2 - A model of single neuron with chaotic and hysteretic characteristics is proposed. Neural network coupled by such neurons exhibits complex dynamic behaviors. The network is also studied from the viewpoint of optimization. Chaos and hysteresis phenomena make the network have the characteristic of escaping from a local minimum of the energy function, so it can find a global minimum more easily as compared with others. The experimental results show that it has a higher average success rate of obtaining a global optimization solution.

AB - A model of single neuron with chaotic and hysteretic characteristics is proposed. Neural network coupled by such neurons exhibits complex dynamic behaviors. The network is also studied from the viewpoint of optimization. Chaos and hysteresis phenomena make the network have the characteristic of escaping from a local minimum of the energy function, so it can find a global minimum more easily as compared with others. The experimental results show that it has a higher average success rate of obtaining a global optimization solution.

KW - Chaos

KW - Hysteresis

KW - Neural network

KW - Neurons

KW - TSP

UR - https://www.scopus.com/pages/publications/34249651431

U2 - 10.1016/j.neucom.2007.02.002

DO - 10.1016/j.neucom.2007.02.002

M3 - Article

AN - SCOPUS:34249651431

SN - 0925-2312

VL - 70

SP - 2561

EP - 2565

JO - Neurocomputing

JF - Neurocomputing

IS - 13-15

ER -

A novel hysteretic chaotic neural network and its applications

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this