Activation function of wavelet chaotic neural networks

Yao Qun Xu; Ming Sun; Meng Shu Guo

doi:10.1109/COGINF.2006.365577

Activation function of wavelet chaotic neural networks

Yao Qun Xu^*
, Ming Sun
, Meng Shu Guo

^*Corresponding author for this work

School of Mathematics

Harbin University of Commerce

Research output: Contribution to conference › Paper › peer-review

1 Scopus citations

Abstract

In this paper, we studied the activation function of chaotic neural network, at first we review Chen's chaotic neural network and then propose a novel chaotic neural network model whose activation function is compose of sigmoid and wavelet function. Second, we make an analysis of the largest Lyapunov exponents and the reversed bifurcations of the neural units of Chen's and the proposed model. Third, 10-city traveling salesman problem (TSP) is given to make a comparison between them. Finally we conclude that the novel chaotic neural network model we propose is more valid.

Original language	English
Pages	716-721
Number of pages	6
DOIs	https://doi.org/10.1109/COGINF.2006.365577
State	Published - 2006
Event	5th IEEE International Conference on Cognitive Informatics, ICCI 2006 - Beijing, China Duration: 17 Jul 2006 → 19 Jul 2006

Conference

Conference	5th IEEE International Conference on Cognitive Informatics, ICCI 2006
Country/Territory	China
City	Beijing
Period	17/07/06 → 19/07/06

Keywords

Activation function
Chaotic neural network
The largest Lyapunov exponents
Wavelet function

Access to Document

10.1109/COGINF.2006.365577

Cite this

@conference{519563a532b144289fbca46e6b9a438c,

title = "Activation function of wavelet chaotic neural networks",

abstract = "In this paper, we studied the activation function of chaotic neural network, at first we review Chen's chaotic neural network and then propose a novel chaotic neural network model whose activation function is compose of sigmoid and wavelet function. Second, we make an analysis of the largest Lyapunov exponents and the reversed bifurcations of the neural units of Chen's and the proposed model. Third, 10-city traveling salesman problem (TSP) is given to make a comparison between them. Finally we conclude that the novel chaotic neural network model we propose is more valid.",

keywords = "Activation function, Chaotic neural network, The largest Lyapunov exponents, Wavelet function",

author = "Xu, \{Yao Qun\} and Ming Sun and Guo, \{Meng Shu\}",

year = "2006",

doi = "10.1109/COGINF.2006.365577",

language = "英语",

pages = "716--721",

note = "5th IEEE International Conference on Cognitive Informatics, ICCI 2006 ; Conference date: 17-07-2006 Through 19-07-2006",

}

TY - CONF

T1 - Activation function of wavelet chaotic neural networks

AU - Xu, Yao Qun

AU - Sun, Ming

AU - Guo, Meng Shu

PY - 2006

Y1 - 2006

N2 - In this paper, we studied the activation function of chaotic neural network, at first we review Chen's chaotic neural network and then propose a novel chaotic neural network model whose activation function is compose of sigmoid and wavelet function. Second, we make an analysis of the largest Lyapunov exponents and the reversed bifurcations of the neural units of Chen's and the proposed model. Third, 10-city traveling salesman problem (TSP) is given to make a comparison between them. Finally we conclude that the novel chaotic neural network model we propose is more valid.

AB - In this paper, we studied the activation function of chaotic neural network, at first we review Chen's chaotic neural network and then propose a novel chaotic neural network model whose activation function is compose of sigmoid and wavelet function. Second, we make an analysis of the largest Lyapunov exponents and the reversed bifurcations of the neural units of Chen's and the proposed model. Third, 10-city traveling salesman problem (TSP) is given to make a comparison between them. Finally we conclude that the novel chaotic neural network model we propose is more valid.

KW - Activation function

KW - Chaotic neural network

KW - The largest Lyapunov exponents

KW - Wavelet function

UR - https://www.scopus.com/pages/publications/67349280544

U2 - 10.1109/COGINF.2006.365577

DO - 10.1109/COGINF.2006.365577

M3 - 论文

AN - SCOPUS:67349280544

SP - 716

EP - 721

T2 - 5th IEEE International Conference on Cognitive Informatics, ICCI 2006

Y2 - 17 July 2006 through 19 July 2006

ER -

Activation function of wavelet chaotic neural networks

Abstract

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this