Transiently chaotic neural networks with piecewise linear output functions

Shyan Shiou Chen, Chih W. Shih

Research output: Contribution to journalArticle

4 Citations (Scopus)

Abstract

Admitting both transient chaotic phase and convergent phase, the transiently chaotic neural network (TCNN) provides superior performance than the classical networks in solving combinatorial optimization problems. We derive concrete parameter conditions for these two essential dynamic phases of the TCNN with piecewise linear output function. The confirmation for chaotic dynamics of the system results from a successful application of the Marotto theorem which was recently clarified. Numerical simulation on applying the TCNN with piecewise linear output function is carried out to find the optimal solution of a travelling salesman problem. It is demonstrated that the performance is even better than the previous TCNN model with logistic output function.

Original languageEnglish
Pages (from-to)717-730
Number of pages14
JournalChaos, Solitons and Fractals
Volume39
Issue number2
DOIs
Publication statusPublished - 2009 Jan 30

Fingerprint

Chaotic Neural Network
Piecewise Linear
Output
Chaotic Dynamics
Travelling salesman problems
Combinatorial Optimization Problem
Neural Network Model
Logistics
Optimal Solution
Numerical Simulation
Theorem

ASJC Scopus subject areas

  • Mathematics(all)

Cite this

Transiently chaotic neural networks with piecewise linear output functions. / Chen, Shyan Shiou; Shih, Chih W.

In: Chaos, Solitons and Fractals, Vol. 39, No. 2, 30.01.2009, p. 717-730.

Research output: Contribution to journalArticle

@article{b7ca1c38260c431dbc5218ab57e103d2,
title = "Transiently chaotic neural networks with piecewise linear output functions",
abstract = "Admitting both transient chaotic phase and convergent phase, the transiently chaotic neural network (TCNN) provides superior performance than the classical networks in solving combinatorial optimization problems. We derive concrete parameter conditions for these two essential dynamic phases of the TCNN with piecewise linear output function. The confirmation for chaotic dynamics of the system results from a successful application of the Marotto theorem which was recently clarified. Numerical simulation on applying the TCNN with piecewise linear output function is carried out to find the optimal solution of a travelling salesman problem. It is demonstrated that the performance is even better than the previous TCNN model with logistic output function.",
author = "Chen, {Shyan Shiou} and Shih, {Chih W.}",
year = "2009",
month = "1",
day = "30",
doi = "10.1016/j.chaos.2007.01.103",
language = "English",
volume = "39",
pages = "717--730",
journal = "Chaos, Solitons and Fractals",
issn = "0960-0779",
publisher = "Elsevier Limited",
number = "2",

}

TY - JOUR

T1 - Transiently chaotic neural networks with piecewise linear output functions

AU - Chen, Shyan Shiou

AU - Shih, Chih W.

PY - 2009/1/30

Y1 - 2009/1/30

N2 - Admitting both transient chaotic phase and convergent phase, the transiently chaotic neural network (TCNN) provides superior performance than the classical networks in solving combinatorial optimization problems. We derive concrete parameter conditions for these two essential dynamic phases of the TCNN with piecewise linear output function. The confirmation for chaotic dynamics of the system results from a successful application of the Marotto theorem which was recently clarified. Numerical simulation on applying the TCNN with piecewise linear output function is carried out to find the optimal solution of a travelling salesman problem. It is demonstrated that the performance is even better than the previous TCNN model with logistic output function.

AB - Admitting both transient chaotic phase and convergent phase, the transiently chaotic neural network (TCNN) provides superior performance than the classical networks in solving combinatorial optimization problems. We derive concrete parameter conditions for these two essential dynamic phases of the TCNN with piecewise linear output function. The confirmation for chaotic dynamics of the system results from a successful application of the Marotto theorem which was recently clarified. Numerical simulation on applying the TCNN with piecewise linear output function is carried out to find the optimal solution of a travelling salesman problem. It is demonstrated that the performance is even better than the previous TCNN model with logistic output function.

UR - http://www.scopus.com/inward/record.url?scp=62549158682&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=62549158682&partnerID=8YFLogxK

U2 - 10.1016/j.chaos.2007.01.103

DO - 10.1016/j.chaos.2007.01.103

M3 - Article

AN - SCOPUS:62549158682

VL - 39

SP - 717

EP - 730

JO - Chaos, Solitons and Fractals

JF - Chaos, Solitons and Fractals

SN - 0960-0779

IS - 2

ER -