Improved simulated annealing mechanics in transiently chaotic neural network

Author

Bo, Kang ; Li Xinyu ; Bingchao, Lu

Author_Institution

Coll. of Autom. Eng., Univ. of Electron. Sci. & Technol. of China, Chengdu, China

Volume

2

fYear

2004

Firstpage

1057

Abstract

The paper analyses the dynamic characteristics of transiently chaotic neural networks (TCNN), finding that they quite sensitively depend on the value of the self-feedback connection weights, and researches the annealing function that intensively influences the veracity and search speed of the TCNN model. Improved simulated annealing mechanics are proposed for the value of the self-feedback connection weights that can accelerate the search speed and guarantee the accuracy of the optimal arithmetic. To demonstrate the validity of these mechanics, two examples of function optimization problems are given.

Keywords

neural nets; optimisation; simulated annealing; annealing function; function optimization problems; optimal arithmetic; optimization; search speed; self-feedback connection weights; simulated annealing mechanics; transiently chaotic neural networks; Acceleration; Arithmetic; Cellular neural networks; Chaos; Computer networks; Concurrent computing; Intelligent networks; Neural networks; Neurons; Simulated annealing;

fLanguage

English

Publisher

ieee

Conference_Titel

Communications, Circuits and Systems, 2004. ICCCAS 2004. 2004 International Conference on

Print_ISBN

0-7803-8647-7

Type

conf

DOI

10.1109/ICCCAS.2004.1346359

Filename

1346359