A Tabu based NN Learning Algorithm for Nonlinear Function Approximation

Author

Ye, Jian ; Qiao, Junfei ; Yu, Jianjun

Author_Institution

Inst. of Artificial Intelligence & Robotics, Beijing Univ. of Technol.

Volume

1

fYear

0

fDate

0-0 0

Firstpage

2998

Lastpage

3003

Abstract

In this paper, a tabu based neural network learning algorithm (TBBP) is represented to improve the function approximation ability of neural networks to nonlinear functions. By using the tabu search during the search process in the global area, the algorithm can escape from the local optimal solution and get a superior global optimization for the neural networks. The TBBP is tested in 6 different nonlinear functions. It is compared with the standard BP algorithm. The results show that the tabu search has improved the ability of the approximating ability of the neural networks

Keywords

function approximation; learning (artificial intelligence); neural nets; optimisation; search problems; local optimal solution; neural network learning algorithm; nonlinear function approximation; superior global optimization; tabu search; Approximation algorithms; Artificial intelligence; Artificial neural networks; Electronic mail; Function approximation; Intelligent control; Intelligent robots; Learning; Neural networks; Testing; function approximation; global optimization; neural network; tabu search;

fLanguage

English

Publisher

ieee

Conference_Titel

Intelligent Control and Automation, 2006. WCICA 2006. The Sixth World Congress on

Conference_Location

Dalian

Print_ISBN

1-4244-0332-4

Type

conf

DOI

10.1109/WCICA.2006.1712916

Filename

1712916