Evolutionary fuzzy system for architecture control in a constructive neural network

Author

Calvo, Rodrigo ; Figueiredo, Mauricio ; Antonelo, Eric Aislan

Author_Institution

Dept. of Comput. Sci. & Stat., Sao Paulo Univ., Brazil

fYear

2005

fDate

27-30 June 2005

Firstpage

541

Lastpage

546

Abstract

This work describes an evolutionary system to control the growth of a constructive neural network for autonomous navigation. A classifier system generates Takagi-Sugeno fuzzy rules and controls the architecture of a constructive neural network. The performance of the mobile robot guides the evolutionary learning mechanism. Experiments show the efficiency of the classifier fuzzy system for analyzing if it is worth inserting a new neuron into the architecture.

Keywords

evolutionary computation; fuzzy neural nets; learning (artificial intelligence); mobile robots; navigation; neural net architecture; Takagi-Sugeno fuzzy rules; architecture control; autonomous navigation; classifier fuzzy system; classifier system; classifier systems; constructive neural network; evolutionary fuzzy system; evolutionary learning; mobile robot; robot navigation; Control systems; Fuzzy control; Fuzzy neural networks; Fuzzy systems; Learning systems; Mobile robots; Navigation; Neural networks; Neurons; Takagi-Sugeno model; classifier systems; constructive neural networks; robot navigation;

fLanguage

English

Publisher

ieee

Conference_Titel

Computational Intelligence in Robotics and Automation, 2005. CIRA 2005. Proceedings. 2005 IEEE International Symposium on

Print_ISBN

0-7803-9355-4

Type

conf

DOI

10.1109/CIRA.2005.1554333

Filename

1554333