Skip directly to content

Evolutionary fuzzy system for architecture control in a constructive neural network

on Thu, 09/29/2016 - 20:42
TitleEvolutionary fuzzy system for architecture control in a constructive neural network
Publication TypeConference Paper
Year of Publication2005
AuthorsCalvo R, Antonelo EA, Figueiredo M
Conference Name6th IEEE International Symposium on Computational Intelligence in Robotics and Automation
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.

Draft File: