Nature Inspired Methods in the Radial Basis Function Network Learning Process

Authors:
Miroslav Burša;Lenka Lhotská
Affiliations:
Gerstner Laboratory, BioDat Research Group, Czech Technical University in Prague,;Gerstner Laboratory, BioDat Research Group, Czech Technical University in Prague,
Venue:
ICANN '08 Proceedings of the 18th international conference on Artificial Neural Networks, Part II
Year:
2008

Citing 9
Cited 0

Growing cell structures—a self-organizing network for unsupervised and supervised learning

Neural Networks
Introduction to artificial life

Introduction to artificial life
On how pachycondyla apicalis ants suggest a new search algorithm

Future Generation Computer Systems
A New Ant Colony Algorithm Using the Heterarchical Concept Aimed at Optimization of Multiminima Continuous Functions

ANTS '02 Proceedings of the Third International Workshop on Ant Algorithms
The Ant Colony Metaphor for Searching Continuous Design Spaces

Selected Papers from AISB Workshop on Evolutionary Computing
Ant Colony Optimization

Ant Colony Optimization
Ant colony optimization theory: a survey

Theoretical Computer Science
A new version of the ant-miner algorithm discovering unordered rule sets

Proceedings of the 8th annual conference on Genetic and evolutionary computation
Fast learning in networks of locally-tuned processing units

Neural Computation

Quantified Score

Hi-index	0.00

Visualization

Abstract

In present we benefit from the use of nature processes which provide us with highly effective heuristics for solving various problems. Their advantages are mainly prominent in hybrid approach. This paper evaluates several approaches for learning neural network based on Radial Basis Function (RBF) for distinguishing different sets in $\mathcal{R}^{L}$. RBF networks use one layer of hidden RBF units and the number of RBF units is kept constatnt. In the paper we evaluate the ACO$_\mathcal{R}$ (Ant Colony Approach for Real domain) approach inspired by ant behavior and the PSO (Particle Swarm Optimization) algorithm inspired by behavior of flock of birds or fish in the nature. Nature inspired and classical algorithms are compared and evaluated.