Simultaneous optimization of weights and structure of an RBF neural network

Authors:
Virginie Lefort;Carole Knibbe;Guillaume Beslon;Joël Favrel
Affiliations:
INSA-IF/PRISMa, Villeurbanne, France;INSA-IF/PRISMa, Villeurbanne, France;INSA-IF/PRISMa, Villeurbanne, France;INSA-IF/PRISMa, Villeurbanne, France
Venue:
EA'05 Proceedings of the 7th international conference on Artificial Evolution
Year:
2005

Citing 9
Cited 5

A real-coded genetic algorithm for training recurrent neural networks

Neural Networks
Incremental Evolution in ANNs: Neural Netswhich Grow

Artificial Intelligence Review
Neural Networks: A Comprehensive Foundation

Neural Networks: A Comprehensive Foundation
Genetic Algorithms in Search, Optimization and Machine Learning

Genetic Algorithms in Search, Optimization and Machine Learning
An Algebraic Model for Generating and Adapting Neural Networks by Means of Optimization Methods

Annals of Mathematics and Artificial Intelligence
A Survey of Intron Research in Genetics

PPSN IV Proceedings of the 4th International Conference on Parallel Problem Solving from Nature
Optimization of Recurrent NN by GA with Variable Length Genotype

AI '02 Proceedings of the 15th Australian Joint Conference on Artificial Intelligence: Advances in Artificial Intelligence
Putting more genetics into genetic algorithms

Evolutionary Computation
Self-adaptation of genome size in artificial organisms

ECAL'05 Proceedings of the 8th European conference on Advances in Artificial Life

Improving generalization of radial basis function network with adaptive multi-objective particle swarm optimization

SMC'09 Proceedings of the 2009 IEEE international conference on Systems, Man and Cybernetics
Radial basis function network based on time variant multi-objective particle swarm optimization for medical diseases diagnosis

Applied Soft Computing
Memetic Elitist Pareto Differential Evolution algorithm based Radial Basis Function Networks for classification problems

Applied Soft Computing
Multi-objective hybrid evolutionary algorithms for radial basis function neural network design

Knowledge-Based Systems
Robust Neuroevolutionary Identification of Nonlinear Nonstationary Objects

Cybernetics and Systems Analysis

Quantified Score

Hi-index	0.00

Visualization

Abstract

We propose here a new evolutionary algorithm, the RBF-Gene algorithm, to optimize Radial Basis Function Neural Networks. Unlike other works on this subject, our algorithm can evolve both the structure and the numerical parameters of the network: it is able to evolve the number of neurons and their weights. The RBF-Gene algorithm's behavior is shown on a simple toy problem, the 2D sine wave. Results on a classical benchmark are then presented. They show that our algorithm is able to fit the data very well while keeping the structure simple – the solution can be applied generally.