An Evolutionary Approach for Tuning Artificial Neural Network Parameters

Authors:
Leandro M. Almeida;Teresa B. Ludermir
Affiliations:
Center of Informatics, Federal University of Pernambuco, Recife, Brazil 50732-970;Center of Informatics, Federal University of Pernambuco, Recife, Brazil 50732-970
Venue:
HAIS '08 Proceedings of the 3rd international workshop on Hybrid Artificial Intelligence Systems
Year:
2008

Citing 7
Cited 1

Neural Networks: A Comprehensive Foundation

Neural Networks: A Comprehensive Foundation
A new algorithm to design compact two-hidden-layer artificial neural networks

Neural Networks
Introduction to Evolutionary Computing

Introduction to Evolutionary Computing
New training strategies for constructive neural networks with application to regression problems

Neural Networks
Biological engineering applications of feedforward neural networks designed and parameterized by genetic algorithms

Neural Networks
Cooperative coevolution of artificial neural network ensembles for pattern classification

IEEE Transactions on Evolutionary Computation
An empirical comparison of combinations of evolutionary algorithms and neural networks for classification problems

IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics

Improving the MLP learning by using a method to calculate the initial weights of the network based on the quality of similarity measure

MICAI'11 Proceedings of the 10th international conference on Artificial Intelligence: advances in Soft Computing - Volume Part II

Quantified Score

Hi-index	0.00

Visualization

Abstract

The widespread use of artificial neural networks and the difficult work regarding the correct specification (tuning) of parameters for a given problem are the main aspects that motivated the approach purposed in this paper. This approach employs an evolutionary search to perform the simultaneous tuning of initial weights, transfer functions, architectures and learning rules (learning algorithm parameters). Experiments were performed and the results demonstrate that the method is able to find efficient networks with satisfactory generalization in a shorter search time.