Neural network construction and training using grammatical evolution

Authors:
Ioannis Tsoulos;Dimitris Gavrilis;Euripidis Glavas
Affiliations:
Department of Computer Science, University of Ioannina, Ioannina, Greece;Department of Electrical & Computer Engineering, University of Patras, Greece;Department of Communications, Informatics and Management, Technological Educational Institute of Epirus, Greece
Venue:
Neurocomputing
Year:
2008

Citing 13
Cited 4

A tolerant algorithm for linearly constrained optimization calculations

Mathematical Programming: Series A and B
Genetic algorithms + data structures = evolution programs (2nd, extended ed.)

Genetic algorithms + data structures = evolution programs (2nd, extended ed.)
Neural Networks for Pattern Recognition

Neural Networks for Pattern Recognition
Evolving the Topology and the Weights of Neural Networks Using a Dual Representation

Applied Intelligence
Time Series Forecasting Using Massively Parallel Genetic Programming

IPDPS '03 Proceedings of the 17th International Symposium on Parallel and Distributed Processing
Grammatical Evolution: Evolutionary Automatic Programming in an Arbitrary Language

Grammatical Evolution: Evolutionary Automatic Programming in an Arbitrary Language
Evolving RBF neural networks for time-series forecasting with EvRBF

Information Sciences—Informatics and Computer Science: An International Journal - Special issue: Informatics and computer science intelligent systems applications
Grammatical evolution

IEEE Transactions on Evolutionary Computation
Evolutionary Design of Neural Network Architectures Using a Descriptive Encoding Language

IEEE Transactions on Evolutionary Computation
Evolutionary neural networks for anomaly detection based on the behavior of a program

IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics
An evolutionary artificial neural networks approach for breast cancer diagnosis

Artificial Intelligence in Medicine
Artificial neural networks for solving ordinary and partial differential equations

IEEE Transactions on Neural Networks
Pruning algorithms-a survey

IEEE Transactions on Neural Networks

Solving differential equations with constructed neural networks

Neurocomputing
Location of amide I mode of vibration in computed data utilizing constructed neural networks

Expert Systems with Applications: An International Journal
Multilayer perceptrons and radial basis function neural network methods for the solution of differential equations: A survey

Computers & Mathematics with Applications
Vector-valued function estimation by grammatical evolution for autonomous robot control

Information Sciences: an International Journal

Quantified Score

Hi-index	0.02

Visualization

Abstract

The term neural network evolution usually refers to network topology evolution leaving the network's parameters to be trained using conventional algorithms. In this paper we present a new method for neural network evolution that evolves the network topology along with the network parameters. The proposed method uses grammatical evolution to encode both the network and the parameters space. This allows for a better description of the network using a formal grammar allowing the network architect to shape the resulting search space in order to meet each problem requirement. The proposed method is compared with other three methods for neural network training and is evaluated using 9 known classification problems and 9 known regression problems. In all 18 datasets, the proposed method outperforms its competitors.