Studying the capacity of grammatical encoding to generate FNN architectures

Authors:
Germán Gutiérrez;Beatriz García;José M. Molina;Araceli Sanchis
Affiliations:
SCALAB, Departamento de Informática, Universided Carlos III de Madrid, Madrid, Spain;SCALAB, Departamento de Informática, Universided Carlos III de Madrid, Madrid, Spain;SCALAB, Departamento de Informática, Universided Carlos III de Madrid, Madrid, Spain;SCALAB, Departamento de Informática, Universided Carlos III de Madrid, Madrid, Spain
Venue:
IWANN'03 Proceedings of the Artificial and natural neural networks 7th international conference on Computational methods in neural modeling - Volume 1
Year:
2003

Citing 7
Cited 0

Combining evolution with credit apportionment: a new learning algorithm for neural nets

Neural Networks
Neural Networks: A Comprehensive Foundation

Neural Networks: A Comprehensive Foundation
Multi-objective cooperative coevolution of artificial neural networks (multi-objective cooperative networks)

Neural Networks
RBF Neural Networks, Multiobjective Optimization and Time Series Forecasting

IWANN '01 Proceedings of the 6th International Work-Conference on Artificial and Natural Neural Networks: Connectionist Models of Neurons, Learning Processes and Artificial Intelligence-Part I
A systematic approach to a self-generating fuzzy rule-table forfunction approximation

IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics
Cooperative-competitive genetic evolution of radial basis function centers and widths for time series prediction

IEEE Transactions on Neural Networks
Comparison of adaptive methods for function estimation from samples

IEEE Transactions on Neural Networks

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper presents a new evolutionary procedure to design optimal networks of Radial Basis Functions (RBFs). It defines a self-organizing process into a population of RBFs based on the estimation of the fitness for each neuron in the population, and on the use of operators that, according to a set of fuzzy rules, transform the RBFs. This way, it has been possible to define cooperation, speciation, and niching features in the evolution of the population.