Title | ||
---|---|---|
Fast Evolutionary Learning of Minimal Radial Basis Function Neural Networks Using a Genetic Algorithm |
Abstract | ||
---|---|---|
A hybrid algorithm for determining Radial Basis Function (RBF) networks is proposed. Evolutionary learning is applied to the non-linear problem of determining RBF network architecture (number of hidden layer nodes, basis function centres and widths) in conjunction with supervised gradient-based learning for tuning connection weights. A direct encoding of RBF hidden layer node basis function centres and widths is employed. The genetic operators utilised are adapted from those used in recent work on evolution of fuzzy inference systems. A parsimonious allocation of training sets and training epochs to evaluation of candidate networks during evolution is proposed in order to accelerate the learning process. |
Year | DOI | Venue |
---|---|---|
1996 | 10.1007/BFb0032769 | Evolutionary Computing, AISB Workshop |
Keywords | Field | DocType |
neural networks,genetic algorithm,fast evolutionary learning,minimal radial basis function,hybrid algorithm,radial basis function,genetic operator | Radial basis function network,Radial basis function,Radial basis function kernel,Computer science,Wake-sleep algorithm,Artificial intelligence,Genetic representation,Basis function,Population-based incremental learning,Machine learning,Genetic algorithm | Conference |
ISBN | Citations | PageRank |
3-540-61749-3 | 18 | 1.15 |
References | Authors | |
17 | 2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Brian Carse | 1 | 259 | 26.31 |
T C Fogarty | 2 | 1147 | 152.53 |