Title | ||
---|---|---|
Parallelizing the Design of Radial Basis Function Neural Networks by Means of Evolutionary Meta-algorithms |
Abstract | ||
---|---|---|
This work introduces SymbPar, a parallel meta-evolutionary algorithm designed to build Radial Basis Function Networks minimizing the number of parameters needed to be set by hand. Parallelization is implemented using independent agents to evaluate every individual. Experiments over classifications problems show that the new method drastically reduces the time took by sequential algorithms, while maintaining the generalization capabilities and sizes of the nets it builds. |
Year | DOI | Venue |
---|---|---|
2009 | 10.1007/978-3-642-02478-8_48 | IWANN (1) |
Keywords | Field | DocType |
evolutionary meta-algorithms,generalization capability,classifications problem,parallel meta-evolutionary algorithm,new method,sequential algorithm,independent agent,radial basis function networks,radial basis function neural,parallelization,neural networks,evolutionary algorithm,evolutionary algorithms,neural network,radial basis function network | Radial basis function network,Radial basis function,Evolutionary algorithm,Computer science,Radial basis function neural,Activation function,Algorithm,Theoretical computer science,Time delay neural network,Artificial neural network | Conference |
Volume | ISSN | Citations |
5517 | 0302-9743 | 2 |
PageRank | References | Authors |
0.41 | 14 | 6 |
Name | Order | Citations | PageRank |
---|---|---|---|
M. G. Arenas | 1 | 48 | 6.27 |
E. Parras-Gutiérrez | 2 | 2 | 0.41 |
V. Rivas | 3 | 532 | 23.12 |
P. A. Castillo | 4 | 134 | 13.95 |
M. Jose del Jesus | 5 | 26 | 3.13 |
J. J. Merelo | 6 | 363 | 33.51 |