Please use this identifier to cite or link to this item:
|Type:||Artigo de evento|
|Title:||Particles Gradient: A New Approach To Perform Mlp Neural Network Training Based On Particle Swarm Optimization|
|Abstract:||The use of heuristic algorithms in neural networks training is not a new subject. Several works have already accomplished good results, however not competitive with procedural methods for problems where the gradient of the error is well defined. The present document proposes an alternative for neural networks training using PSO(Particle Swarm Optimization) to evolve the training process itself and not to evolve directly the network parameters as usually. This way we get quite superior results and obtain a method clearly faster than others known methods for training neural networks using heuristic algorithms.|
|Appears in Collections:||Unicamp - Artigos e Outros Documentos|
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.