An alternative approach to solve convergence problems in the backpropagation algorithm
Contribuinte(s) |
Universidade Estadual Paulista (UNESP) |
---|---|
Data(s) |
20/05/2014
20/05/2014
01/01/2004
|
Resumo |
The multilayer perceptron network has become one of the most used in the solution of a wide variety of problems. The training process is based on the supervised method where the inputs are presented to the neural network and the output is compared with a desired value. However, the algorithm presents convergence problems when the desired output of the network has small slope in the discrete time samples or the output is a quasi-constant value. The proposal of this paper is presenting an alternative approach to solve this convergence problem with a pre-conditioning method of the desired output data set before the training process and a post-conditioning when the generalization results are obtained. Simulations results are presented in order to validate the proposed approach. |
Formato |
1021-1026 |
Identificador |
http://dx.doi.org/10.1109/IJCNN.2004.1380074 2004 IEEE International Joint Conference on Neural Networks, Vols 1-4, Proceedings. New York: IEEE, p. 1021-1026, 2004. 1098-7576 http://hdl.handle.net/11449/36159 10.1109/IJCNN.2004.1380074 WOS:000224941900177 |
Idioma(s) |
eng |
Publicador |
IEEE |
Relação |
2004 IEEE International Joint Conference on Neural Networks, Vols 1-4, Proceedings |
Direitos |
closedAccess |
Tipo |
info:eu-repo/semantics/conferencePaper |