Discrete Dynamics in Nature and Society
Volume 2009 (2009), Article ID 329173, 16 pages
doi:10.1155/2009/329173

Convergence of batch split-complex backpropagation algorithm for complex-valued neural networks

Abstract

The batch split-complex backpropagation (BSCBP) algorithm for training complex-valued neural networks is considered. For constant learning rate, it is proved that the error function of BSCBP algorithm is monotone during the training iteration process, and the gradient of the error function tends to zero. By adding a moderate condition, the weights sequence itself is also proved to be convergent. A numerical example is given to support the theoretical analysis.