Professor
Supervisor of Doctorate Candidates
Supervisor of Master's Candidates
Paper Publications
Convergence of Batch Split-Complex Backpropagation Algorithm for Complex-Valued Neural Networks
Hits:
Indexed by:Journal Article
Date of Publication:2009-01-01
Journal:DISCRETE DYNAMICS IN NATURE AND SOCIETY
Included Journals:Scopus、SCIE
Volume:2009
ISSN:1026-0226
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. Copyright (C) 2009 Huisheng Zhang et al.