Convergence of Batch Split-Complex Backpropagation Algorithm for Complex-Valued Neural Networks

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...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Discrete Dynamics in Nature and Society Ročník 2009; číslo 1; s. 539 - 554
Hlavní autoři: Zhang, Huisheng, Zhang, Chao, Wu, Wei
Médium: Journal Article
Jazyk:angličtina
Vydáno: New York Hindawi Limiteds 01.01.2009
Hindawi Publishing Corporation
John Wiley & Sons, Inc
Wiley
Témata:
Algorithms
Back propagation
Convergence
Distance learning
Mathematical functions
Neural networks
Online instruction
Signal processing
Studies
ISSN:1026-0226, 1607-887X
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí: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.
Bibliografie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ObjectType-Article-2
ObjectType-Feature-1
content type line 23
ISSN:1026-0226
1607-887X
DOI:10.1155/2009/329173