![](/images/graphics-bg.png)
Convergence of Batch Split-Complex Backpropagation Algorithm for Complex-Valued Neural Networks
Joint Authors
Zhang, Huisheng
Zhang, Chao
Wu, Wei
Source
Discrete Dynamics in Nature and Society
Issue
Vol. 2009, Issue 2009 (31 Dec. 2009), pp.1-16, 16 p.
Publisher
Hindawi Publishing Corporation
Publication Date
2009-04-22
Country of Publication
Egypt
No. of Pages
16
Main Subjects
Abstract EN
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.
American Psychological Association (APA)
Zhang, Huisheng& Zhang, Chao& Wu, Wei. 2009. Convergence of Batch Split-Complex Backpropagation Algorithm for Complex-Valued Neural Networks. Discrete Dynamics in Nature and Society،Vol. 2009, no. 2009, pp.1-16.
https://search.emarefa.net/detail/BIM-463989
Modern Language Association (MLA)
Zhang, Huisheng…[et al.]. Convergence of Batch Split-Complex Backpropagation Algorithm for Complex-Valued Neural Networks. Discrete Dynamics in Nature and Society No. 2009 (2009), pp.1-16.
https://search.emarefa.net/detail/BIM-463989
American Medical Association (AMA)
Zhang, Huisheng& Zhang, Chao& Wu, Wei. Convergence of Batch Split-Complex Backpropagation Algorithm for Complex-Valued Neural Networks. Discrete Dynamics in Nature and Society. 2009. Vol. 2009, no. 2009, pp.1-16.
https://search.emarefa.net/detail/BIM-463989
Data Type
Journal Articles
Language
English
Notes
Includes bibliographical references
Record ID
BIM-463989