Convergence of an Online Split-Complex Gradient Algorithm for Complex-Valued Neural Networks
Joint Authors
Wang, Zhiping
Zhang, Huisheng
Xu, Dongpo
Source
Discrete Dynamics in Nature and Society
Issue
Vol. 2010, Issue 2010 (31 Dec. 2010), pp.1-27, 27 p.
Publisher
Hindawi Publishing Corporation
Publication Date
2010-03-21
Country of Publication
Egypt
No. of Pages
27
Main Subjects
Abstract EN
The online gradient method has been widely used in training neural networks.
We consider in this paper an online split-complex gradient algorithm for complex-valued neural networks.
We choose an adaptive learning rate during the training procedure.
Under certain conditions, by firstly showing the monotonicity of the error function, it is proved that the gradient of the error function tends to zero and the weight sequence tends to a fixed point.
A numerical example is given to support the theoretical findings.
American Psychological Association (APA)
Zhang, Huisheng& Xu, Dongpo& Wang, Zhiping. 2010. Convergence of an Online Split-Complex Gradient Algorithm for Complex-Valued Neural Networks. Discrete Dynamics in Nature and Society،Vol. 2010, no. 2010, pp.1-27.
https://search.emarefa.net/detail/BIM-501508
Modern Language Association (MLA)
Zhang, Huisheng…[et al.]. Convergence of an Online Split-Complex Gradient Algorithm for Complex-Valued Neural Networks. Discrete Dynamics in Nature and Society No. 2010 (2010), pp.1-27.
https://search.emarefa.net/detail/BIM-501508
American Medical Association (AMA)
Zhang, Huisheng& Xu, Dongpo& Wang, Zhiping. Convergence of an Online Split-Complex Gradient Algorithm for Complex-Valued Neural Networks. Discrete Dynamics in Nature and Society. 2010. Vol. 2010, no. 2010, pp.1-27.
https://search.emarefa.net/detail/BIM-501508
Data Type
Journal Articles
Language
English
Notes
Includes bibliographical references
Record ID
BIM-501508