convergence of an online split-complex gradient algorithm for complex-valued neural networks在线split-complex梯度算法的收敛为复数神经网络.pdfVIP

Hindawi Publishing Corporation Discrete Dynamics in Nature and Society Volume 2010, Article ID 829692, 27 pages doi:10.1155/2010/829692 Research Article Convergence of an Online Split-Complex Gradient Algorithm for Complex-Valued Neural Networks Huisheng Zhang,1 Dongpo Xu,2 and Zhiping Wang1 1 Department of Mathematics, Dalian Maritime University, Dalian 116026, China 2 Department of Applied Mathematics, Harbin Engineering University, Harbin 150001, China Correspondence should be addressed to Huisheng Zhang, zhhuisheng@163.com Received 1 September 2009; Accepted 19 January 2010 Academic Editor: Manuel De La Sen Copyright q 2010 Huisheng Zhang et al. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited. 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. 1. Introduction In recent years, neural networks have been widely used because of their outstanding capa- bility of approximating nonlinear models. As an important search method in optimization theory, gradient algorithm has been applied in various engineering fields, such as adaptive control and recursive parametrical estimation 1–3. Gradient algorithm is also a popular training method for neural