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

Huisheng Zhang | Zendy; Chao Zhang | Zendy; Wei Wu | Zendy

AI Assistant Blog Pricing

Home ZAIA Blog

Open Access

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

Author(s) -

Huisheng Zhang,

Chao Zhang,

Wei Wu

Publication year - 2009

Publication title -

discrete dynamics in nature and society

Language(s) - English

Resource type - Journals

SCImago Journal Rank - 0.264

H-Index - 39

eISSN - 1607-887X

pISSN - 1026-0226

DOI - 10.1155/2009/329173

Subject(s) - backpropagation , artificial neural network , sequence (biology) , algorithm , convergence (economics) , monotone polygon , constant (computer programming) , error function , computer science , function (biology) , process (computing) , zero (linguistics) , continuous function (set theory) , rate of convergence , rprop , mathematics , artificial intelligence , recurrent neural network , types of artificial neural networks , key (lock) , philosophy , computer security , economic growth , linguistics , biology , genetics , operating system , geometry , evolutionary biology , programming language , economics

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

The content you want is available to Zendy users.

Already have an account? Click here to sign in.

Having issues? You can contact us here

Accelerating Research