Title :
Monotonicity of asynchronous gradient method for RPNN
Author :
Xin Yu ; Lixia Tang ; Yan Yu
Author_Institution :
Sch. of Comput., Electron. & Inf., Guangxi Univ., Nanning, China
Abstract :
The Ridge Polynomial neural network is one of the most popular higher-order neural networks, which has the powerful capability of approximating reasonable functions. In order to select appropriate learning parameters to perform an efficient training, the monotonicity of asynchronous gradient method is proved for training Ridge Polynomial neural networks.
Keywords :
function approximation; gradient methods; learning (artificial intelligence); neural nets; RPNN; asynchronous gradient method monotonicity; higher-order neural networks; learning parameters; reasonable function approximation; ridge polynomial neural network training; Ridge Polynomial neural network; asynchronous gradient algorithm; monotonicity;
Conference_Titel :
Information Science and Control Engineering 2012 (ICISCE 2012), IET International Conference on
Conference_Location :
Shenzhen
Electronic_ISBN :
978-1-84919-641-3
DOI :
10.1049/cp.2012.2344
