Title :
Iterative Learning Neurocomputing
Author_Institution :
Coll. of Inf. Eng., Zhejiang Univ. of Technol., Hangzhou, China
Abstract :
This paper presents a neural network framework for implementing unknown time-varying mappings. A unified architecture of time-varying neural networks is proposed, and the methodology of iterative learning is used for the network training. Convergence results of the iterative learning least squares algorithm are derived under assumption of bounded input signals. Periodic neural networks are explored as well to be used as periodic function approximation tools.
Keywords :
iterative methods; learning systems; least squares approximations; neural nets; iterative learning least squares algorithm; iterative learning neurocomputing; periodic function approximation tools; periodic neural networks; time-varying neural networks; unknown time-varying mappings; Artificial neural networks; Feedforward neural networks; Function approximation; Iterative algorithms; Iterative methods; Least squares approximation; Least squares methods; Neural networks; Neurons; Time varying systems; Neural networks; iterative learning; periodic systems; time-varying systems;
Conference_Titel :
Wireless Networks and Information Systems, 2009. WNIS '09. International Conference on
Conference_Location :
Shanghai
Print_ISBN :
978-0-7695-3901-0
Electronic_ISBN :
978-1-4244-5400-6
DOI :
10.1109/WNIS.2009.47
