Title :
Approximation Capability of a Novel Neural Network Model for Dynamic Systems
Author :
Zhang, Jianhai ; Kong, Wanzeng ; Zhang, Senlin ; Liu, Meiqin
Author_Institution :
Coll. of Comput., Hangzhou Dianzi Univ., Hangzhou, China
Abstract :
The approximation power for dynamic systems of a novel neural network model-standard neural network model (SNNM) is examined. Applying Stone-Weierstrass theorem, it is proved that SNNM is capable of approximating dynamic systems to any degree of accuracy. Furthermore, the results are briefly extended for any bounded measurable functions. The approximation capability together with the learn ability justify the use of SNNM in practical applications.
Keywords :
approximation theory; neural nets; Stone-Weierstrass theorem; approximation capability; approximation power; dynamic systems; measurable function; standard neural network model; Automation; Cellular neural networks; Computer networks; Educational institutions; Fuzzy control; Intelligent networks; Neural networks; Power system modeling; Recurrent neural networks; Stability analysis; approximation capability; dynamic systems; recurrent neural network; standard neural network model;
Conference_Titel :
Intelligent Computation Technology and Automation, 2009. ICICTA '09. Second International Conference on
Print_ISBN :
978-0-7695-3804-4
DOI :
10.1109/ICICTA.2009.23
