TY - GEN
T1 - Approximation capability of a novel neural network model for dynamic systems
AU - Zhang, Jianhai
AU - Kong, Wanzeng
AU - Zhang, Senlin
AU - Liu, Meiqin
PY - 2009
Y1 - 2009
N2 - 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.
AB - 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.
KW - Approximation capability
KW - Dynamic systems
KW - Recurrent neural network
KW - Standard neural network model
UR - https://www.scopus.com/pages/publications/71949106769
U2 - 10.1109/ICICTA.2009.23
DO - 10.1109/ICICTA.2009.23
M3 - 会议稿件
AN - SCOPUS:71949106769
SN - 9780769538044
T3 - 2009 2nd International Conference on Intelligent Computing Technology and Automation, ICICTA 2009
SP - 59
EP - 62
BT - 2009 2nd International Conference on Intelligent Computing Technology and Automation, ICICTA 2009
T2 - 2009 2nd International Conference on Intelligent Computing Technology and Automation, ICICTA 2009
Y2 - 10 October 2009 through 11 October 2009
ER -