Share Email Print

Proceedings Paper

Criteria for passivity of uncertain neural networks with time-varying delay
Author(s): Xuyang Lou; Huibin Zhu; Baotong Cui
Format Member Price Non-Member Price
PDF $14.40 $18.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

This paper deals with the delay-dependent passivity problem for neural networks with norm-bounded parameter uncertainties and time-varying delay. Some new delay-dependent criteria ensuring delayed neural networks to be passive are derived with the aid of the Leibniz-Newton formula. By exploiting free-weighting matrix (relaxation matrix) approach and an inequality technique, we essentially remove the requirement of Lipschitz condition on neuron activation functions and rigorous assumption on the derivative of the time-varying delay to be less than one.

Paper Details

Date Published: 14 March 2013
PDF: 9 pages
Proc. SPIE 8768, International Conference on Graphic and Image Processing (ICGIP 2012), 87680T (14 March 2013); doi: 10.1117/12.2010654
Show Author Affiliations
Xuyang Lou, Jiangnan Univ. (China)
Huibin Zhu, Jiangnan Univ. (China)
Baotong Cui, Jiangnan Univ. (China)

Published in SPIE Proceedings Vol. 8768:
International Conference on Graphic and Image Processing (ICGIP 2012)
Zeng Zhu, Editor(s)

© SPIE. Terms of Use
Back to Top