Journal
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
Volume 26, Issue 12, Pages 3293-3300Publisher
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TNNLS.2015.2399421
Keywords
Extended dissipativity; neural networks; reciprocally convex combination; time-varying delay
Categories
Funding
- National Natural Science Foundation of China [61304063]
- Liaoning Provincial Natural Science Foundation of China [2013020227]
- Program for Liaoning Innovative Research Team in University [LT2013023]
- Australian Research Council [DP120104986]
Ask authors/readers for more resources
In this brief, the problem of extended dissipativity analysis for discrete-time neural networks with time-varying delay is investigated. The definition of extended dissipativity of discrete-time neural networks is proposed, which unifies several performance measures, such as the H-infinity performance, passivity, l(2)-l(infinity) performance, and dissipativity. By introducing a triple-summable term in Lyapunov function, the reciprocally convex approach is utilized to bound the forward difference of the triple-summable term and then the extended dissipativity criterion for discrete-time neural networks with time-varying delay is established. The derived condition guarantees not only the extended dissipativity but also the stability of the neural networks. Two numerical examples are given to demonstrate the reduced conservatism and effectiveness of the obtained results.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available