Skip to main content
placeholder image

Dissipativity analysis of discrete-time delayed neural networks

Conference Paper


Abstract


  • The objective of this paper to analyze dissipativity of discrete-time neural networks with time-varying delay. The main idea is to introduce the concept of extended dissipativity for discrete-time neural networks with a view to unifying several performance measures such as the H∞ performance, passivity, l2-l∞ performance and dissipativity. The reciprocally convex approach together with a Lyapunov function involving a triple-summable term is applied to develop the extended dissipativity criterion for discrete-time neural networks with time-varying delay. In addition, the new criterion also ensures the stability of the neural networks. The improved results are validated through a numerical example in comparison with the existing results.

Publication Date


  • 2015

Citation


  • Feng, Z., & Zheng, W. X. (2015). Dissipativity analysis of discrete-time delayed neural networks. In 2015 Australian Control Conference, AUCC 2015 (pp. 134-137).

Scopus Eid


  • 2-s2.0-84964057242

Web Of Science Accession Number


Start Page


  • 134

End Page


  • 137

Abstract


  • The objective of this paper to analyze dissipativity of discrete-time neural networks with time-varying delay. The main idea is to introduce the concept of extended dissipativity for discrete-time neural networks with a view to unifying several performance measures such as the H∞ performance, passivity, l2-l∞ performance and dissipativity. The reciprocally convex approach together with a Lyapunov function involving a triple-summable term is applied to develop the extended dissipativity criterion for discrete-time neural networks with time-varying delay. In addition, the new criterion also ensures the stability of the neural networks. The improved results are validated through a numerical example in comparison with the existing results.

Publication Date


  • 2015

Citation


  • Feng, Z., & Zheng, W. X. (2015). Dissipativity analysis of discrete-time delayed neural networks. In 2015 Australian Control Conference, AUCC 2015 (pp. 134-137).

Scopus Eid


  • 2-s2.0-84964057242

Web Of Science Accession Number


Start Page


  • 134

End Page


  • 137