Some Generalized Sufficient Convergence Criteria for Nonlinear Continuous Neural Networks

Authors:
Jito Vanualailai;Shin-Ichi Nakagiri
Affiliations:
Department of Mathematics and Computing Science, University of the South Pacific, Suva, Fiji;Department of Applied Mathematics, Faculty of Engineering, Kobe University, Kobe, Japan
Venue:
Neural Computation
Year:
2005

Citing 11
Cited 1

Convergent activation dynamics in continuous time networks

Neural Networks
Stability conditions for nonlinear continuous neural networks with asymmetric connection weights

Neural Networks
The Handbook of Brain Theory and Neural Networks

The Handbook of Brain Theory and Neural Networks
Global convergence rate of recurrently connected neural networks

Neural Computation
Stability analysis of dynamical neural networks

IEEE Transactions on Neural Networks
Stability analysis of Hopfield-type neural networks

IEEE Transactions on Neural Networks
Asymptotic behavior of irreducible excitatory networks of analog graded-response neurons

IEEE Transactions on Neural Networks
Estimate of exponential convergence rate and exponential stability for neural networks

IEEE Transactions on Neural Networks
On equilibria, stability, and instability of Hopfield neural networks

IEEE Transactions on Neural Networks
Global exponential stability of neural networks with globally Lipschitz continuous activations and its application to linear variational inequality problem

IEEE Transactions on Neural Networks
Nonlinear measures: a new approach to exponential stability analysis for Hopfield-type neural networks

IEEE Transactions on Neural Networks

Long-range out-of-sample properties of autoregressive neural networks

Neural Computation

Quantified Score

Hi-index	0.00

Visualization

Abstract

A reason for applying the direct method of Lyapunov to artificial neural networks (ANNs) is to design dynamical neural networks so that they exhibit global asymptotic stability. Lyapunov functions that frequently appear in the ANN literature include the quadratic function, the Persidskii function, and the Luré-Postnikov function. This contribution revisits the quadratic function and shows that via Krasovskii-like stability criteria, it is possible to have a very simple and systematic procedure to obtain not only new and generalized results but also well-known sufficient conditions for convergence established recently by non-Lyapunov methods, such as the matrix measure and nonlinear measure.