Complete Convergence of Competitive Neural Networks with Different Time Scales

Authors:
Mao Ye;Yi Zhang
Affiliations:
Aff1 Aff2;Department of Computer Science and Engineering, Nanjing University of Aeronautics and Astronautics, Nanjing, PR China 210016
Venue:
Neural Processing Letters
Year:
2005

Citing 9
Cited 2

Emulating the dynamics for a class of laterally inhibited neural networks

Neural Networks
Singular perturbation analysis of competitive neural networks with different time scales

Neural Computation
On the piecewise analysis of networks of linear threshold neurons

Neural Networks
Selectively grouping neurons in recurrent networks of lateral inhibition

Neural Computation
Permitted and forbidden sets in symmetric threshold-linear networks

Neural Computation
Multistability analysis for recurrent neural networks with unsaturating piecewise linear transfer functions

Neural Computation
Convergence Analysis of Recurrent Neural Networks (Network Theory and Applications, V. 13)

Convergence Analysis of Recurrent Neural Networks (Network Theory and Applications, V. 13)
Dynamical Stability Conditions for Recurrent Neural Networks with Unsaturating Piecewise Linear Transfer Functions

Neural Computation
Global exponential stability of competitive neural networks with different time scales

IEEE Transactions on Neural Networks

Passivity Analysis of Dynamic Neural Networks with Different Time-scales

Neural Processing Letters
Passivity analysis for neuro identifier with different time-scales

ICIC'06 Proceedings of the 2006 international conference on Intelligent Computing - Volume Part I

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper studies the complete convergence of a class of neural networks with different time scales under the assumption that the activation functions are unsaturated piecewise linear functions. Under this assumption, there are multiple equilibrium points in the neural network. Traditional methods cannot be used in this neural network. Complete convergence is proved by constructing an energy-like function. Simulations are employed to illustrate the theory.