Dynamic analysis of winner-take-all neural networks with global inhibitory feedback

摘要

This work studies dynamical behavior of a general class of winner-take-all (WTA) neural networks with global inhibitory feedback. Sufficient conditions for the neural network to have equilibrium solution and WTA point are obtained. Furthermore, new conditions for exponential stabilization of the WTA neural network are presented. Finally, simulation results verify the feasibility and effectiveness of our method. The results can be extended to design other competitive neural networks.