Title :
Dynamic analysis of winner-take-all neural networks with global inhibitory feedback
Author :
Yu, Yongbin ; Jin, Ju ; Zhang, Rongquan ; Ebong, Idongesit E. ; Mazumder, Pinaki
Author_Institution :
School of Information and Software Engineering, University of Electronic Science and Technology of China, Chengdu, Sichuan, 610054, P.R. China
Abstract :
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.
Keywords :
Biological neural networks; Mathematical model; Neurons; Recurrent neural networks; Simulation; Stability analysis; Winner-take-all; exponentially stable; inhibition; neural network;
Conference_Titel :
Control Conference (CCC), 2015 34th Chinese
Conference_Location :
Hangzhou, China
DOI :
10.1109/ChiCC.2015.7260178
