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

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.

[1]  Zhi-Hong Mao,et al.  Dynamics of Winner-Take-All Competition in Recurrent Neural Networks With Lateral Inhibition , 2007, IEEE Transactions on Neural Networks.

[2]  Bard Ermentrout,et al.  Complex dynamics in winner-take-all neural nets with slow inhibition , 1992, Neural Networks.

[3]  Giacomo Indiveri,et al.  Recurrent networks of coupled Winner-Take-All oscillators for solving constraint satisfaction problems , 2013, NIPS.

[4]  Chi-Sing Leung,et al.  Analysis on the Convergence Time of Dual Neural Network-Based $k{\rm WTA}$ , 2012, IEEE Transactions on Neural Networks and Learning Systems.

[5]  D. Gale.  The Game of Hex and the Brouwer Fixed-Point Theorem , 1979 .

[6]  Pei Yu,et al.  Stability of dynamical systems , 2007 .

[7]  Ralf Wessel,et al.  Winner-take-all selection in a neural system with delayed feedback , 2007, Biological Cybernetics.

[8]  Xilin Fu,et al.  Nonlinear dynamics and Complexity , 2014 .

[9]  S. Ge,et al.  Stability Theory of Switched Dynamical Systems , 2011 .

[10]  Yuguang Fang,et al.  Dynamic Analysis of a General Class of Winner-Take-All Competitive Neural Networks , 2010, IEEE Transactions on Neural Networks.

[11]  Pinaki Mazumder,et al.  CMOS and Memristor-Based Neural Network Design for Position Detection , 2012, Proceedings of the IEEE.

[12]  Shyang Chang,et al.  A new winners-take-all architecture in artificial neural networks , 1994, IEEE Trans. Neural Networks.

[13]  Shuai Li,et al.  Selective Positive–Negative Feedback Produces the Winner-Take-All Competition in Recurrent Neural Networks , 2013, IEEE Transactions on Neural Networks and Learning Systems.

[14]  Iasson Karafyllis,et al.  Stability and Stabilization of Nonlinear Systems , 2011 .