A novel recurrent neural network with one neuron and finite-time convergence for k-winners-take-all operation

Qingshan Liu; Chuangyin Dang; Jinde Cao

doi:10.1109/TNN.2010.2050781

A novel recurrent neural network with one neuron and finite-time convergence for k-winners-take-all operation

IEEE Trans Neural Netw. 2010 Jul;21(7):1140-8. doi: 10.1109/TNN.2010.2050781.

Authors

Qingshan Liu¹, Chuangyin Dang, Jinde Cao

Affiliation

¹ School of Automation, Southeast University, Nanjing 210096, China. qsliu@seu.edu.cn

PMID: 20659863
DOI: 10.1109/TNN.2010.2050781

Abstract

In this paper, based on a one-neuron recurrent neural network, a novel k-winners-take-all ( k -WTA) network is proposed. Finite time convergence of the proposed neural network is proved using the Lyapunov method. The k-WTA operation is first converted equivalently into a linear programming problem. Then, a one-neuron recurrent neural network is proposed to get the kth or (k+1)th largest inputs of the k-WTA problem. Furthermore, a k-WTA network is designed based on the proposed neural network to perform the k-WTA operation. Compared with the existing k-WTA networks, the proposed network has simple structure and finite time convergence. In addition, simulation results on numerical examples show the effectiveness and performance of the proposed k-WTA network.

Publication types

Research Support, Non-U.S. Gov't

MeSH terms

Algorithms*
Animals
Feedback
Game Theory*
Models, Neurological*
Neural Networks, Computer*
Neurons / physiology*
Time Factors