Distributed Winner-Take-All in Dynamic Networks

被引：83

作者：

Li, Shuai ^{[1
]}

Zhou, MengChu ^{[2
,3
]}

Luo, Xin ^{[4
]}

You, Zhu-Hong ^{[5
]}

机构：

[1] Hong Kong Polytech Univ, Dept Comp, Kl, Hong Kong, Peoples R China

[2] Macau Univ Sci & Technol, Inst Syst Engn, Macau 999078, Peoples R China

[3] New Jersey Inst Technol, Helen & John C Hartmann Dept Elect & Comp Engn, Newark, NJ 07102 USA

[4] Chinese Acad Sci, Chongqing Inst Green & Intelligent Technol, Chongqing, Peoples R China

[5] Chinese Acad Sci, Xinjiang Tech Inst Phys & Chem, Urumqi 830011, Peoples R China

来源：

IEEE TRANSACTIONS ON AUTOMATIC CONTROL | 2017年 / 62卷 / 02期

基金：

中国国家自然科学基金;

关键词：

Competitive control; consensus; cooperative control; distributed control; dynamic networks; networked control system; winner-take-all; CONSENSUS PROBLEMS; NEURAL-NETWORKS; COMPETITION; SYSTEMS; SYNCHRONIZATION; CONVERGENCE; COMPUTATION; DECISION;

D O I：

10.1109/TAC.2016.2578645

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

This paper is concerned with the winner-take-all (WTA) problem on networks. We propose the first distributed protocol to address this problem dynamically. This protocol features strong nonlinearity. Theoretical analysis reveals that it contains invariant quantities, symmetric solutions, and multiple equilibrium points. By leveraging these properties, this work proves the instability of its non-WTA solutions, and global convergence to the WTA solution via Lyapunov theory. Two simulations over networks with 10 and 200 nodes, respectively, are conducted. Simulation results have well verified the theoretical conclusions drawn in this paper.

引用

下载

页码：577 / 589

页数：13

共 50 条

[1] DYNAMIC WINNER-TAKE-ALL CONFLICT
Reuveny, Rafael
Maxwell, John W.
Davis, Jefferson
DEFENCE AND PEACE ECONOMICS, 2011, 22 (05) : 471 - 492
[2] A fast winner-take-all neural networks with the dynamic ratio
Chen, CM
Hsu, MH
Wang, TY
JOURNAL OF INFORMATION SCIENCE AND ENGINEERING, 2002, 18 (02) : 211 - 222
[3] Winner-Take-All Networks with Lateral Excitation
Giacomo Indiveri
Analog Integrated Circuits and Signal Processing, 1997, 13 : 185 - 193
[4] Winner-take-all networks with lateral excitation
Indiveri, G
ANALOG INTEGRATED CIRCUITS AND SIGNAL PROCESSING, 1997, 13 (1-2) : 185 - 193
[5] WINNER-TAKE-ALL CELLULAR NEURAL NETWORKS
SEILER, G
NOSSEK, JA
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS II-ANALOG AND DIGITAL SIGNAL PROCESSING, 1993, 40 (03): : 184 - 190
[6] Winner-Take-All Autoencoders
Makhzani, Alireza
Frey, Brendan
ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 28 (NIPS 2015), 2015, 28
[7] CONNECTIONISM AND EPISTEMOLOGY, GOLDMAN ON WINNER-TAKE-ALL NETWORKS
THAGARD, P
PHILOSOPHIA, 1989, 19 (2-3) : 189 - 196
[8] Dynamic Analysis of a General Class of Winner-Take-All Competitive Neural Networks
Fang, Yuguang
Cohen, Michael A.
Kincaid, Thomas G.
IEEE TRANSACTIONS ON NEURAL NETWORKS, 2010, 21 (05): : 771 - 783
[9] Collective Stability of Networks of Winner-Take-All Circuits
Rutishauser, Ueli
Douglas, Rodney J.
Slotine, Jean-Jacques
NEURAL COMPUTATION, 2011, 23 (03) : 735 - 773
[10] Dynamic Analysis of Winner-Take-All Neural Networks with Global Inhibitory Feedback
Yu, Yongbin
Jin, Ju
Zhang, Rongquan
Ebong, Idongesit E.
Mazumder, Pinaki
2015 34TH CHINESE CONTROL CONFERENCE (CCC), 2015, : 3497 - 3500

← 1 2 3 4 5 →