Asynchronous Steady State Particle Swarm

被引：3

作者：

Fernandes, Carlos M. ^{[1
]}

Julian Merelo, Juan ^{[2
]}

Rosa, Agostinho C. ^{[1
]}

机构：

[1] Univ Lisbon, LARSyS Lab Robot & Syst Engn & Sci, Lisbon, Portugal

[2] Univ Granada, Dept Comp Architecture, Granada, Spain

来源：

PROCEEDINGS OF THE 2016 GENETIC AND EVOLUTIONARY COMPUTATION CONFERENCE (GECCO'16 COMPANION) | 2016年

关键词：

Particle Swarm Optimization; Asynchronous PSO; Self-Organized Criticality;

D O I：

10.1145/2908961.2909035

中图分类号：

TP301 [理论、方法];

学科分类号：

081202 ;

摘要：

We propose an asynchronous and steady state update strategy for the Particle Swarm Optimization inspired by the Bak-Sneppen model of co-evolution between interacting species: only the worst particle and its neighbors are updated and evaluated in each time-step. The strategy improves the quality of results and convergence speed of PSO with Moore neighborhood.

引用

页码：1 / 2

页数：2

共 6 条

[1] PUNCTUATED EQUILIBRIUM AND CRITICALITY IN A SIMPLE-MODEL OF EVOLUTION
BAK, P
SNEPPEN, K
[J]. PHYSICAL REVIEW LETTERS, 1993, 71 (24) : 4083 - 4086
[2] CARLISLE A, 2001, WORKSH PART SWARM OP
[3] Fernandes CM, 2012, LNCS, V7492, P153
[4] Kennedy J, 1995, 1995 IEEE INTERNATIONAL CONFERENCE ON NEURAL NETWORKS PROCEEDINGS, VOLS 1-6, P1942, DOI 10.1109/icnn.1995.488968
[5] Lovbjerg M, 2002, IEEE C EVOL COMPUTAT, P1588, DOI 10.1109/CEC.2002.1004479
[6] A performance study on synchronicity and neighborhood size in particle swarm optimization
Rada-Vilela, Juan
Zhang, Mengjie
Seah, Winston
[J]. SOFT COMPUTING, 2013, 17 (06) : 1019 - 1030

← 1 →