A new optimizer using particle swarm theory

Author

Eberhart, Russell ; Kennedy, James

Author_Institution

Purdue Sch. of Eng. & Technol., Indianapolis, IN, USA

fYear

1995

fDate

4-6 Oct 1995

Firstpage

39

Lastpage

43

Abstract

The optimization of nonlinear functions using particle swarm methodology is described. Implementations of two paradigms are discussed and compared, including a recently developed locally oriented paradigm. Benchmark testing of both paradigms is described, and applications, including neural network training and robot task learning, are proposed. Relationships between particle swarm optimization and both artificial life and evolutionary computation are reviewed

Keywords

algorithm theory; feedforward neural nets; genetic algorithms; intelligent control; learning (artificial intelligence); multilayer perceptrons; optimisation; artificial life; benchmark testing; bird flocks; evolutionary computation; gbest; genetic algorithms; globally oriented concept; hyperspace; lbest; locally oriented paradigm; multilayer perceptron; neural network training; nonlinear functions; optimization; particle swarm theory; pbest; robot task learning; Acceleration; Artificial neural networks; Evolutionary computation; Genetic algorithms; Optimization methods; Particle swarm optimization; Particle tracking; Performance evaluation; Statistics; Testing;

fLanguage

English

Publisher

ieee

Conference_Titel

Micro Machine and Human Science, 1995. MHS '95., Proceedings of the Sixth International Symposium on

Conference_Location

Nagoya

Print_ISBN

0-7803-2676-8

Type

conf

DOI

10.1109/MHS.1995.494215

Filename

494215