Comparison of PSO and DE for Training Neural Networks

Author

Espinal, A. ; Sotelo-Figueroa, M. ; Soria-Alcaraz, Jorge A. ; Ornelas, M. ; Puga, H. ; Carpio, M. ; Baltazar, Rosario ; Rico, J.L.

Author_Institution

Div. de Estudios de Posgrado e Investig., Inst. Tecnol. de Leon, Leon, Mexico

fYear

2011

fDate

Nov. 26 2011-Dec. 4 2011

Firstpage

83

Lastpage

87

Abstract

The use of computational resources required for Feed-Forward Artificial Neural Network (FFANN) training phase by means of classical techniques such as the back propagation learning rule can be prohibitive in some applications. A good training phase is needed for a high performance of a neural network. In searching for alternative methods for training phase of FFANN, some metaheuristic techniques have been used to do this task. This paper compares the performance of Particle Swarm Optimization (PSO) and Differential Evolution (DE) as training methods for FFANN under several well-known pattern recognition instances.

Keywords

backpropagation; evolutionary computation; feedforward neural nets; particle swarm optimisation; pattern recognition; DE; PSO; back propagation learning rule; classical techniques; computational resources; differential evolution; feed-forward artificial neural network training phase; metaheuristic techniques; particle swarm optimization; pattern recognition instances; Biological neural networks; Genomics; Neurons; Optimization; Particle swarm optimization; Training; Vectors; Differential Evolution; Neural Networks; Particle Swarm Optimization;

fLanguage

English

Publisher

ieee

Conference_Titel

Artificial Intelligence (MICAI), 2011 10th Mexican International Conference on

Conference_Location

Puebla

Print_ISBN

978-1-4577-2173-1

Type

conf

DOI

10.1109/MICAI.2011.16

Filename

6119009