Training the multifeedback-layer neural network using the Particle Swarm Optimization algorithm

Author

Aksu, Inayet Ozge ; Coban, Ramazan

Author_Institution

Dept. of Comput. Eng., Adana Sci. & Technol. Univ., Adana, Turkey

fYear

2013

fDate

7-9 Nov. 2013

Firstpage

172

Lastpage

175

Abstract

In this study, the Multifeedback-Layer Neural Network (MFLNN) weights are trained by the Particle Swarm Optimization (PSO). This method (MFLNN-PSO) is applied to two different problems to prove accomplishment of the study. Firstly, a chaotic time series prediction problem is used to test the MFLNN-PSO. Also, the method is used for identification of a non-linear dynamic system. This study shows that the MFLNN-PSO can be used for dynamic system identification as well as controller design.

Keywords

multilayer perceptrons; particle swarm optimisation; MFLNN training; MFLNN-PSO method; chaotic time series prediction problem; controller design; multifeedback-layer neural network; nonlinear dynamic system identification; particle swarm optimization algorithm; Algorithm design and analysis; Biological neural networks; Heuristic algorithms; Neurons; Particle swarm optimization; Recurrent neural networks; Training; Multifeedback-Layer Neural Network; Particle Swarm Optimization; dynamic system identification; recurrent neural networks; training procedure;

fLanguage

English

Publisher

ieee

Conference_Titel

Electronics, Computer and Computation (ICECCO), 2013 International Conference on

Conference_Location

Ankara

Type

conf

DOI

10.1109/ICECCO.2013.6718256

Filename

6718256