Multilayer perceptrons constructed of fuzzy flip-flops

Author

Lovassy, Rita ; Kóczy, László T. ; Gál, László

Author_Institution

Fac. of Eng. Sci., Szechenyi Istvan Univ. Hungary, Gyor, Hungary

fYear

2009

fDate

21-25 Oct. 2009

Firstpage

9

Lastpage

14

Abstract

The target of this paper is to propose a hybrid combination of the three main branches of Computational Intelligence, namely Fuzzy Systems, Neural Networks and Evolutionary Computing. The function approximation properties of fuzzy J-K and D flip-flops based feedforward neural network optimized and trained with a novel evolutionary algorithm based technique; the Bacterial Memetic Algorithm with Modified Operator Execution Order (BMAM) is studied.

Keywords

electronic engineering computing; evolutionary computation; flip-flops; function approximation; fuzzy neural nets; learning (artificial intelligence); multilayer perceptrons; optimisation; bacterial memetic algorithm; computational intelligence; evolutionary algorithm; evolutionary computing; feedforward neural network optimization; function approximation; fuzzy J-K-and-D flip-flop system; modified operator execution order; multilayer perceptron; neural network training; Computational intelligence; Computer networks; Evolutionary computation; Feedforward neural networks; Flip-flops; Function approximation; Fuzzy neural networks; Fuzzy systems; Multilayer perceptrons; Neural networks;

fLanguage

English

Publisher

ieee

Conference_Titel

Computational Intelligence and Intelligent Informatics, 2009. ISCIII '09. 4th International Symposium on

Conference_Location

Luxor

Print_ISBN

978-1-4244-5380-1

Electronic_ISBN

978-1-4244-5382-5

Type

conf

DOI

10.1109/ISCIII.2009.5342288

Filename

5342288