Polynomial Discrete Time Cellular Neural Networks to solve the XOR problem

Author

Gomez-Ramirez, Ediuardo ; Pazienza, Giovanni Egidio ; Vilasis-Cardona, Xavier

Author_Institution

La Salle Univ., Mexico City

fYear

2006

fDate

28-30 Aug. 2006

Firstpage

1

Lastpage

6

Abstract

Some papers discuss different options to improve the capabilities of cellular neural networks (CNN). The principal point is that a single layer CNN can not solve problems with linearly nonseparable data. In this paper a new model called polynomial discrete time cellular neural networks is presented. This model has a very simple nonlinear term that can improve the performance of the network. The results show how it is possible to solve the XOR problem. The templates of the entire network are computed using genetic algorithm

Keywords

Boolean algebra; cellular neural nets; genetic algorithms; polynomials; XOR problem; genetic algorithm; polynomial discrete time cellular neural networks; Artificial neural networks; Cellular networks; Cellular neural networks; Computer networks; Electronic mail; Genetic algorithms; Helium; Nonhomogeneous media; Nonlinear equations; Polynomials; Polynomial Discrete Time Cellular Neural Networks; XOR problem; genetic algorithm;

fLanguage

English

Publisher

ieee

Conference_Titel

Cellular Neural Networks and Their Applications, 2006. CNNA '06. 10th International Workshop on

Conference_Location

Istanbul

Print_ISBN

1-4244-0640-4

Electronic_ISBN

1-4244-0640-4

Type

conf

DOI

10.1109/CNNA.2006.341598

Filename

4145838