Structure determination of artificial neural network using modified cellular encoding

Author

Alim, Md Abdul ; Rabbani, Md Golam ; Azad, Mohammad Mohiuddin

Author_Institution

Bangladesh Univ. of Eng. & Technol., Dhaka

fYear

2007

fDate

27-29 Dec. 2007

Firstpage

1

Lastpage

6

Abstract

This paper works with a new evolutionary system to construct and control the structure of feed forward artificial neural networks (ANNs), represented by modified cellular encoding (MCE) that is not subject to the well-known permutation problem. It is shown in this paper that addition or deletion of nodes or connections can evidently be done by crossover automatically. Hence, the number of user specified parameter is also decreased. The ANN architecture determination algorithm is tested on some real world problems. The algorithm is made adaptive.

Keywords

evolutionary computation; feedforward neural nets; neural net architecture; artificial neural network structure determination; evolutionary system; feed forward artificial neural networks; modified cellular encoding; Artificial neural networks; Automatic control; Cellular networks; Cellular neural networks; Electronic mail; Encoding; Neural networks; Neurons; Paper technology; Tree graphs; Artificial Neural Network; Evolutionary Process; Modified Cellular Encoding; Permutation problem;

fLanguage

English

Publisher

ieee

Conference_Titel

Computer and information technology, 2007. iccit 2007. 10th international conference on

Conference_Location

Dhaka

Print_ISBN

978-1-4244-1550-2

Electronic_ISBN

978-1-4244-1551-9

Type

conf

DOI

10.1109/ICCITECHN.2007.4579425

Filename

4579425