A novel Boolean self-organization mapping based on fuzzy geometrical expansion

Author

Chaudhari, Narendra S. ; Wang, D.

Author_Institution

Sch. of Comput. Eng., Nanyang Technol. Univ., Singapore

Volume

2

fYear

2003

fDate

15-18 Dec. 2003

Firstpage

1211

Abstract

A novel self-organization mapping algorithm for Boolean neural networks (BSOM) based on geometrical expansion is proposed in this paper. The proposed BSOM algorithm possesses generalization capability. Compared with traditional self organization mapping (SOM) algorithms, BSOM algorithm is based on geometrical expansion, not gradient descent. BSOM algorithm memorizes more vectors in a hidden neuron, not only an exemplar in the center of SOM cell. Finally BSOM algorithm needs less number of iterations and simple training equations. Test results are given on simple Boolean functions, and a randomly generated Boolean function with 10 variables.

Keywords

Boolean functions; gradient methods; learning (artificial intelligence); self-organising feature maps; BNN; BSOM; Boolean function; Boolean neural networks; binary neural network; geometrical expansion; hidden neuron; self-organization mapping algorithm; Backpropagation algorithms; Boolean functions; Computer networks; Data mining; Equations; Hamming distance; Neural networks; Neurons; Testing; Very large scale integration;

fLanguage

English

Publisher

ieee

Conference_Titel

Information, Communications and Signal Processing, 2003 and Fourth Pacific Rim Conference on Multimedia. Proceedings of the 2003 Joint Conference of the Fourth International Conference on

Print_ISBN

0-7803-8185-8

Type

conf

DOI

10.1109/ICICS.2003.1292653

Filename

1292653