An enhanced fuzzy neural network

Authors:
Kwang Baek Kim;Young-Hoon Joo;Jae-Hyun Cho
Affiliations:
Dept. of Computer Engineering, Silla University, S. Korea;School of Electronic and Information Engneering, Kunsan National University, S. Korea;Dept. of Computer Information, Catholic University of Pusan, S. Korea
Venue:
PDCAT'04 Proceedings of the 5th international conference on Parallel and Distributed Computing: applications and Technologies
Year:
2004

Citing 1
Cited 6

Back-propagation algorithm which varies the number of hidden units

Neural Networks

Enhanced fuzzy single layer perceptron

ISNN'05 Proceedings of the Second international conference on Advances in Neural Networks - Volume Part I
Recognition of concrete surface cracks using the ART1-Based RBF network

ISNN'06 Proceedings of the Third international conference on Advnaces in Neural Networks - Volume Part II
Recognition of identifiers from shipping container images using fuzzy binarization and enhanced fuzzy neural network

FSKD'05 Proceedings of the Second international conference on Fuzzy Systems and Knowledge Discovery - Volume Part I
A physiological fuzzy neural network

ICNC'05 Proceedings of the First international conference on Advances in Natural Computation - Volume Part III
Performance improvement of fuzzy RBF networks

ICNC'05 Proceedings of the First international conference on Advances in Natural Computation - Volume Part I
Recognition of concrete surface cracks using ART2-Based radial basis function neural network

ICCSA'06 Proceedings of the 2006 international conference on Computational Science and Its Applications - Volume Part III

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper, we propose a novel approach for evolving the architecture of a multi-layer neural network. Our method uses combined ART1 algorithm and Max-Min neural network to self-generate nodes in the hidden layer. We have applied the proposed method to the problem of recognizing ID number in identity cards. Experimental results with a real database show that the proposed method has better performance than a conventional neural network.