Adaptive BAM for pattern classification

Author

López-Aligué, Francisco J. ; Troncoso, I. Alvarez ; Sotoca, I. Acevedo ; Orellana, C. J García ; Macias, M. Macías ; Velasco, H. González

Author_Institution

Fac. de Ciencias, Univ. de Extremadura, Badajoz, Spain

Volume

5

fYear

2000

fDate

2000

Firstpage

529

Abstract

A new method for the synthesis of neural networks with BAM (bidirectional associative memory) features, based on the ART structure, is presented. Intended for pattern classification, it contains a new procedure for the correct usage of the relation matrix, and avoids the inherent defects of the BAM and its misclassifications with appropriate actions on the thresholds of the neurons of the ART layers. The results clearly indicate that this method leads to a good improvement in the performance that is achievable in a BAM, with a 0% error rate found in a test on the well-known NIST 19 character database

Keywords

ART neural nets; character recognition; content-addressable storage; network synthesis; pattern classification; performance evaluation; ART neural network synthesis; NIST 19 character database; adaptive bidirectional associative memory; error rate; misclassifications; neuron threshold; pattern classification; performance improvement; relation matrix; Associative memory; Error analysis; Magnesium compounds; NIST; Network synthesis; Neural networks; Neurons; Pattern classification; Subspace constraints; Testing;

fLanguage

English

Publisher

ieee

Conference_Titel

Neural Networks, 2000. IJCNN 2000, Proceedings of the IEEE-INNS-ENNS International Joint Conference on

Conference_Location

Como

ISSN

1098-7576

Print_ISBN

0-7695-0619-4

Type

conf

DOI

10.1109/IJCNN.2000.861523

Filename

861523