A new neural network classifier based on ART theory

Author

Lv, Xiu-jiang ; Zhang, Qi-Wen ; Zhao, Yan ; Li, Yu-E ; Yao, Guang-shun

Author_Institution

Dept. of Electron. & Electr. Eng., Changchun Univ. of Technol., China

Volume

4

fYear

2005

fDate

18-21 Aug. 2005

Firstpage

2059

Abstract

ART-2 is a self-organized and unsupervised artificial neural network constructed from adaptive resonance theory which can be used to classify continuous active data. We have found that the theory is limited of the same phase data with different amplitudes and insensitivity to gradual change data during the simulation of data classified with ART-2 neural network. Therefore, we propose a new neural network model based on adaptive resonance theory. We provide the model construction and relevant algorithm as well as the comparison with ART-2.

Keywords

ART neural nets; learning (artificial intelligence); pattern classification; ART theory; ART-2 neural network classifier; adaptive resonance theory; unsupervised artificial neural network; Adaptive filters; Adaptive systems; Artificial neural networks; Cybernetics; Electronic mail; Machine learning; Neural networks; Neurofeedback; Resonance; Subspace constraints; ART-2; adaptive resonance theory; classifer; neural network;

fLanguage

English

Publisher

ieee

Conference_Titel

Machine Learning and Cybernetics, 2005. Proceedings of 2005 International Conference on

Conference_Location

Guangzhou, China

Print_ISBN

0-7803-9091-1

Type

conf

DOI

10.1109/ICMLC.2005.1527284

Filename

1527284