A modular neural network architecture for pattern classification

Author

Elsherif, H. ; Hambaba, M.

Author_Institution

Electr. Eng. & Comput. Sci. Dept., Stevens Inst. of Technol., Hoboken, NJ, USA

fYear

1993

fDate

6-9 Sep 1993

Firstpage

232

Lastpage

238

Abstract

A modular neural network architecture is proposed to classify binary and continuous patterns. This system consists of a supervised feedforward backpropagation network and an unsupervised self-organization map network. The supervised feedforward (basic) network is trained until a saturation error level occurs. Simultaneously, the unsupervised self-organization map (control) network fluids the mapping features for the given input/output patterns. The resultant features are used by Gaussian and linear functions to adjust the hidden and the output weights of the basic network and to classify the given patterns

Keywords

backpropagation; feedforward neural nets; pattern recognition; self-organising feature maps; Gaussian functions; architecture; hidden weight; input/output patterns; linear functions; mapping features; modular neural network; output weights; pattern classification; supervised feedforward backpropagation network; unsupervised self-organization map network; Artificial neural networks; Biological neural networks; Computer architecture; Feedforward neural networks; Feedforward systems; Intelligent systems; Jacobian matrices; Neural networks; Pattern classification; Speech recognition;

fLanguage

English

Publisher

ieee

Conference_Titel

Neural Networks for Processing [1993] III. Proceedings of the 1993 IEEE-SP Workshop

Conference_Location

Linthicum Heights, MD

Print_ISBN

0-7803-0928-6

Type

conf

DOI

10.1109/NNSP.1993.471865

Filename

471865