Share Email Print

Proceedings Paper

New algorithm for self-organizing neural classifiers suitable for easy hardware implementation
Author(s): Slawomir Przylucki; Konrad Plachecki; Mariusz Duk
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

Artificial neural networks (ANN), or connectionist classifiers, are massively parallel computation systems that are based on simplified models of the human brain. Their complex classifications capabilities, combined with properties such as generalization, fault-tolerance and learning make them attractive for a range of applications that conventional computers found difficult. One of the possible neural net applications is an analysis of high dimension data sets. Thanks to mentioned above classifications capabilities, net output signals are low-dimension representations of inputs where each output can represented some input signal feature. In this paper we present the new algorihtm of multivariate data classification. The algorithm based on modified counterpropagation neural network. The main goal of our research as to develop a new classifier architecture which reduces the required number of interconnection in a hidden layer as well as output layer. That allows easier hardware implementation of proposed algorithm.

Paper Details

Date Published: 24 October 2003
PDF: 7 pages
Proc. SPIE 5125, Photonics Applications in Astronomy, Communications, Industry, and High-Energy Physics Experiments, (24 October 2003); doi: 10.1117/12.532389
Show Author Affiliations
Slawomir Przylucki, Technical Univ. of Lublin (Poland)
Konrad Plachecki, Technical Univ. of Lublin (Poland)
Mariusz Duk, Technical Univ. of Lublin (Poland)

Published in SPIE Proceedings Vol. 5125:
Photonics Applications in Astronomy, Communications, Industry, and High-Energy Physics Experiments
Ryszard S. Romaniuk; Krzysztof T. Pozniak, Editor(s)

© SPIE. Terms of Use
Back to Top