Get 20M+ Full-Text Papers For Less Than $1.50/day. Start a 14-Day Trial for You or Your Team.

Learn More →

Self-Organizing Neural Networks as a Means of Cluster Analysis in Clinical Chemistry

Self-Organizing Neural Networks as a Means of Cluster Analysis in Clinical Chemistry Introduction The basic concepts of connectionist computing schemes, often referred to in a suggestive way as "neural networks", date back to the 1940's (1). An initial burst of enthusiasm accompanied the invention of the "perceptron" (2), but early hopes were disappointed, and only few pioneers continued studying such models (3). The demonstration that principles of the theoretical physics of multiparticle systems are applicable to connectionist data processing schemes (4) gave new respectability to the field, and the invention of ingenious and efficient learning schemes such as the error back-propagation method (5) led to a remarkable renaissance of interest in the field. Neural networks are an attempt to model, albeit in a very primitive and over-simplistic way, principles of data processing which are thought to give biological nervous systems and brains their superb capabilities in performing complex tasks, particularly in the wide and important field of pattern recognition. It is only natural therefore that neural network models have also been studied in medical science, particularly with Eur. J. Clin. Chem. Clio. Bioehem. / Vol. 31,1993 / No. 5 the aim of recognizing patterns underlying complex data sets and employing these patterns for diagnostic purposes (6 -- 12). Most if http://www.deepdyve.com/assets/images/DeepDyve-Logo-lg.png Clinical Chemistry and Laboratory Medicine de Gruyter

Self-Organizing Neural Networks as a Means of Cluster Analysis in Clinical Chemistry

Loading next page...
 
/lp/de-gruyter/self-organizing-neural-networks-as-a-means-of-cluster-analysis-in-N12efbojZv

References

References for this paper are not available at this time. We will be adding them shortly, thank you for your patience.

Publisher
de Gruyter
Copyright
Copyright © 2009 Walter de Gruyter
ISSN
1434-6621
eISSN
1437-4331
DOI
10.1515/cclm.1993.31.5.311
Publisher site
See Article on Publisher Site

Abstract

Introduction The basic concepts of connectionist computing schemes, often referred to in a suggestive way as "neural networks", date back to the 1940's (1). An initial burst of enthusiasm accompanied the invention of the "perceptron" (2), but early hopes were disappointed, and only few pioneers continued studying such models (3). The demonstration that principles of the theoretical physics of multiparticle systems are applicable to connectionist data processing schemes (4) gave new respectability to the field, and the invention of ingenious and efficient learning schemes such as the error back-propagation method (5) led to a remarkable renaissance of interest in the field. Neural networks are an attempt to model, albeit in a very primitive and over-simplistic way, principles of data processing which are thought to give biological nervous systems and brains their superb capabilities in performing complex tasks, particularly in the wide and important field of pattern recognition. It is only natural therefore that neural network models have also been studied in medical science, particularly with Eur. J. Clin. Chem. Clio. Bioehem. / Vol. 31,1993 / No. 5 the aim of recognizing patterns underlying complex data sets and employing these patterns for diagnostic purposes (6 -- 12). Most if

Journal

Clinical Chemistry and Laboratory Medicinede Gruyter

Published: Jan 1, 1993

There are no references for this article.