PARALLEL SELF-ORGANIZING FEATURE MAPS FOR UNSUPERVISED PATTERN RECOGNITION

International Journal of General SystemsPublished 1 May 1990

Terrance L. Huntsberger, Pongsak Ajjimarangsee

DOI10.1080/03081079008935088

Source URL

Citations150

SJR quartileQ2

SJR score0.56

SNIP1.17

TL;DR

This paper presents four new algorithms based on the Kohonen self-organizing feature maps which are capable of generating a continuous valued output.

Abstract

Abstract Neural network research has recently undergone a revival for use in pattern recognition applications.1 If a training set of data can be provided, the supervised types of networks, such as the Hopfield nets or perceptrons, can be used to recognize patterns. 10·11·18 For unsupervised pattern recognition, systems such as those of the Carpenter/Grossberg ART2 system8 and Kohonens’ self-organizing feature maps11 are the most commonly used The problem of poor separability of input vectors was recently addressed by Keller and Hunt with the fuzzy perceptron model. 13 However, with the exception of the ART2 system, none of these systems are capable of producing continuous valued output, as would be a desirable model for representation of non-distinct input vectors. This paper presents four new algorithms based on the Kohonen self-organizing feature maps which are capable of generating a continuous valued output. 4 We also present the results of some experimental studies run on the NCUBE/10 hypercube at the University of South Carolina. INDEX TERMS: Clusteringneural netspattern recognition.

Keywords

Computer Science

Bulletin of Mathematical BiologyA logical calculus of the ideas immanent in nervous activity

17,984 Citations1943Warren S. McCulloch, Walter Pitts

The MIT Press eBooksParallel Distributed Processing

15,227 Citations1986David E. Rumelhart, James L. McClelland +1 more

Springer series in information sciencesSelf-Organization and Associative Memory

8,770 Citations1989Teuvo Kohonen

Psychology Press eBooksThe Organization of Behavior

8,467 Citations2005D. O. Hebb

IEEE ASSP MagazineAn introduction to computing with neural nets

7,858 Citations1987Richard P. Lippmann

ScienceComputing with Neural Circuits: A Model

2,130 Citations1986J. J. Hopfield, David W. Tank

A new conceptual framework and a minimization principle together provide an understanding of computation in model neural circuits that represent an approximation to biological neurons in which a simplified set of important computational properties is retained.

The MIT Press eBooksNeural Networks and Natural Intelligence

723 Citations1988

This book is packed with real-time computer simulations and rigorous demonstrations of results on vision, speech, cognitive information processing; adaptive pattern recognition, adaptive robotics, conditioning and attention, cognitive-emotional interactions, and decision making under risk.

IEEE Transactions on Pattern Analysis and Machine IntelligenceIncorporating Fuzzy Membership Functions into the Perceptron Algorithm

235 Citations1985James M. Keller, Douglas J. Hunt

It is shown that the fuzzy perceptron, like its crisp counterpart, converges in the separable case.

Pattern RecognitionIterative fuzzy image segmentation

132 Citations1985T.L. Huntsherger, Chuck Jacobs +1 more

This work has led to the development of a iterative fuzzy clustering technique which represents an image segmentation scheme which can be used as a preprocessor for a multivalued logic based computer vision system.

Pattern recognition by neural network model on hypercubes

9 Citations1988W. Furmański

Preliminary results indicate that local spatial decomposition of characters in the training set leads to simple parallel implementation of the neural net model on hypercubes, and also serves as an effective pre-processor which provides high quality of recognition and good efficiency.