Share Email Print

Proceedings Paper

DIGNET: a self-organizing neural network for automatic pattern recognition and classification
Author(s): Stelios C.A. Thomopoulos; Dimitrios K. Bougoulias
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

The demonstrated ability of artificial neural networks to retrieve information that is addressed by content makes them a competitive candidate for automatic pattern recognition. Furthermore, their capability to reconstruct their memory from partially presented stored information compliments their recognition capabilities with classification. However, artificial neural networks (ANNs) are known to possess preferential behavior as far as the initial conditions and noise interference are concerned. A self-organizing artificial neural network is presented that exhibits deterministically reliable behavior to noise interference when the noise does not exceed a specified level of tolerance. The complexity of the proposed ANN, in terms of neuron requirements versus stored patterns, increases linearly with the number of stored patterns and their dimensionality. The self-organization of the proposed DIGNET is based on the idea of competitive generation and elimination of attraction wells in the pattern space. The same artificial neural network can be sued both for pattern recognition and classification.

Paper Details

Date Published: 1 August 1991
PDF: 10 pages
Proc. SPIE 1470, Data Structures and Target Classification, (1 August 1991); doi: 10.1117/12.44860
Show Author Affiliations
Stelios C.A. Thomopoulos, The Pennsylvania State Univ. (United States)
Dimitrios K. Bougoulias, Southern Illinois Univ. (United States)

Published in SPIE Proceedings Vol. 1470:
Data Structures and Target Classification
Vibeke Libby, Editor(s)

© SPIE. Terms of Use
Back to Top