Paper
6 April 1995 Eliminating order dependency of classification in artificial resonance theory (ART1) networks
Astrid Leuba, Billy V. Koen
Author Affiliations +
Abstract
Incorrect classification of patterns can occur with ART1 networks when data are presented in certain sequences. The reason for this problem is the coding of the category templates, which are memory-less and give more importance to 1s than to 0s. This paper modifies the ART1 network architecture to alter these two features by adding a second set of top-down LTMs, in effect defining a second template. Computer simulations show that this modification ensures that patterns are always classified in the same category and that information is never lost. As a result, no pre-processing of the data is necessary, and ART1 networks can be used to classify patterns on-line without errors.
© (1995) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Astrid Leuba and Billy V. Koen "Eliminating order dependency of classification in artificial resonance theory (ART1) networks", Proc. SPIE 2492, Applications and Science of Artificial Neural Networks, (6 April 1995); https://doi.org/10.1117/12.205192
Advertisement
Advertisement
RIGHTS & PERMISSIONS
Get copyright permission  Get copyright permission on Copyright Marketplace
KEYWORDS
Image classification

Network architectures

Detection and tracking algorithms

Neurons

Optical character recognition

Computer simulations

Sensors

RELATED CONTENT

A reusable robotic grasping creator
Proceedings of SPIE (May 07 2010)
Neural network target tracker
Proceedings of SPIE (August 01 1990)
MOSIX cluster: construction and testing
Proceedings of SPIE (October 11 2005)

Back to Top