12 September 2005 Pattern recognition and classification using weightless neural networks (WNN) and Steinbuch Lernmatrix
Author Affiliations +
Proceedings Volume 5916, Mathematical Methods in Pattern and Image Analysis; 59160P (2005); doi: 10.1117/12.621783
Event: Optics and Photonics 2005, 2005, San Diego, California, United States
Abstract
This proposal presents a novel use of Weightless Neural Networks (WNN) and Steinbuch Lernmatrix for pattern recognition and classification. High speed of learning, easy of implementation and flexibility given by WNN, combined with the learning capacity, recovery efficiency, noise immunity and fast processing shown by Steinbuch Lernmatrix are key factors considered on the pattern recognition exposed by the suggested model. For experimental purposes, the fundamental pattern sets are built and provided to the model under the learning phase. The additive, subtractive and mixed noises are applied to fundamental patterns to check out the response of the model during the recovery phase. Field Programmable Gate arrays are used in the implementation of such model, since it allows custom user-defined models to be embedded in a reconfigurable hardware platform, and provides block memories and dedicated multipliers suitable for the model.
© (2005) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Amadeo Jose Argüelles C., Juan Luis Díaz de León S., Cornelio Yáñez M., Oscar Camacho N., "Pattern recognition and classification using weightless neural networks (WNN) and Steinbuch Lernmatrix", Proc. SPIE 5916, Mathematical Methods in Pattern and Image Analysis, 59160P (12 September 2005); doi: 10.1117/12.621783; https://doi.org/10.1117/12.621783
PROCEEDINGS
8 PAGES


SHARE
KEYWORDS
Pattern recognition

Neural networks

Binary data

Neurons

Image classification

Logic

Content addressable memory

RELATED CONTENT

Improving The Performance Of Neural Networks
Proceedings of SPIE (May 03 1988)
Beyond Pattern Recognition With Neural Nets
Proceedings of SPIE (February 08 1989)
Novel RAM-based neural networks for object recognition
Proceedings of SPIE (October 31 1996)
Multithresholding: a neural approach
Proceedings of SPIE (May 01 1994)

Back to Top