Share Email Print

Proceedings Paper

Noise tolerance of adaptive resonance theory neural network for binary pattern recognition
Author(s): Yong Soo Kim; Sunanda Mitra
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

Assuming a fast learning condition for an adaptive resonance theory (ART) type neural network, we have explored the effect of the vigilance parameter and the order function on the performance of the neural network for binary pattern recognition. A modified search order was developed for classification of binary alphabet characters and airplane classes and compared with the performance of the original ART-1 network for binary pattern recognition with and without the presence of noise. Our results suggest that the effect of noise on binary pattern recognition is solely dependent on the induced changes in the critical feature patterns when other control parameters remained the same.

Paper Details

Date Published: 1 December 1991
PDF: 8 pages
Proc. SPIE 1565, Adaptive Signal Processing, (1 December 1991); doi: 10.1117/12.49787
Show Author Affiliations
Yong Soo Kim, Texas Tech Univ. (United States)
Sunanda Mitra, Texas Tech Univ. (United States)

Published in SPIE Proceedings Vol. 1565:
Adaptive Signal Processing
Simon Haykin, Editor(s)

© SPIE. Terms of Use
Back to Top
Sign in to read the full article
Create a free SPIE account to get access to
premium articles and original research
Forgot your username?