56.

[Cover] [Contents] [Index]

Page 148

longer training time may decrease its attractiveness. The performance of the counter-propagation networks was the least satisfactory in our study. The training stage for fuzzy ARTMAP network is significantly faster than the other network types tested. However, in contrast to the observations made by Carpenter et al. (1997) and Mannan et al. (1998), the performance of the fuzzy ARTMAP networks in our experiments did not show outstanding results. Further comparative studies are required to completely investigate the sensitivity of the performance of fuzzy ARTMAP to factors such as variations in the model-associated parameters and training patterns.

[Cover] [Contents] [Index]


Classification Methods for Remotely Sensed Data
Classification Methods for Remotely Sensed Data, Second Edition
ISBN: 1420090720
EAN: 2147483647
Year: 2001
Pages: 354

flylib.com © 2008-2017.
If you may any questions please contact us: flylib@qtcs.net