Share Email Print

Proceedings Paper

Genetic algorithms in estimating optimal neural network topologies for the classification of remotely sensed images
Author(s): Demetris Stathakis
Format Member Price Non-Member Price
PDF $14.40 $18.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

Neural networks have received much attention in the field of remote sensing. Topology identification remains however one of the major difficulties in the efficient application of neural networks. Currently, topology determination is based on trial and error, on heuristics that amalgamate past experience and on weight pruning algorithms. It is argued in this paper that global search methods such as genetic algorithms can be deployed in discovering near optimal network topologies. An example on multisource classification for land cover mapping is presented. The results indicate that the global search paradigm is worth further exploration especially now that computing becomes more and more powerful.

Paper Details

Date Published: 24 October 2007
PDF: 8 pages
Proc. SPIE 6748, Image and Signal Processing for Remote Sensing XIII, 67480T (24 October 2007); doi: 10.1117/12.736455
Show Author Affiliations
Demetris Stathakis, Joint Research Ctr. (Italy)

Published in SPIE Proceedings Vol. 6748:
Image and Signal Processing for Remote Sensing XIII
Lorenzo Bruzzone, Editor(s)

© SPIE. Terms of Use
Back to Top