DocumentCode
2740720
Title
Multimodular neural architecture for teledetection
Author
Thiria ; Mejia, Carolina ; Badran, F. ; Crepon, M.
Author_Institution
Lab. de Recherche en Inf., Univ. de Paris Sud, Orsay
fYear
1991
fDate
8-14 Jul 1991
Abstract
Summary form only given, as follows. In order to solve complex tasks, a ´machine´ made with three levels of nonlinear multilayer networks has been designed. Each level works in parallel and is dedicated to a specific task. On each level all networks are of the same type. This machine was used to compute wind direction and wind speed measured by satellite scatterometers. The performances obtained demonstrate the power of this approach
Keywords
atmospheric techniques; geophysics computing; neural nets; remote sensing; wind; multimodular neural architecture; nonlinear multilayer networks; performance; satellite scatterometers; teledetection; wind direction; wind speed; Algorithm design and analysis; Application software; Art; Computer networks; Design engineering; Group technology; Neural networks; Power engineering computing; Resonance; Wind speed;
fLanguage
English
Publisher
ieee
Conference_Titel
Neural Networks, 1991., IJCNN-91-Seattle International Joint Conference on
Conference_Location
Seattle, WA
Print_ISBN
0-7803-0164-1
Type
conf
DOI
10.1109/IJCNN.1991.155569
Filename
155569
Link To Document