Title :
Domain check for input to NN emulating an inverse model
Author :
Schiller, Helmut ; Krasnopolsky, Vladimir
Author_Institution :
GKSS Forschungszentrum, Geesthacht, Germany
Abstract :
Multi-layer perceptrons are used in many fields of science and technology to emulate forward and inverse models. The paper proposes a necessary condition check for the validity of results obtained by inverse NNs. The solution consists of a combination of inverse and forward NNs that, in addition to the inversion, computes a quality measure for the inversion. Examples of such combined NNs from applications in the remote sensing area are discussed
Keywords :
geophysics computing; multilayer perceptrons; remote sensing; domain check; forward models; inverse model; multilayer perceptrons; necessary condition check; quality measure; remote sensing; Geophysical measurements; Geophysics computing; Inverse problems; Multilayer perceptrons; Neural networks; Performance evaluation; Remote sensing; Satellites; Training data; Water;
Conference_Titel :
Neural Networks, 2001. Proceedings. IJCNN '01. International Joint Conference on
Conference_Location :
Washington, DC
Print_ISBN :
0-7803-7044-9
DOI :
10.1109/IJCNN.2001.938499
