| | |
Summary: Neural network uncertainty assessment using Bayesian
statistics with application to remote sensing:
3. Network Jacobians
F. Aires
Department of Applied Physics and Applied Mathematics, Columbia University/NASA Goddard Institute for Space Studies,
New York, USA
CNRS/IPSL/Laboratoire de Me´te´orologie Dynamique, E´cole Polytechnique, Palaiseau, France
C. Prigent
CNRS, LERMA, Observatoire de Paris, Paris, France
W. B. Rossow
NASA Goddard Institute for Space Studies, New York, USA
Received 22 September 2003; revised 17 February 2004; accepted 18 March 2004; published 21 May 2004.
[1] Used for regression fitting, neural network (NN) models can be used effectively to
represent highly nonlinear, multivariate functions. In this situation, most emphasis has
been on estimating the output errors, but almost no attention has been given to errors
associated with the internal structure of the NN model. The complex relationships linking
the inputs to the outputs inside the network are the essence of the model and assessing
their physical meaning makes all the difference between a ``black box'' model with small
output errors and a physically meaningful model that will provide insight on the problem
and will have better generalization properties. Such dependency structures can, for
|
