The Community for Technology Leaders
Proceedings of 1994 28th Asilomar Conference on Signals, Systems and Computers (1994)
Pacific Grove, CA, USA
Oct. 31, 1994 to Nov. 2, 1994
ISSN: 1058-6393
ISBN: 0-8186-6405-3
pp: 902-906
L.M. Liu , Dept. of Electr. Eng., Texas Univ., Arlington, TX, USA
M.T. Manry , Dept. of Electr. Eng., Texas Univ., Arlington, TX, USA
F. Amar , Dept. of Electr. Eng., Texas Univ., Arlington, TX, USA
M.S. Dawson , Dept. of Electr. Eng., Texas Univ., Arlington, TX, USA
A.K. Fung , Dept. of Electr. Eng., Texas Univ., Arlington, TX, USA
ABSTRACT
A new objective function for neural net classifier design is presented, which has more free parameters than the classical objective function. An iterative minimization technique for the objective function is derived which requires the solution of multiple sets of numerically ill-conditioned linear equations. A numerically stable solution to the neural network design equations, which utilizes the conjugate gradient algorithm and a relaxation algorithm, is presented. The design method is applied to networks used to classify SAR imagery from remote sensing. The improvement of the iterative technique over classical design approaches is clearly demonstrated.<>
INDEX TERMS
image classification, conjugate gradient methods, minimisation, remote sensing by radar, radar imaging, synthetic aperture radar, geophysical signal processing, multilayer perceptrons
CITATION

L. Liu, M. Manry, F. Amar, M. Dawson and A. Fung, "Iterative improvement of image classifiers using relaxation," Proceedings of 1994 28th Asilomar Conference on Signals, Systems and Computers(ACSSC), Pacific Grove, CA, USA, 1995, pp. 902-906.
doi:10.1109/ACSSC.1994.471591
95 ms
(Ver 3.3 (11022016))