Analysis and optimization of neural networks for remote sensing

Abstract A technique for improving the topology of a trained neural network, used for an inversion or classification problem, is presented. The technique models the multilayer perceptron as a power series, which allows us to (1) remove units from the network which are well‐approximated by zero‐degree or first‐degree polynomials, (2) measure the effect of removing a hidden layer, and (3) determine the degree of the overall polynomial discriminant which approximates the network. The smaller, pruned networks can process data faster than can the larger original networks. The network degree is a direct measure of the nonlinearity inherent in the particular inversion or classification problem of interest. Neural networks for inversion of surface scattering parameters and classification of sea ice are analyzed to illustrate the technique.

[1]  T. Kohonen,et al.  Statistical pattern recognition with neural networks: benchmarking studies , 1988, IEEE 1988 International Conference on Neural Networks.

[2]  Michael T. Manry,et al.  Basis vector analyses of back-propagation neural networks , 1991, [1991] Proceedings of the 34th Midwest Symposium on Circuits and Systems.

[3]  Taiho Koh,et al.  Second-order Volterra filtering and its application to nonlinear system identification , 1985, IEEE Trans. Acoust. Speech Signal Process..

[4]  Michael T. Manry,et al.  Inversion of Surface Parameters Using Fast Learning Neural Networks , 1992, [Proceedings] IGARSS '92 International Geoscience and Remote Sensing Symposium.

[5]  James L. McClelland,et al.  Parallel distributed processing: explorations in the microstructure of cognition, vol. 1: foundations , 1986 .

[6]  P. D. Heermann,et al.  Classification of multispectral remote sensing data using a back-propagation neural network , 1992, IEEE Trans. Geosci. Remote. Sens..

[7]  Dennis Gabor,et al.  A universal nonlinear filter, predictor and simulator which optimizes itself by a learning process , 1961 .

[8]  P. Werbos,et al.  Beyond Regression : "New Tools for Prediction and Analysis in the Behavioral Sciences , 1974 .

[9]  Michael T. Manry,et al.  Conventional modeling of the multilayer perceptron using polynomial basis functions , 1993, IEEE Trans. Neural Networks.

[10]  Michael T. Manry,et al.  Output weight optimization for the multi-layer perceptron , 1992, [1992] Conference Record of the Twenty-Sixth Asilomar Conference on Signals, Systems & Computers.

[11]  G. W. Davis,et al.  ANN modeling of Volterra systems , 1991, IJCNN-91-Seattle International Joint Conference on Neural Networks.

[12]  William H. Press,et al.  Numerical recipes , 1990 .

[13]  P. Swain,et al.  Neural Network Approaches Versus Statistical Methods In Classification Of Multisource Remote Sensing Data , 1990 .

[14]  Ron Kwok,et al.  Application Of Neural Networks To Sea Ice Classification Using Polarimetric SAR Images , 1991, [Proceedings] IGARSS'91 Remote Sensing: Global Monitoring for Earth Management.

[15]  Michael T. Manry,et al.  Backpropagation representation theorem using power series , 1990, 1990 IJCNN International Joint Conference on Neural Networks.

[16]  Adrian K. Fung,et al.  Sea Ice Classification Using Fast Learning Neural Networks , 1992, [Proceedings] IGARSS '92 International Geoscience and Remote Sensing Symposium.

[17]  G. Govind,et al.  Multi-layered neural networks and Volterra series: The missing link , 1990, 1990 IEEE International Conference on Systems Engineering.

[18]  Michael T. Manry,et al.  Power series analyses of back-propagation neural networks , 1991, IJCNN-91-Seattle International Joint Conference on Neural Networks.

[19]  I. W. Sandberg.  Approximation theorems for discrete-time systems , 1991 .

[20]  Michael T. Manry,et al.  Surface parameter retrieval using fast learning neural networks , 1993 .

[21]  Horst Bischof,et al.  Multispectral classification of Landsat-images using neural networks , 1992, IEEE Trans. Geosci. Remote. Sens..

[22]  Maureen Caudill.  The polynomial ADALINE algorithm , 1988 .

[23]  D. F. Specht,et al.  Probabilistic neural networks for classification, mapping, or associative memory , 1988, IEEE 1988 International Conference on Neural Networks.