Summary
In this paper we present a fully automatic and computationally efficient algorithm for optimising multilayer perceptron classifiers. The approach involves two procedures: adaptation (training) and selection. The first procedure adaptively changes the weights of the network. The selection procedure performs the elimination of some of the hidden units (weights). By iteratively combining these two procedures we achieve a controlled way of training and modifying neural networks, which balances accuracy, learning time, and complexity of the resulting network. We demonstrate our method on the problem of multispectral Landsat image classification. We compare our results with a hand designed multi-layer perceptron and a Gaussian maximum likelihood classifier on the same data. Our method produces a better classification accuracy with a smaller number of hidden units than the hand designed network.
This work was supported by a grant from the Austrian National Fonds zur Förderung der wissenschaftlichen Forschung (No. S7002MAT).
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
H. Bischof, Pyramidal Neural Networks, Lawrence Erlbaum Associates, 1995.
H. Bischof, W. Schneider, and A. Pinz, “Multispectral classification of Landsatimages using neural networks”, IEEE Transactions on Geoscience and Remote Sensing, vol. 30, no. 3, pp. 482–490, 1992.
A. Cichocki and R. Unbehauen, Neural Networks for Optimisation and Signal Processing, New York: Wiley, 1993.
R. O. Duda and P. E. Hart, Pattern Classification and Scene Analysis, New York: Wiley, 1973.
F. Glover and M. Laguna, “Tabu search”, In C. R. Reeves, editor, Modern heuristic techniques for combinatorial problems,pp. 70–150, Blackwell Scientific Publications, 1993.
B. Hassibi and D. G. Stork, “Second order derivatives for network pruning: Optimal brain surgeo”,n In S. J. Hanson et al., editor, NIPS 5, pp. 164–172, Morgan Kaufmann, 1993.
G. E. Hinton, J. L. McClelland, and D. E. Rumelhart, “Distributed representations”, In D. E. Rumelhart and J. L. McClelland, editors, Parallel Distributed Processing, vol. 1, pp. 77–109, Cambridge, MA: MIT Press, 1986.
Y. L. Le Cun, J. S. Denker, and S. A. Solla, “Optimal brain damage”, In D. S. Touretzky, editor, Advances in Neural Information Processing Systems 2, pp. 598–605, San Mateo, CA: Morgan Kaufmann, 1988.
A. Leonardis, A. Gupta, and R. Bajcsy, “Segmentation of range images as the search for geometric parametric models”, International Journal of Computer Vision, vol. 14, no. 3,pp. 253–277, 1995.
A. Leonardis and H. Bischof, “Complexity optimisation of adaptive RBF networks”, 13th International Conference on Pattern Recognition, vol. IV, IEEE Comp.Soc., 1996 (in press).
J. Rissanen, “Universal coding, information, prediction, and estimation”, IEEE Transactions on Information Theory,vol. 30, pp. 629–636, 1984.
R. Wagner, Verfolgung der Siedlungsentwicklung mit Landsat TM Bilddaten (Settlement development with Landsat TM data), PhD thesis, Institute for Surveying and Remote Sensing, University of Natural Resources, Vienna, 1991.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 1997 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Bischof, H., Leonardis, A. (1997). Optimising Neural Networks for Land Use Classification. In: Kanellopoulos, I., Wilkinson, G.G., Roli, F., Austin, J. (eds) Neurocomputation in Remote Sensing Data Analysis. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-59041-2_22
Download citation
DOI: https://doi.org/10.1007/978-3-642-59041-2_22
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-63828-2
Online ISBN: 978-3-642-59041-2
eBook Packages: Springer Book Archive