Abstract
In this paper, we present an algorithm that provides adaptive plasticity in function approximation problems: the deformable (feature) map (DM) algorithm. The DM approach reduces a class of similar function approximation problems to the explicit supervised one-shot trainng of a single data set. This is followed by a subsequent, appropriate similarity transformation which is based on a self-organized deformation of the underlying multidimensional probability distributions. After discussing the theory of the DM algorithm, we use a computer simulation to visualize its effects on a two-dimensional toy example. Finally, we present results of its application to the real-world problem of fully automatic voxel-based multispectral image segmentation, employing magnetic resonance data sets of the human brain.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
D.R. Dersch. Eigenschaften neuronaler Vektorquantisierer und ihre Anwendung in der Sprachverarbeitung. Verlag Harri Deutsch, Reihe Physik, Bd. 54, Thun, Frankfurt am Main, 1996. ISBN 3-8171-1492-3.
F. Girosi and T. Poggio. Networks and the best approximation property. Biological Cybernetics, 63:169–176, 1990.
J. Kohlmorgen, K.R. Müller, and K. Pawelzik. Improving short-term prediction with competing experts. In Proceedings of the International Conference on Artificial Neural Networks ICANN, volume 2, pages 215–220, Paris, 1995. EC2 & Cie.
T. Kohonen. Self-Organization and Associative Memory. Springer, Berlin, 1989.
J. Moody and C. Darken. Fast learning in networks of locally-tuned processing units. Neural Computation, 1:281–294, 1989.
K. Rose, E. Gurewitz, and G.C. Fox. Vector quantization by deterministic annealing. IEEE Transactions on Information Theory, 38(4):1249–1257, 1992.
D.E. Rumelhart and J.L. McClelland. Learning internal representations by error propagation. In Parallel Distributed Processing, volume I. M.I.T. Press, Cambridge, MA, 1986.
J. Walter and H. Ritter. Investment learning with hierarchical PSOM. In A. Wismüller and D.R. Dersch, editors, Symposion über biologische Informationsverarbeitung und Neuronale Netze — SINN’ 95, Konferenzband, pages 161–168. Hanns-Seidel-Stiftung, München, 1996.
A. Wismüller and D.R. Dersch. Neural network computation in biomedical research: chances for conceptual cross-fertilization. Theory in Biosciences, 116(3), 1997.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 1998 Springer-Verlag London
About this paper
Cite this paper
Wismüller, A., Vietze, F., Dersch, D.R., Hahn, K., Ritter, H. (1998). The Deformable Feature Map — Adaptive Plasticity for Function Approximation. In: Niklasson, L., Bodén, M., Ziemke, T. (eds) ICANN 98. ICANN 1998. Perspectives in Neural Computing. Springer, London. https://doi.org/10.1007/978-1-4471-1599-1_14
Download citation
DOI: https://doi.org/10.1007/978-1-4471-1599-1_14
Published:
Publisher Name: Springer, London
Print ISBN: 978-3-540-76263-8
Online ISBN: 978-1-4471-1599-1
eBook Packages: Springer Book Archive