Abstract
Unsupervised learning algorithms realizing topographic mappings are justified by neurobiology while they are useful for multivariate data analysis. In contrast to supervised learning algorithms unsupervised neural networks have their objective function implicitly defined by the learning rule. When considering topographic mapping as an optimization problem, the presence of explicitly defined objective functions becomes essential. In this paper, we show that measures of neighborhood preservation can be used for optimizing and learning topographic mappings by means of evolution strategies. Numerical experiments reveal these measures also being a possible description of the principles governing the learning process of unsupervised neural networks. We argue that quantifying neighborhood preservation provides a link for connecting evolution strategies and unsupervised neural learning algorithms for building hybrid learning architectures.
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
J. C. Bezdek and N. R. Pal. An index of topological preservation for feature extraction. Pattern Recognition, 28(3):381–391, 1995.
R. Folk and A. Kartashov. A simple elastic model for self-organizing topological mappings. Network: Computation in Neural Systems, 5(3):369–387, 1994.
R. Garionis. Quantifying neighborhood preservation: Linking evolutionary and unsupervised neural learning. In X. Yao, R. I. McKay, C. S. Newton, J.-H. Kim, and T. Furuhashi, editors, Proc. Second Asia-Pacific Conf. on simulated Evolution and Learning (SEAL’98), volume 2, Canberra, 1998. University College, The University of New South Wales, Canberra, and Australian Defence Force Academy, Canberra, Australia. ISBN 0-7317-0500-9.
G. J. Goodhill, S. Finch, and T. J. Sejnowski. Optimizing cortical mappings. In D. S. Touretzky, M. C. Mozer, and M. E. Hasselmo, editors, Advances in Neural Information Processing Systems, volume 8, pages 330–336. MIT Press, Cambridge, MA, 1996.
G. J. Goodhill and T. J. Sejnowski. Quantifying neighbourhood preservation in topographic mappings. In Proceedings of the 3rd Joint Symposium on Neural Computation, University of California, San Diego and California Institute of Technology, Pasadena, volume 6, pages 61–82, Pasadena, 1996. California Institute of Technology.
R. Hooke and T. A. Jeeves. Direct search solution of numerical and statistical problems. JACM, 8:221–229, 1961.
T. Kohonen. Self-organized formation of topologically correct feature maps. Biological Cybernetics, 43:59–69, 1982.
R. Linsker. How to generate ordered maps by maximizing the mutual information between input and output. Neural Computation, 1(3):402–411, 1989.
W. H. Press, S. A. Teukolsky, W. T. Vetterling, and B. P. Flannery. Numerical Recipes in C, 2nd Edition. Cambridge University Press, 1992.
J. W. Sammon. A nonlinear mapping for data structure analysis. IEEE Trans. Comput., 18:401–409, 1969.
M. Schütz and J. Sprave. Application of parallel mixed-integer evolution strategies with mutation rate pooling. In L. J. Fogel, P. J. Angeline, and Th. Bück, editors, Evolutionary Programming V — Proc. Fifth Annual Conf. Evolutionary Programming (EP’96), pages 345–354, San Diego CA, 1996. The MIT Press, Cambridge MA.
H.-P. Schwefel. Evolution and Optimum Seeking. Sixth-Generation Computer Technology. Wiley, New York, 1995.
J. Sprave. Linear neighborhood evolution strategy. In A. V. Sebald and L. J. Fogel, editors, Proc. Third Annual Conf. Evolutionary Programming (EP’94), pages 42–51, San Diego, CA, 1994. World Scientific, Singapore.
W. S. Torgerson. Multidimensional scaling: I. theory and method. Psychometrika, 17:401–419, 1952.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 1999 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Garionis, R. (1999). Quantifying Neighborhood Preservation: Joint Properties of Evolutionary and Unsupervised Neural Learning. In: McKay, B., Yao, X., Newton, C.S., Kim, JH., Furuhashi, T. (eds) Simulated Evolution and Learning. SEAL 1998. Lecture Notes in Computer Science(), vol 1585. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-48873-1_14
Download citation
DOI: https://doi.org/10.1007/3-540-48873-1_14
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-65907-5
Online ISBN: 978-3-540-48873-6
eBook Packages: Springer Book Archive