Abstract
A large attraction of neural systems lies in their promise of replacing programming by learning. A problem with many current neural models is that, with realistically large input patterns, learning time explodes. This is a problem inherent in a notion of learning that is based almost entirely on statistical estimation. We propose here a different learning style, wherein significant relations in the input patterns are recognized and expressed by the unsupervised self-organization of dynamic links. The power of this mechanism is due to the very general a prioriprinciple of conservation of topological structure. We demonstrate that style with a system that learns to classify mirror symmetric pixel patterns from single examples.
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
Ackley DH, Hinton GE, Sejnowski TS (1985) A learning algorithm for Boltzmann machines. Cogn Sci 9:147–149
Barlow HB, Reeves BC (1979) The versatility and absolute efficiency of detecting mirror symmetry in random dot display. Vision Res 19:783–793
Bienenstock E, von der Malsburg C (1987) A neural network for invariant pattern recognition. Europhysics Lett 4:121–126
Bomstein MH, Ferdinandsen K, Gross CG (1981) Perception of symmetry in infancy. Devel Psychol 17:82–86
Buhmann J, Lange J, von der Malsburg C (1989) Distortion invariant object recognition by matching hierarchically labeled graphs. In: IJCNN International Conference on Neural Networks, Washington, pages I 155–159. IEEE
Buhmann J, Lange C, von der Malsburg C, Vorbrüggen JC, Würtz RP (1991) Object recognition in the dynamic link architecture—parallel implementation on a transputer network. In: Kosko B, (ed) Neural networks: a dynamical systems approach to machine intelligence. Prentice Hall, New York
Corballis MC, Roldan CE (1974) On the perception of symmetrical and repeated patterns. Perception Psychophysics 16:136–142
Cover TM, Hart PE (1967) Nearest neighbor pattern classification. IEEE Transactions on Information Theory IT-13:21–27
Crick F (1984) Function of the thalamic reticular complex: the searchlight hypothesis. Proc Natl Acad Sci 81:4586–4590
Delius JD, Nowak B (1982) Visual symmetry recognition by pigeons. Psychol Res 44:199–212
Eckhorn R, Bauer R, Jordan W, Brosch M, Kruse W, Munk M, Reitboeck H (1988) Coherent oscillations: A mechanism of feature linking in the visual cortex? Biol Cybernetics 60:121–130
Fix E, Hodges JL (1951) Discriminatory analysis, non-parametric discrimination. Technical report, USAF School of Aviation Medicine, Project 21-49-004, Rept 4
Gray CM, König P, Engel AK, Singer W (1989) Oscillatory responses in cat visual cortex exhibit inter-columnar synchronization which reflects global stimulus properties. Nature 338:334–337
Julesz B (1975) Experiments in the visual perception of texture. Sci Ainer 232:34–44
Kohonen T, Barna G, Chrisely R (1988) Statistical pattern recognition with neural networks: benchmarking studies. Proceedings of the IEEE ICNN, San Diego 61–76
Lades M, Vorbrüggen JC, Buhmann J, Lange J, von der Malsburg C, Würtz RP, Konen W (1993) Distortion invariant object recognition in the dynamic link architecture. IEEE Transaction on Computers 300–311
Ramachandran V (1988) Perceiving shape from shading. Sci Amer 10:76–83
Reilly DL, Cooper LN, Elbaum C (1982) A neural model for category learning. Biol Cybernetics 45:35–41
Rosenblatt F (1962) Principles of neurodynamics: perceptrons and the theory of brain mechanisms. Spartan Books, Washington, DC
Rumelhart DE, Hinton GE, Williams RJ (1986) Learning representations by backpropagating errors. Nature 323:533–536
Schneider W (1986) Anwendung der Korrelationstheorie der Hirnfunktion auf das akustische Figur-Hintergrund-Problem (Cocktailparty-Effekt). Ph. D. Thesis, Universität Göttingen
Sejnowski TJ, Kienker PK, Hinton GE (1986) Learning symmetry groups with hidden units: Beyond the perceptron. Physica, 22D: 260–275
von der Malsburg C (1981) The correlation theory of brain function. Internal report, 81–2, Max-Planck-Institut für Biophysikalische Chemie
von der Malsburg C (1988) Pattern recognition by labeled graph matching. Neural Networks 1:141–148
von der Malsburg C, Buhmann J (1992) Sensory segmentation with coupled neural oscillators. Biol Cybernetics 67:233–242
Willshaw DJ, von der Malsburg C (1976) How patterned neural connections can be set up by self-organization. Proc Roy Soc London B194:431–445
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 1994 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Konen, W., von der Malsburg, C. (1994). Learning to Generalize from Single Examples in Dynamic Link Architecture. In: Buzsáki, G., Llinás, R., Singer, W., Berthoz, A., Christen, Y. (eds) Temporal Coding in the Brain. Research and Perspectives in Neurosciences. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-85148-3_12
Download citation
DOI: https://doi.org/10.1007/978-3-642-85148-3_12
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-85150-6
Online ISBN: 978-3-642-85148-3
eBook Packages: Springer Book Archive