Learning to Generalize from Single Examples in the Dynamic Link Architecture

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 where significant relations in the input pattern are recognized and expressed by the unsupervised self-organization of dynamic links. The power of this mechanism is due to the very general a priori principle of conservation of topological structure. We demonstrate that style with a system that learns to classify mirror symmetric pixel patterns from single examples.

[1]  F. Crick.  Function of the thalamic reticular complex: the searchlight hypothesis. , 1984, Proceedings of the National Academy of Sciences of the United States of America.

[2]  Elie Bienenstock,et al.  A neural network for invariant pattern recognition. , 1987 .

[3]  J. L. Hodges,et al.  Discriminatory Analysis - Nonparametric Discrimination: Consistency Properties , 1989 .

[4]  Joachim M. Buhmann,et al.  Object recognition with Gabor functions in the dynamic link architecture , 1992 .

[5]  Wolfgang Konen,et al.  A fast dynamic link matching algorithm for invariant pattern recognition , 1994, Neural Networks.

[6]  Geoffrey E. Hinton,et al.  Learning symmetry groups with hidden units: beyond the perceptron , 1986 .

[7]  D. Signorini,et al.  Neural networks , 1995, The Lancet.

[8]  Anthony C. C. Coolen,et al.  A learning mechanism for invariant pattern recognition in neural networks , 1989, Neural Networks.

[9]  B Julesz,et al.  Experiments in the visual perception of texture. , 1975, Scientific American.

[10]  Bart Kosko,et al.  Neural networks and fuzzy systems: a dynamical systems approach to machine intelligence , 1991 .

[11]  J D Delius,et al.  Visual symmetry recognition by pigeons , 1982, Psychological research.

[12]  Michael C. Corballis,et al.  On the perception of symmetrical and repeated patterns , 1974 .

[13]  C. Gross,et al.  Perception of symmetry in infancy. , 1981 .

[14]  H. Barlow,et al.  The versatility and absolute efficiency of detecting mirror symmetry in random dot displays , 1979, Vision Research.

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

[16]  H. Kalmus.  Biological Cybernetics , 1972, Nature.

[17]  Christoph von der Malsburg,et al.  The Correlation Theory of Brain Function , 1994 .

[18]  J. Orbach.  Principles of Neurodynamics. Perceptrons and the Theory of Brain Mechanisms. , 1962 .

[19]  C. Malsburg,et al.  How patterned neural connections can be set up by self-organization , 1976, Proceedings of the Royal Society of London. Series B. Biological Sciences.

[20]  J. Kellett.  London , 1914, The Hospital.

[21]  Geoffrey E. Hinton,et al.  Learning representations by back-propagating errors , 1986, Nature.

[22]  V S Ramachandran,et al.  Perceiving shape from shading. , 1988, Scientific American.

[23]  Jin Ho Kim,et al.  Distortion-Invariant Object Recognition by Optimization Neural Network , 1990 .

[24]  W. Singer,et al.  Oscillatory responses in cat visual cortex exhibit inter-columnar synchronization which reflects global stimulus properties , 1989, Nature.

[25]  Joachim M. Buhmann,et al.  Distortion Invariant Object Recognition in the Dynamic Link Architecture , 1993, IEEE Trans. Computers.

[26]  Christoph von der Malsburg,et al.  Pattern recognition by labeled graph matching , 1988, Neural Networks.

[27]  C. von der Malsburg,et al.  Distortion invariant object recognition by matching hierarchically labeled graphs , 1989, International 1989 Joint Conference on Neural Networks.

[28]  J. Russell.  Developmental psychology , 1980, Nature.

[29]  Geoffrey E. Hinton,et al.  A Learning Algorithm for Boltzmann Machines , 1985, Cogn. Sci..

[30]  Geoffrey E. Hinton,et al.  Learning representations by back-propagation errors, nature , 1986 .

[31]  Peter E. Hart,et al.  Nearest neighbor pattern classification , 1967, IEEE Trans. Inf. Theory.