Identification of pattern dimensionality by self-organization

In computational models of the human brain, beneath the symbolic-type reasoning modelled by logic-based formalisms, there is another level of computation. It is implemented in a sub-symbolic substrate, in which operations are carried out by local interactions of simple computing elements, without any central guidance. Such a substrate is apparent in perception. In this paper, we show how a distributed, sub-symbolic organization can be usefully employed in pattern recognition. We present a self-organizing model that automatically learns the topology of an input space based on samples drawn from that space. Experiments are carried out to show that such a model can build a template to be used for character recognition, by autonomously inferring the essential topological features from a set of character images.

[1]  G. B. M..  Principia Mathematica , 1911, Nature.

[2]  M. Ohlsson.  Extensions and explorations of the elastic arms algorithm , 1993 .

[3]  Bernard Widrow,et al.  The "rubber-mask" technique-II. Pattern storage and recognition , 1973, Pattern Recognit..

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

[5]  Bernard Widrow,et al.  The "rubber-mask" technique - I. Pattern measurement and analysis , 1973, Pattern Recognit..

[6]  Richard Durbin,et al.  An analogue approach to the travelling salesman problem using an elastic net method , 1987, Nature.

[7]  Teuvo Kohonen,et al.  The self-organizing map , 1990 .

[8]  Lawrence D. Jackel,et al.  Backpropagation Applied to Handwritten Zip Code Recognition , 1989, Neural Computation.

[9]  R. F. Thompson,et al.  The search for the engram. , 1976, The American psychologist.

[10]  Donald Geman,et al.  Stochastic Relaxation, Gibbs Distributions, and the Bayesian Restoration of Images , 1984, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[11]  Bruce J. MacLennan,et al.  Field Computation in the Brain , 1992 .

[12]  Bruce J. MacLennan,et al.  Flexible Computing in the 21st Century , 1991 .

[13]  Helge J. Ritter,et al.  Three-dimensional neural net for learning visuomotor coordination of a robot arm , 1990, IEEE Trans. Neural Networks.

[14]  Bruce J. MacLennan,et al.  Characteristics of connectionist knowledge representation , 1991, Inf. Sci..

[15]  A. Pellionisz,et al.  Tensor network theory of the metaorganization of functional geometries in the central nervous system , 1985, Neuroscience.

[16]  R. Shepard,et al.  Turning something over in the mind. , 1984, Scientific American.

[17]  R. Shepard,et al.  Mental Rotation of Three-Dimensional Objects , 1971, Science.

[18]  Helge Ritter,et al.  Learning with the Self-Organizing Map , 1991 .

[19]  S. Havlin,et al.  Fractals and Disordered Systems , 1991 .

[20]  D Marr,et al.  Cooperative computation of stereo disparity. , 1976, Science.

[21]  S. Grossberg,et al.  ART 2: self-organization of stable category recognition codes for analog input patterns. , 1987, Applied optics.

[22]  Alan L. Yuille,et al.  Particle tracking by deformable templates , 1991, IJCNN-91-Seattle International Joint Conference on Neural Networks.

[23]  W. Boothby.  An introduction to differentiable manifolds and Riemannian geometry , 1975 .

[24]  H. Haken.  Cooperative phenomena in systems far from thermal equilibrium and in nonphysical systems , 1975 .

[25]  Jonathan A. Marshall,et al.  Self-organizing neural networks for perception of visual motion , 1990, Neural Networks.

[26]  E I Knudsen,et al.  Computational maps in the brain. , 1987, Annual review of neuroscience.

[27]  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.

[28]  W. Freeman,et al.  How brains make chaos in order to make sense of the world , 1987, Behavioral and Brain Sciences.