Geometric neural computing

This paper shows the analysis and design of feedforward neural networks using the coordinate-free system of Clifford or geometric algebra. It is shown that real-, complex-, and quaternion-valued neural networks are simply particular cases of the geometric algebra multidimensional neural networks and that some of them can also be generated using support multivector machines (SMVMs). Particularly, the generation of radial basis function for neurocomputing in geometric algebra is easier using the SMVM, which allows one to find automatically the optimal parameters. The use of support vector machines in the geometric algebra framework expands its sphere of applicability for multidimensional learning. Interesting examples of nonlinear problems show the effect of the use of an adequate Clifford geometric algebra which alleviate the training of neural networks and that of SMVMs.

[1]  George Cybenko,et al.  Approximation by superpositions of a sigmoidal function , 1992, Math. Control. Signals Syst..

[2]  Roger Y. Tsai,et al.  A versatile camera calibration technique for high-accuracy 3D machine vision metrology using off-the-shelf TV cameras and lenses , 1987, IEEE J. Robotics Autom..

[3]  Eduardo Bayro Corrochano,et al.  Applications of Lie Algebras and the Algebra of Incidence , 2001 .

[4]  Cris Koutsougeras,et al.  Complex domain backpropagation , 1992 .

[5]  Chris Doran,et al.  Geometric algebra and its application to mathematical physics , 1994 .

[6]  D. Hestenes,et al.  Clifford Algebra to Geometric Calculus , 1984 .

[7]  Joseph N. Wilson,et al.  Handbook of computer vision algorithms in image algebra , 1996 .

[8]  Luigi Fortuna,et al.  Chaotic time series prediction via quaternionic multilayer perceptrons , 1995, 1995 IEEE International Conference on Systems, Man and Cybernetics. Intelligent Systems for the 21st Century.

[9]  P. Arena,et al.  Quaternionic Multilayer Perceptrons for Chaotic Time Series Prediction , 1996 .

[10]  Kurt Hornik,et al.  Multilayer feedforward networks are universal approximators , 1989, Neural Networks.

[11]  David Hestenes,et al.  Space-time algebra , 1966 .

[12]  I. Porteous.  Cli ord Algebras and the Classical Groups , 1995 .

[13]  Eduardo Bayro-Corrochano,et al.  Selforganizing Clifford neural network , 1996, Proceedings of International Conference on Neural Networks (ICNN'96).

[14]  Paulo J. G. Lisboa,et al.  Translation, rotation, and scale invariant pattern recognition by high-order neural networks and moment classifiers , 1992, IEEE Trans. Neural Networks.

[15]  David Hestenes,et al.  Invariant body kinematics: I. Saccadic and compensatory eye movements , 1994, Neural Networks.

[16]  Vladimir Vapnik,et al.  Statistical learning theory , 1998 .

[17]  David Hestenes,et al.  Old Wine in New Bottles: A New Algebraic Framework for Computational Geometry , 2001 .

[18]  James L. McClelland,et al.  James L. McClelland, David Rumelhart and the PDP Research Group, Parallel distributed processing: explorations in the microstructure of cognition . Vol. 1. Foundations . Vol. 2. Psychological and biological models . Cambridge MA: M.I.T. Press, 1987. , 1989, Journal of Child Language.

[19]  F. Girosi,et al.  Networks for approximation and learning , 1990, Proc. IEEE.

[20]  D. Hestenes,et al.  Clifford Algebra to Geometric Calculus: A Unified Language for Mathematics and Physics , 1984 .

[21]  Reinhard Klette,et al.  Computer vision - three-dimensional data from images , 1998 .

[22]  David Hestenes.  Invariant body kinematics: II. Reaching and neurogeometry , 1994, Neural Networks.

[23]  Azriel Rosenfeld,et al.  Computer Vision , 1988, Adv. Comput..

[24]  A. Pellionisz,et al.  Tensorial approach to the geometry of brain function: Cerebellar coordination via a metric tensor , 1980, Neuroscience.

[25]  J. P..  Lectures on Quaternions , 1897, Nature.

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

[27]  J. Koenderink.  The brain a geometry engine , 1990, Psychological research.