An analog neural network solution to the inverse problem of 'early taction'

The authors examine an application of analog neural networks to low-level processing of tactile sensory data. In analogy to the term early vision, the authors call the first level of processing required in tactile sensing early taction. The problem of deblurring or deconvolution of data provided by an array of tactile sensors that is also assumed to be corrupted by noise is addressed. It is noted that this inverse problem is ill posed and that the technique of regularization may be used to obtain solutions. The theory of nonlinear electrical networks is utilized to describe energy functions for a class of nonlinear networks and to show that the equilibrium states of the proposed network correspond to regularized solutions of the deblurring problem. An entropy regularizer is incorporated into the energy function of the network for the recovery of normal stress distributions. An integrated circuit prototype of the proposed network is discussed. >

[1]  Demetri Psaltis,et al.  Optical Neural Computers , 1987, Topical Meeting on Optical Computing.

[2]  Richard P. Lippmann,et al.  An introduction to computing with neural nets , 1987 .

[3]  Colin Cherry M.Sc. A.M.I.E.E..  CXVII. Some general theorems for non-linear systems possessing reactance , 1951 .

[4]  Tomaso Poggio,et al.  Probabilistic Solution of Ill-Posed Problems in Computational Vision , 1987 .

[5]  R. Westervelt,et al.  Stability of analog neural networks with delay. , 1989, Physical review. A, General physics.

[6]  T. Matsumoto,et al.  Eventually passive nonlinear networks , 1977 .

[7]  S. Smale.  On the mathematical foundations of electrical circuit theory , 1972 .

[8]  T. Poggio,et al.  III-Posed problems early vision: from computational theory to analogue networks , 1985, Proceedings of the Royal Society of London. Series B. Biological Sciences.

[9]  John J. Hopfield,et al.  Simple 'neural' optimization networks: An A/D converter, signal decision circuit, and a linear programming circuit , 1986 .

[10]  Martin Peckerar,et al.  Neutral networks for tactile perception , 1988, Proceedings. 1988 IEEE International Conference on Robotics and Automation.

[11]  John M. Hollerbach,et al.  Basic Solid Mechanics for Tactile Sensing , 1984, ICRA.

[12]  Paolo Dario,et al.  Ferroelectric polymer tactile sensors with anthropomorphic features , 1984, ICRA.

[13]  C. Desoer,et al.  Trajectories of nonlinear RLC networks: A geometric approach , 1972 .

[14]  J. K. Moser,et al.  A theory of nonlinear networks. I , 1964 .

[15]  I. Gohberg,et al.  Basic Operator Theory , 1981 .

[16]  F.J. Kub,et al.  Architecture for large microelectronic supervised learning artificial neural networks using a hybrid digital-analog approach , 1988, Neural Networks.

[17]  S. Timoshenko,et al.  Theory of elasticity , 1975 .

[18]  Jin Luo,et al.  Computing motion using analog and binary resistive networks , 1988, Computer.

[19]  Tomaso Poggio,et al.  Computational vision and regularization theory , 1985, Nature.

[20]  Yagyensh C. Pati.  Neural Networks for Low Level Processing of Tactile Sensory Data , 1989 .

[21]  Roger W. Brockett.  Stability and control of grasping , 1986, Proceedings. 1986 IEEE International Conference on Robotics and Automation.

[22]  R. Yang.  Tactile Perception for Multifingered Hands , 1987 .

[23]  Lawrence D. Jackel,et al.  VLSI implementation of a neural network model , 1988, Computer.

[24]  A Tikhonov,et al.  Solution of Incorrectly Formulated Problems and the Regularization Method , 1963 .

[25]  I. A. Mack,et al.  Electronic ‘Neural’ Nets for Solving Ill-Posed Problems with an Entropy Regulariser , 1989 .

[26]  G. Wahba.  Ill Posed Problems: Numerical and Statistical Methods for Mildly, Moderately and Severely Ill Posed Problems with Noisy Data. , 1980 .

[27]  James J. Clark.  A magnetic field based compliance matching sensor for high resolution, high compliance tactile sensing , 1988, Proceedings. 1988 IEEE International Conference on Robotics and Automation.

[28]  T. Matsumoto,et al.  On several geometric aspects of nonlinear networks , 1976 .

[29]  W. Millar.  CXVI. Some general theorems for non-linear systems possessing resistance , 1951 .

[30]  H. D. Conway,et al.  Normal and shearing contact stresses in indented strips and slabs , 1966 .

[31]  Leon D. Harmon,et al.  Automated Tactile Sensing , 1982 .

[32]  Mark H. Lee,et al.  A Survey of Robot Tactile Sensing Technology , 1989, Int. J. Robotics Res..

[33]  D. B. Schwartz,et al.  Dynamics of microfabricated electronic neural networks , 1987 .

[34]  G. Wahba,et al.  Gcvpack – routines for generalized cross validation , 1987 .

[35]  W. Rudin.  Real and complex analysis , 1968 .

[36]  Demetri Terzopoulos,et al.  Multiresolution computation of visible-surface representations , 1984 .

[37]  T. Matsumoto,et al.  On the dynamics of electrical networks , 1976 .

[38]  J. Maxwell.  A Treatise on Electricity and Magnetism , 1873, Nature.