Abstract
Multiply connected analogue electronic circuits (‘neural’ nets) are characterised by having a large number of simple processing nodes such as threshold or summing devices which are connected to many other nodes through weighted interconnects. Under certain conditions the transient and equilibrium behaviour of these nets can be described in terms of a stability or Lyapunov function which is minimised at the equilibrium conditions of the net. This paper describes a circuit which is capable of solving ill-posed problems through use of an informational entropy regulariser which is incorporated into the stability function of the net. A circuit has been constructed which provides maximum entropy solutions to the loaded dice problem. The performance in terms of accuracy and speed of such circuits is discussed.
Keywords
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
For example, ‘Proceedings of the First International Conference on Neural Nets’ ed. M. Caudhill & C. Butler, IEEE, 1987.
J.J. Hopfield Proc. Nat. Acad. Sci. USA, 79, p. 2554, 1982.
J.J. Hopfield & D.W. Tank, Biological Cybern., 52, p. 141, 1985.
D.W. Tank & J.J. Hopfield, IEEE Trans. on Circ. and Sys., CAS-33, #5, p. 533, 1986.
T.J. Sejnowski & C.R. Rosenberg in ‘Neurocomputing’ ed. J.A. Anderson & E. Rosenfeld, MIT Press, Cambridge MA, 1988.
Y.C. Pati, D. Friedman, P.S. Krishnaprasad, C.T. Yao, M.C. Peckerar, R. Yang and C.R.K. Marrian, ‘Neural Networks for Tactile Perception’, Proc. IEEE Automation and Robotics Conference, Philadelphia PA, 1988.
C.R.K. Marrian and M.C. Peckerar, ‘Electronic “Neural” Net Algorithm for Maximum Entropy Solutions of Ill-posed Problems’, to appear in IEEE Trans. on Circuits and Systems.
J. Skilling, ‘The axiom of Maximum Entropy’ presented at 1986 Maximum Entropy Workshop, Seattle WA, 1986.
‘E.T. Jaynes: Papers on Probability Statistics and Statistical Physics’, p. 39 & 211, ed. R.D. Rosenkrantz, D. Reidel, Dordrecht, Holland, 1983.
C.R.K. Marrian, I. Mack, C. Banks & M.C. Peckerar, to be published.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 1989 Springer Science+Business Media Dordrecht
About this chapter
Cite this chapter
Marrian, C.R.K., Peckerar, M.C., Mack, I.A., Pati, Y.C. (1989). Electronic ‘Neural’ Nets for Solving Ill-Posed Problems with an Entropy Regulariser. In: Skilling, J. (eds) Maximum Entropy and Bayesian Methods. Fundamental Theories of Physics, vol 36. Springer, Dordrecht. https://doi.org/10.1007/978-94-015-7860-8_38
Download citation
DOI: https://doi.org/10.1007/978-94-015-7860-8_38
Publisher Name: Springer, Dordrecht
Print ISBN: 978-90-481-4044-2
Online ISBN: 978-94-015-7860-8
eBook Packages: Springer Book Archive