Patent
1990-02-06
1992-07-28
Fleming, Michael R.
395 23, G06F 1500
Patent
active
051346850
ABSTRACT:
The present invention is a node for a network that combines a Hopfield and Tank type neuron, having a sigmoid type transfer function, with a nonmonotonic neuron, having a transfer function such as a parabolic transfer function, to produce a neural node with a deterministic chaotic response suitable for quickly and globally solving optimizatioin problems and avoiding local minima. The node can be included in a completely connected single layer network. The Hopfield neuron operates continuously while the nonmonotonic neuron operates periodically to prevent the network from getting stuck in a local optimum solution. The node can also be included in a local area architecture where local areas can be linked together in a hierarchy of nonmonotonic neurons.
REFERENCES:
patent: 4660166 (1987-04-01), Hopfield
patent: 4897811 (1990-01-01), Scofield
patent: 4901271 (1990-02-01), Graf
Holler et al., "An Electrically Trainable Artificial Neural Network (ETANN) with 10290 `Floating Gate` Synapses", Proceedings of the International Annual Conference on Neural Networks, 1989, pp. 11-191-11-196.
S. Kirkpatrick, C. D. Gettatt, Jr., M. P. Vecchi, "Optimization by Simulated Annealing", Science May 13, 1983, vol. 220, No. 4598, pp. 671-680.
D. S. Johnson, C. R. Aragon, L. A. McGeoch, C. Schevon, "Optimization by Simulated Annealing: An Experimental Evaluation (Part I)", pp. 1-48.
H. Sompolinsky and A. Crisanti, "Chaos in Random Neural Networks", Physical Review Letters, vol. 61, No. 3, Jul. 18, 1988, pp. 259-262.
S. R. White, "Concepts of Scale In Simulated Annealing", IEEE, 1984, pp. 646-651.
D. H. Ackley, G. E. Hinton & T. J. Sejnowski, "A learning algorithm for Boltzmann machines", Cognitive Science 9:147-169, pp. 635-649.
C. Grebogi, E. Ott, J. A. Yorke, "Chaos, Strange Attractors, and Fractal Basin Boundaries in Nonlinear Dynamics", Science, vol. 238, Oct. 1987, pp. 634-637.
J. P. Eckmann, "Roads to turbulence in dissipative dynamical systems", Reviews of Modern Physics, vol. 53, No. 4, Part 1, Oct. 1981, pp. 643-654.
E. Ott, "Strange attractors and chaotic motions of dynamical systems", Rev. Mod. Phys., vol. 53, No. 4, Part 1, Oct. 1981, pp. 655-671.
J. J. Hopfield & D. W. Tank, "Computing with Neural Circuits: A Model", Science, vol. 233, Aug. 8, 1986, pp. 625-633.
Yaser S. Abu-Mostafa & Jeannine-Marie St. Jacques, "Information Capacity of the Hopfield Model", IEEE Transactions on Theory, vol. IT-31, No. 4, Jul. 1985, pp. 461-464.
D. S. Ornstein, "Ergodic Theory, Randomness, and Chaos", Science vol. 24, Jan. 13, 1989, pp. 182-186.
J. J. Hopfield, "Neural networks and physical systems with emergent collective computational abilities", Proc. Natl. Acad. Sci. USA, vol. 79, pp. 2334-2338.
J. J. Hopfield and D. W. Tank, "Neural Computation of Decisions in Optimization Problems", Biological Cybernetics, 1985, pp. 141-152.
S. Kirkpatrick, C. D. Gelatt, Jr., and M. P. Vecchi, "Optimization By Simulated Annealing", pp. 1-52.
J. J. Hopfield, "Neurons with graded response have collective computational properties like those of two-state neurons", Proc. Natl. Acad. Sci. USA, vol. 81, pp. 3088-3092.
P. Smolensky, "Information Processing in Dynamical Systems: Foundations of Harmony Theory", Parallel Distributed Processing, vol. 1, pp. 194-317.
Downs Robert W.
Fleming Michael R.
Sutcliff W. G.
Westinghouse Electric Corp.
LandOfFree
Neural node, a netowrk and a chaotic annealing optimization meth does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with Neural node, a netowrk and a chaotic annealing optimization meth, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Neural node, a netowrk and a chaotic annealing optimization meth will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-1692457