Neural-network dedicated processor for solving assignment proble

Details Neural-network dedicated processor for solving assignment proble Neural-network dedicated processor for solving assignment proble

1991-08-12

1993-03-16

MacDonald, Allen R.

395 11, 395 23, G06F 1518

Patent

active

051951703

ABSTRACT:
A neural network processor for solving first-order competitive assignment problems consists of a matrix of N.times.M processing units, each of which corresponds to the pairing of a first number of elements of {R.sub.i } with a second number of elements {C.sub.j }, wherein limits of the first number are programmed in row control superneurons, and limits of the second number are programmed in column superneurons as MIN and MAX values. The cost (weight) W.sub.ij of the pairings is programmed separately into each PU. For each row and column of PUs, a dedicated constraint superneuron insures that the number of active neurons within the associated row or column fall within a specified range. Annealing is provided by gradually increasing the PU gain for each row and column or increasing positive feedback to each PU, the latter being effective to increase hysteresis of each PU or by combining both of these techniques.

REFERENCES:
patent: 3134017 (1964-05-01), Burhans et al.
patent: 4660166 (1987-04-01), Hopfield
patent: 4866645 (1989-09-01), Lish
patent: 5016188 (1991-05-01), Lan
patent: 5047655 (1991-09-01), Chambost et al.
Majani, et al., "On the K-Winners-Take-All Network," Advances in Neural Network Information Systems 1, D. Touretzky, ed., pp. 634-642, Palo Alto, Calif., Morgan Kaufman Publishers, Inc. 1989).
Brown, et al., "Neural Network Design of a Banyan Network Controller," IEEE Journal of Selected Areas in Communication, vol. 8, No. 8, pp. 1428-1438, (1991).
Moopenn, et al., "A Neural Network for Euclidian Distance Minimization," Proc. IEEE, Intl. Conf. on Neural Networks, vol. II, pp. 349-356, San Diego, Calif., Jul. 24-27, (1988).
J. Munkres, "Algorithms for the Assignment and Transportation Problems," Journal of the Society for Industrial Applications of Mathematics, vol. 5, No. 1, pp. 32-38, (1957).
S. Blackman, "Multiple-Target Tracking with Radar Applications," Artech House Inc., Norwood, Mass., pp. 397-403, (1986).
Hopfield, et al., "Neural Computation of Decisions in Optimization Problems," Biol. Cybern., 52:147-152, (1985).
Tagliarini, et al., "A Neural-Network Solution to the Concentrator Assignment Problem," Proc. IEEE Conf. on Neural Information Processing Systems-Natural and Synthetic (1988).
Kirkpatrick, et al., "Optimization by Simulated Annealing," Science, vol. 220, pp. 670-680, (1983).
Bilbro, et al., "Optimization by Mean Field Annealing," Advances in Neural Information Processing Systems 1, Touretzky, ed., Morgan, Kaufman Publishers, Inc., pp. 91-98, (1989).
Peng, et al., "A Connectionist Model for Diagnostic Problem Solving," IEEE Trans. on Systems, Man and Cybernetics, vol. 19, No. 2, pp. 285-289, (1989).
Saeckinger, et al., "A Versatile Building Block: The CMOS Differential Difference Amplifier," IEEE J. Solid-State Circuits, SC-22, No. 2, pp. 287-294, Apr. 1987.
Lazzaro, et al., "Winner-Take-All Networks of O(N) Complexity," Technical Report Caltech-CS-TR-21-88, California Institute of Technology 1988.
Analog Devices, "1990/91 Linear Products Databook," Analog Devices, Inc., 1990, p. 4-61.
Hillier et al., Introduction to Operations Research, Fourth Edition, Holden-Day, Inc., 1986, p. 217.

Affiliated with

Also associated with

Rating

Neural-network dedicated processor for solving assignment proble 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-network dedicated processor for solving assignment proble, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Neural-network dedicated processor for solving assignment proble will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFUS-PAI-O-357126