Patent
1991-11-08
1993-10-19
MacDonald, Allen R.
395 24, G06F 1546, G06G 712
Patent
active
052553493
ABSTRACT:
This invention is a novel high-speed neural network based processor for solving the "traveling salesman" and other global optimization problems. It comprises a novel hybrid architecture employing a binary synaptic array whose embodiment incorporates the fixed rules of the problem, such as the number of cities to be visited. The array is prompted by analog voltages representing variables such as distances. The processor incorporates two interconnected feedback networks, each of which solves part of the problem independently and simultaneously, yet which exchange information dynamically.
REFERENCES:
patent: 4660166 (1987-04-01), Hopfield
patent: 4807168 (1989-02-01), Moopenn et al.
patent: 4931763 (1990-06-01), Ramesham et al.
Goldstein, M., N. Toomarian, and J. Barhen, 1988. "A Comparison Study of Optimization Methods of the Bipartite Matching Problem (BMP)". IEEE conf. Neural Networks II-267, San Diego, Calif., Jul. 24-27, 1988.
Hopfield, J. and D. Tank, 1985. "Neural Computation of Decisions in Optimization Problems". Biol. Cybern. 52:147-152.
Moopenn A., A. Thakoor, and T. Duong, 1988. "A Neural Network for Euclidean Distance Minimization". Proc. IEEE conf. Neural Network II-349 San Diego, Calif., Jul. 24-27, 1988.
Duong Tuan A.
Eberhardt Silvio P.
Moopenn Alexander W.
Thakoor Anilkumar P.
Davis George
Jones Thomas H.
Kusmiss John H.
MacDonald Allen R.
Miller Guy M.
LandOfFree
Electronic neural network for solving "traveling salesman" and s does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with Electronic neural network for solving "traveling salesman" and s, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Electronic neural network for solving "traveling salesman" and s will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-1358642