Special purpose neurocomputer system for solving optimization problems

作者: Peter R. Conwell

DOI:

关键词: Set (abstract data type)Optimization problemState (computer science)MathematicsCross connectionTime delayedArithmetic

摘要: A network of N parallel processors are each one cross-connected to other. Each cross connection includes a nodal weight delay circuit which carries status information as whether processor is "on" (=1) or "off" (=0) and its weighted influence (wij) excitatory inhibitory between the two i j on that connection. Additionally, time delayed with selectively fixed set machine cycles any j. monitoring processor-controller senses when majority have achieved stable non-changing state will represent an optimum solution for combinatorial problem.

参考文章(9)
Gaines Brian Ronald, Andreae John Hugh, White Peter, Network using adaptive elements ,(1967)
G. PALM, Computing with neural networks. Science. ,vol. 235, pp. 1226- 1228 ,(1987) , 10.1126/SCIENCE.235.4793.1227B
J. J. Hopfield, Neural networks and physical systems with emergent collective computational abilities Proceedings of the National Academy of Sciences of the United States of America. ,vol. 79, pp. 2554- 2558 ,(1982) , 10.1073/PNAS.79.8.2554
Charles V Jakowatz, Self-adapting neuron ,(1961)
Leon N. Cooper, Charles Elbaum, Information processing system ,(1974)