Title :
Knapsack packing networks
Author :
Hellstrom, Benjamin J. ; Kanal, Laveen N.
Author_Institution :
Westinghouse Electr. Corp., Baltimore, MD, USA
fDate :
3/1/1992 12:00:00 AM
Abstract :
A knapsack packing neural network of 4n units with both low-order and conjunctive asymmetric synapses is derived from a non-Hamiltonian energy function. Parallel simulations of randomly generated problems of size n in {5, 10, 20} are used to compare network solutions with those of simple greedy fast parallel enumerative algorithms
Keywords :
computational complexity; neural nets; optimisation; computational complexity; conjunctive asymmetric synapses; knapsack packing neural network; nonHamiltonian energy function; optimisation; parallel simulation; simple greedy fast parallel enumerative algorithms; Artificial neural networks; Computer networks; Concurrent computing; Hopfield neural networks; Hypercubes; Neural networks; Optimization methods; Space exploration; Stability; Traveling salesman problems;
Journal_Title :
Neural Networks, IEEE Transactions on
