Y. Watanabe et al., SOLVING COMBINATORIAL OPTIMIZATION PROBLEMS USING THE OSCILLATORY NEURAL-NETWORK, IEICE transactions on information and systems, E80D(1), 1997, pp. 72-77
The Hopfield neural network for optimization problems often falls into
local minima. To escape from the local minima. the neuron unit in the
neural network is modified to become an oscillatory unit by adding a
simple self-feedback circuit. By combining the oscillatory unit with a
n energy-value extraction circuit, an oscillatory neural network is co
nstructed. The network can repeatedly extract solutions, and can simul
taneously evaluate them. In this paper, the network is applied to four
NP-complete problems to demonstrate its generality and efficiency. Th
e network can serve each problem and can obtain better solutions than
the original Hopfield neural network and simple algorithms.