M. Ohta et al., BINARY NEURAL-NETWORK WITH NEGATIVE SELF-FEEDBACK AND ITS APPLICATIONTO N-QUEENS PROBLEM, IEICE transactions on information and systems, E77D(4), 1994, pp. 459-465
This article deals with the binary neural network with negative self-f
eedback connections as a method for solving combinatorial optimization
problems. Although the binary neural network has a high convergence s
peed, it hardly searches out the optimum solution, because the neuron
is selected randomly at each state update. In this article, an improve
ment using the negative self-feedback is proposed. First it is shown t
hat the negative self-feedback can make some local minimums be unstabl
e. Second a selection rule is proposed and its property is analyzed in
detail. In the binary neural network with negative self-feedback, thi
s selection rule is effective to escape a local minimum. In order to c
onfirm the effectiveness of this selection rule, some computer simulat
ions are carried out for the N-Queens problem. For N = 256, the networ
k is not caught in any local minimum and provides the optimum solution
within 2654 steps (about 10 minutes).