ASYMMETRIC NEURAL-NETWORK AND ITS APPLICATION TO KNAPSACK-PROBLEM

We propose an asymmetric neural network which can solve inequality-con strained combinatorial optimization problems that are difficult to sol ve using symmetric neural networks. In this article, a knapsack proble m that is one of such the problem is solved using the proposed network . Additionally, we study condition for obtaining a valid solution. In computer simulations, we show that the condition is correct and that t he proposed network produces better solutions than the simple greedy a lgorithm.