An execution system of logic programming language using neural networks - An improvement of the transformation algorithm

In this paper, we propose an execution system of logic programming language using neural networks. We transform the style like logic programming language into Hopfield-type neural network and attempt to execute logic programming language using the ability of neural network as optimization machine. Although we have proposed a such system, previous works are not implemented "list processing". Therefore we propose an improved transformation algorithm for "list processing". A performance of the new transformation algorithm is evaluated by comparing with a previous algorithm, without handling list structure, for logic programming language, The result shows that the proposed algorithm generates especially smaller network scale than conventional algorithm, and reduces iteration times.