A parallel sorting algorithm based on harmony theory neural networks

This paper presents a parallel sorting algorithm based on neural network derived from the harmony theory neural networks. The nodes of the proposed neural network are connected in an incomplete way, and the connections between the nodes are greatly reduced. It has the advantage of simple in function and easy for hardware implementation. At the same time, the proposed sorting algorithm, different from other artificial neural network based sorting schemes, does not need any pre-processing for the data to be sorted, and the sorting operation can be terminated automatically in a finite number of steps. The proposed sorting algorithm has the characteristics of simple in function and structure as well as transparent and rapid in operation.(1)