Graph color minimization using neural networks

The problem considered here is that of register allocation which has been shown to map to the non-planar graph coloring problem. Given a graph G, the problem is to color, or label, the vertices such that no two adjacent vertices are the same color. The neural network model presented also minimizes the number of colors used. This additional capability provides for a higher efficiency of resource usage as well as having application to other problems that map to graph coloring. Test results are compared with previous neural network techniques for graph coloring, and it is shown that this neural network model consistently will provide a significant reduction in the number of colors, or registers, required while maintaining a high convergence rate.