Large machine-part family formation utilizing a parallel ART1 neural network

Abstract

The binary adaptive resonance (ART1) neural network algorithm has been successfully implemented in the past for the classifying and grouping of similar vectors from a machine-part matrix. A modified ART1 paradigm which reorders the input vectors, along with a modified procedure for storing a group's representation vectors, has proven successful in both speed and functionality in comparison to former techniques. This paradigm has been adapted and implemented on a neuro-computer utilizing 256 processors which allows the computer to take advantage of the inherent parallelism of the ART1 algorithm. The parallel implementation results in tremendous improvements in the speed of the machine-part matrix optimization. The machine-part matrix was initially limited to 65,536 elements (256×256) which is a consequence of the maximum number of processors within the parallel computer. The restructuring and modification of the parallel implementation has allowed the number of matrix elements to increase well beyond their previous limits. Comparisons of the modified structure with both the serial algorithm and the initial parallel implementation are made. The advantages of using a neural network approach in this case are discussed.