Mapping fuzzy clustering neural networks onto systolic arrays
David D. Zhang, Mohamed S. Kamel, M.I. Elmasry · 1994
In this paper, the implementation of fuzzy clustering neural networks (NN), based on systolic arrays (SA), is explored. Mapping policies from NN to SA are established and some typical SA structures are developed. We illustrate our approach using a mapping of the topology extracted front two fuzzy clustering NNs onto its corresponding SA architecture along with a discussion of data flow and processing element definition in the SA.>