An analog processor architecture for a neural network classifier
Michel Verleysen, Philippe Thissen, Jean-Luc Voz, Jordi Madrenas · IEEE Micro · 1994
Many neural-like algorithms currently under study support classification tasks. Several of these algorithms base their functionality on LVQ-like procedures to find locations of centroids in the data space, and on kernel (or radial-basis) functions centered on these centroids to approximate functions or probability densities. A generic analog chip could implement in a parallel way all basic functions found in these algorithms, permitting construction of a fast, portable classification system.>