The Community for Technology Leaders
Green Image
<p>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.</p>

M. Verleysen, P. Thissen, J. Madrenas and J. Voz, "An Analog Processor Architecture for a Neural Network Classifier," in IEEE Micro, vol. 14, no. , pp. 16-28, 1994.
91 ms
(Ver 3.3 (11022016))