An analog processor architecture for a neural network classifier

Author

Verleysen, Michel ; Thissen, Philippe ; Voz, Jean-Luc ; Madrenas, Jodi

Author_Institution

Katholieke Univ., Leuven, Belgium

Volume

14

Issue

3

fYear

1994

fDate

6/1/1994 12:00:00 AM

Firstpage

16

Lastpage

28

Abstract

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.<>

Keywords

analogue computer circuits; analogue processing circuits; learning (artificial intelligence); neural chips; neural nets; parallel architectures; pattern recognition; LVQ-like procedures; analog processor architecture; classification; functions densities; generic analog chip; neural network classifier; neural-like algorithms; portable classification system; probability densities; Analog computers; Classification algorithms; Image recognition; Neural networks; Optical signal processing; Partitioning algorithms; Portable computers; Shape; Signal processing algorithms; Vector quantization;

fLanguage

English

Journal_Title

Micro, IEEE

Publisher

ieee

ISSN

0272-1732

Type

jour

DOI

10.1109/40.285221

Filename

285221