Design of basic hardware gates for efficient fuzzy computing

In this paper we present proposals for VLSI implementation of some basic fuzzy circuits (called fuzzy-gates), intensive use of which is of help in the design of complex fuzzy computation systems. We decided to use an analog approach with quantified magnitudes, the value of which is immune to error as it is regenerated by each gate. The discrete analog approach chosen combines the advantages of digital technology (regeneration of signals at each gate) with those of analog technology (a reduced number of lines to transport information). As the fuzzy-gates proposed use a CMOS technology similar to that of the digital approach, they share the performance of the latter as far as dissipated power is concerned