VLSI implementation of fuzzy adaptive resonance and learning vector quantization

Abstract

We present a mixed-mode VLSI chip performing unsupervised clustering and classification, implementing models of fuzzy adaptive resonance theory (ART) and learning vector quantization (LVQ), and extending to variants such as Kohonen self-organizing maps (SOM). The parallel processor classifies analog vectorial data into a digital code in a single clock, and implements on-line learning of the analog templates, stored locally and dynamically using the same adaptive circuits for on-chip quantization and refresh. The unit cell performing fuzzy choice and vigilance functions, adaptive resonance learning and long-term analog storage, measures 71 /spl mu/m/spl times/71 /spl mu/m in 2 /spl mu/m CMOS. Experimental learning results are included from a 16-input, 16-category prototype on a 2.2 mm/spl times/2.2 mm chip, operating at 10 ksample/s parallel data rate and 2 mW power dissipation.