Cell-Stitching for Analog Neuromorphic Computing

Neuromorphic computing is an innovative paradigm aiming to unify storage and computation, thereby addressing the constraints imposed by the Von Neumann bottleneck. Within this domain, analog computing based on memristors as synaptic elements has emerged as a promising avenue, though achieving consistent accuracy has proven to be challenging, due to limited precision of memristors. One promising strategy involves harnessing multiple memristor cells to improve synaptic precision, yet a mere concatenation approach as published in the literature falls short of meeting this goal, as inherent variations in the memristor writing process would render errors of higher order bit cells to overshadow lower order bits cells. In response to this challenge, we present a novel’ cell splicing’ methodology designed to enhance accuracy with analog computation. Experimental simulations using the ImageNet dataset demonstrate that it achieves accuracy similar to the baseline, and markedly outperforms the rudimentary concatenation approach.