In-situ Tuning of Printed Neural Networks for Variation Tolerance
Michael Hefenbrocka, Dennis D. Wellerb, Jasmin Aghassi-Hagmannc, Michael Beigld and Mehdi B. Tahoorie
Karlsruhe Institute of Technology, Karlsruhe, Germany
amichael.hefenbrock@kit.edu
bdennis.weller@kit.edu
cjasmin.aghassi@kit.edu
dmichael.beigl@kit.edu
emehdi.tahoori@kit.edu
ABSTRACT
Printed electronic (PE) can meet the requirements of many application domains with requirements on cost, conformity, and non-toxicity which silicon-based computing systems cannot achieve. A typical computational task to be performed in many of such applications is classification. Therefore, printed Neural Networks (pNNs) have been proposed to meet these requirements. However, PE suffers from high process variations due to low resolution printing in low-cost additive manufacturing. This can severely impact the inference accuracy of pNNs. In this work, we show how a unique feature of PE, namely additive printing can be leveraged to perform in-situ tuning of pNNs to compensate accuracy losses induced by device variations. The experiments show that, even under 30 % variation of the conductances, up to 90 % of the initial accuracy can be recovered.
