Publication Details
Evolutionary Approximation of Ternary Neurons for On-sensor Printed Neural Networks
KOKKINIS, A.
PAPANIKOLAOU, P.
Vašíček Zdeněk, doc. Ing., Ph.D. (DCSY)
SIOZIOS, K.
TZIMPRAGOS, G.
TAHOORI, M.
ZERVAKIS, G.
Approximate Computing, Electrolyte-gated FET, Printed Electronics, Low-Power
Classifiers, Ternary Neural Networks
Printed electronics offer ultra-low manufacturing costs and the potential for
on-demand fabrication of flexible hardware. However, significant intrinsic
constraints stemming from their large feature sizes and low integration density
pose design challenges that hinder their practicality. In this work, we conduct
a holistic exploration of printed neural network accelerators, starting from the
analog-to-digital interface---a major area and power sink for sensor processing
applications---and extending to networks of ternary neurons and their
implementation. We propose bespoke ternary neural networks using approximate
popcount and popcount-compare units, developed through a multi-phase evolutionary
optimization approach and interfaced with sensors via customizable
analog-to-binary converters. Our evaluation results show that the presented
designs outperform the state of the art, achieving at least 6x improvement in
area and 19x in power. To our knowledge, they represent the first open-source
digital printed neural network classifiers capable of operating with existing
printed energy harvesters.
@inproceedings{BUT188903,
author="MRÁZEK, V. and KOKKINIS, A. and PAPANIKOLAOU, P. and VAŠÍČEK, Z. and SIOZIOS, K. and TZIMPRAGOS, G. and TAHOORI, M. and ZERVAKIS, G.",
title="Evolutionary Approximation of Ternary Neurons for On-sensor Printed Neural Networks",
booktitle="2024 IEEE/ACM International Conference on Computer Aided Design (ICCAD)",
year="2024",
pages="9",
publisher="Association for Computing Machinery",
address="New York",
doi="10.1145/3676536.3676728",
isbn="979-8-4007-1077-3"
}