Co-Design of Approximate Multilayer Perceptron for Ultra-Resource Constrained Printed Circuits

Giorgos Armeniakos, Georgios Zervakis, Dimitrios Soudris, Mehdi B. Tahoori, Jörg Henkel
2/28/2023
cs.LGcs.AR

No official code found. Best implementation: garmeniakos/Ax-Printed-ML-Classifiers (7 stars, last commit 2024-04-15).

Abstract

Printed Electronics (PE) exhibits on-demand, extremely low-cost hardware due to its additive manufacturing process, enabling machine learning (ML) applications for domains that feature ultra-low cost, conformity, and non-toxicity requirements that silicon-based systems cannot deliver. Nevertheless, large feature sizes in PE prohibit the realization of complex printed ML circuits. In this work, we present, for the first time, an automated printed-aware software/hardware co-design framework that exploits approximate computing principles to enable ultra-resource constrained printed multilayer perceptrons (MLPs). Our evaluation demonstrates that, compared to the state-of-the-art baseline, our circuits feature on average 6x (5.7x) lower area (power) and less than 1% accuracy loss.

View on arXivView PDF

Code Implementations(1)

garmeniakos/Ax-Printed-ML-ClassifiersCommunity100%

Approximate Printed Machine Learning Classifiers

72Python, VerilogDec 13, 20212 years ago
approximate-computingcross-layercross-layer-approximationdesign-automationdesign-space-exploration+2 more

Similar Papers

Model-to-Circuit Cross-Approximation For Printed Machine Learning Classifiers

86% match2023

Arbitrary Precision Printed Ternary Neural Networks with Holistic Evolutionary Approximation

85% match1 repo2025

Bespoke Approximation of Multiplication-Accumulation and Activation Targeting Printed Multilayer Perceptrons

84% match1 repo2023

Hybrid unary-binary design for multiplier-less printed Machine Learning classifiers

84% match2025

Machine Learning Accelerators in 2.5D Chiplet Platforms with Silicon Photonics

82% match2023

On-sensor Printed Machine Learning Classification via Bespoke ADC and Decision Tree Co-Design

81% match1 repo72023

Cite this paper

@article{armeniakos2023codesign,
  title  = {Co-Design of Approximate Multilayer Perceptron for Ultra-Resource Constrained Printed Circuits},
  author = {Giorgos Armeniakos and Georgios Zervakis and Dimitrios Soudris and Mehdi B. Tahoori and Jörg Henkel},
  year   = {2023},
  eprint = {2302.14576},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2302.14576v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2302.14576.svg)](https://codeofpaper.com/paper/2302.14576)

Discussion