Late Breaking Results: Energy-Efficient Printed Machine Learning Classifiers with Sequential SVMs

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Besias, Spyridon, Sertaridis, Ilias, Afentaki, Florentia, Balaskas, Konstantinos, Zervakis, Georgios
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929689607536640
author Besias, Spyridon
Sertaridis, Ilias
Afentaki, Florentia
Balaskas, Konstantinos
Zervakis, Georgios
author_facet Besias, Spyridon
Sertaridis, Ilias
Afentaki, Florentia
Balaskas, Konstantinos
Zervakis, Georgios
contents Printed Electronics (PE) provide a mechanically flexible and cost-effective solution for machine learning (ML) circuits, compared to silicon-based technologies. However, due to large feature sizes, printed classifiers are limited by high power, area, and energy overheads, which restricts the realization of battery-powered systems. In this work, we design sequential printed bespoke Support Vector Machine (SVM) circuits that adhere to the power constraints of existing printed batteries while minimizing energy consumption, thereby boosting battery life. Our results show 6.5x energy savings while maintaining higher accuracy compared to the state of the art.
format Preprint
id arxiv_https___arxiv_org_abs_2501_16828
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Late Breaking Results: Energy-Efficient Printed Machine Learning Classifiers with Sequential SVMs
Besias, Spyridon
Sertaridis, Ilias
Afentaki, Florentia
Balaskas, Konstantinos
Zervakis, Georgios
Machine Learning
Systems and Control
Image and Video Processing
Printed Electronics (PE) provide a mechanically flexible and cost-effective solution for machine learning (ML) circuits, compared to silicon-based technologies. However, due to large feature sizes, printed classifiers are limited by high power, area, and energy overheads, which restricts the realization of battery-powered systems. In this work, we design sequential printed bespoke Support Vector Machine (SVM) circuits that adhere to the power constraints of existing printed batteries while minimizing energy consumption, thereby boosting battery life. Our results show 6.5x energy savings while maintaining higher accuracy compared to the state of the art.
title Late Breaking Results: Energy-Efficient Printed Machine Learning Classifiers with Sequential SVMs
topic Machine Learning
Systems and Control
Image and Video Processing
url https://arxiv.org/abs/2501.16828