Guardado en:
Detalles Bibliográficos
Autores principales: Armeniakos, Giorgos, Mantzakidis, Theodoros, Soudris, Dimitrios
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:https://arxiv.org/abs/2509.15316
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866918144107347968
author Armeniakos, Giorgos
Mantzakidis, Theodoros
Soudris, Dimitrios
author_facet Armeniakos, Giorgos
Mantzakidis, Theodoros
Soudris, Dimitrios
contents Printed Electronics (PE) provide a flexible, cost-efficient alternative to silicon for implementing machine learning (ML) circuits, but their large feature sizes limit classifier complexity. Leveraging PE's low fabrication and NRE costs, designers can tailor hardware to specific ML models, simplifying circuit design. This work explores alternative arithmetic and proposes a hybrid unary-binary architecture that removes costly encoders and enables efficient, multiplier-less execution of MLP classifiers. We also introduce architecture-aware training to further improve area and power efficiency. Evaluation on six datasets shows average reductions of 46% in area and 39% in power, with minimal accuracy loss, surpassing other state-of-the-art MLP designs.
format Preprint
id arxiv_https___arxiv_org_abs_2509_15316
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Hybrid unary-binary design for multiplier-less printed Machine Learning classifiers
Armeniakos, Giorgos
Mantzakidis, Theodoros
Soudris, Dimitrios
Machine Learning
Printed Electronics (PE) provide a flexible, cost-efficient alternative to silicon for implementing machine learning (ML) circuits, but their large feature sizes limit classifier complexity. Leveraging PE's low fabrication and NRE costs, designers can tailor hardware to specific ML models, simplifying circuit design. This work explores alternative arithmetic and proposes a hybrid unary-binary architecture that removes costly encoders and enables efficient, multiplier-less execution of MLP classifiers. We also introduce architecture-aware training to further improve area and power efficiency. Evaluation on six datasets shows average reductions of 46% in area and 39% in power, with minimal accuracy loss, surpassing other state-of-the-art MLP designs.
title Hybrid unary-binary design for multiplier-less printed Machine Learning classifiers
topic Machine Learning
url https://arxiv.org/abs/2509.15316