Embedding Hardware Approximations in Discrete Genetic-based Training for Printed MLPs

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Afentaki, Florentia, Hefenbrock, Michael, Zervakis, Georgios, Tahoori, Mehdi B.
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866917836876677120
author Afentaki, Florentia
Hefenbrock, Michael
Zervakis, Georgios
Tahoori, Mehdi B.
author_facet Afentaki, Florentia
Hefenbrock, Michael
Zervakis, Georgios
Tahoori, Mehdi B.
contents Printed Electronics (PE) stands out as a promisingtechnology for widespread computing due to its distinct attributes, such as low costs and flexible manufacturing. Unlike traditional silicon-based technologies, PE enables stretchable, conformal,and non-toxic hardware. However, PE are constrained by larger feature sizes, making it challenging to implement complex circuits such as machine learning (ML) classifiers. Approximate computing has been proven to reduce the hardware cost of ML circuits such as Multilayer Perceptrons (MLPs). In this paper, we maximize the benefits of approximate computing by integrating hardware approximation into the MLP training process. Due to the discrete nature of hardware approximation, we propose and implement a genetic-based, approximate, hardware-aware training approach specifically designed for printed MLPs. For a 5% accuracy loss, our MLPs achieve over 5x area and power reduction compared to the baseline while outperforming state of-the-art approximate and stochastic printed MLPs.
format Preprint
id arxiv_https___arxiv_org_abs_2402_02930
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Embedding Hardware Approximations in Discrete Genetic-based Training for Printed MLPs
Afentaki, Florentia
Hefenbrock, Michael
Zervakis, Georgios
Tahoori, Mehdi B.
Hardware Architecture
Machine Learning
Neural and Evolutionary Computing
Printed Electronics (PE) stands out as a promisingtechnology for widespread computing due to its distinct attributes, such as low costs and flexible manufacturing. Unlike traditional silicon-based technologies, PE enables stretchable, conformal,and non-toxic hardware. However, PE are constrained by larger feature sizes, making it challenging to implement complex circuits such as machine learning (ML) classifiers. Approximate computing has been proven to reduce the hardware cost of ML circuits such as Multilayer Perceptrons (MLPs). In this paper, we maximize the benefits of approximate computing by integrating hardware approximation into the MLP training process. Due to the discrete nature of hardware approximation, we propose and implement a genetic-based, approximate, hardware-aware training approach specifically designed for printed MLPs. For a 5% accuracy loss, our MLPs achieve over 5x area and power reduction compared to the baseline while outperforming state of-the-art approximate and stochastic printed MLPs.
title Embedding Hardware Approximations in Discrete Genetic-based Training for Printed MLPs
topic Hardware Architecture
Machine Learning
Neural and Evolutionary Computing
url https://arxiv.org/abs/2402.02930