Scalable supervised machine learning apparatus for computationally constrained devices

Jorge López, Andrey Laputenko, Natalia Kushik, Nina Yevtushenko, Stanislav N. Torgaev

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Computationally constrained devices are devices with typically low resources / computational power built for specific tasks. At the same time, recent advances in machine learning, e.g., deep learning or hierarchical or cascade compositions of machines, that allow to accurately predict / classify some values of interest such as quality, trust, etc., require high computational power. Often, such complicated machine learning configurations are possible due to advances in processing units, e.g., Graphical Processing Units (GPUs). Computationally constrained devices can also benefit from such advances and an immediate question arises: how? This paper is devoted to reply the stated question. Our approach proposes to use scalable representations of 'trained' models through the synthesis of logic circuits. Furthermore, we showcase how a cascade machine learning composition can be achieved by using 'traditional' digital electronic devices. To validate our approach, we present a set of preliminary experimental studies that show how different circuit apparatus clearly outperform (in terms of processing speed and resource consumption) current machine learning software implementations.

Original languageEnglish
Title of host publicationICSOFT 2018 - Proceedings of the 13th International Conference on Software Technologies
EditorsLeszek Maciaszek, Leszek Maciaszek, Marten van Sinderen
PublisherSciTePress
Pages518-528
Number of pages11
ISBN (Electronic)9789897583209
DOIs
Publication statusPublished - 2019
Event13th International Conference on Software Technologies, ICSOFT 2018 - Porto, Portugal
Duration: 26 Jul 201828 Jul 2018

Publication series

NameICSOFT 2018 - Proceedings of the 13th International Conference on Software Technologies

Conference

Conference13th International Conference on Software Technologies, ICSOFT 2018
CountryPortugal
CityPorto
Period26.7.1828.7.18

Keywords

  • Constrained Devices
  • Deep Learning
  • Digital Circuits
  • Supervised Machine Learning

ASJC Scopus subject areas

  • Software
  • Information Systems
  • Computer Science Applications

Fingerprint Dive into the research topics of 'Scalable supervised machine learning apparatus for computationally constrained devices'. Together they form a unique fingerprint.

Cite this