Cross-layer approaches for improving the dependability of deep learning systems

Muhammad Abdullah Hanif, Le Ha Hoang, Muhammad Shafique

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

Abstract

Deep Neural Networks (DNNs) - the state-of-the-art computational models for many Artificial Intelligence (AI) applications - are inherently compute and resource-intensive and, hence, cannot exploit traditional redundancy-based fault mitigation techniques for enhancing the dependability of DNN-based systems. Therefore, there is a dire need to search for alternate methods that can improve their reliability without high expenditure of resources by exploiting the intrinsic characteristics of these networks. In this paper, we present cross-layer approaches that, based on the intrinsic characteristics of DNNs, employ software and hardware-level modifications for improving the resilience of DNN-based systems to hardware-level faults, e.g., soft errors and permanent faults.

Original languageEnglish (US)
Title of host publicationProceedings of the 23rd International Workshop on Software and Compilers for Embedded Systems, SCOPES 2020
EditorsSander Stuijk
PublisherAssociation for Computing Machinery, Inc
Pages78-81
Number of pages4
ISBN (Electronic)9781450371315
DOIs
StatePublished - May 25 2020
Event23rd International Workshop on Software and Compilers for Embedded Systems, SCOPES 2020 - St. Goar, Germany
Duration: May 25 2020May 26 2020

Publication series

NameProceedings of the 23rd International Workshop on Software and Compilers for Embedded Systems, SCOPES 2020

Conference

Conference23rd International Workshop on Software and Compilers for Embedded Systems, SCOPES 2020
CountryGermany
CitySt. Goar
Period5/25/205/26/20

Keywords

  • cross-layer
  • deep learning
  • dependability
  • DNNs
  • faults
  • hardware accelerators
  • neural networks
  • reliability
  • soft errors
  • systems

ASJC Scopus subject areas

  • Software
  • Hardware and Architecture

Fingerprint Dive into the research topics of 'Cross-layer approaches for improving the dependability of deep learning systems'. Together they form a unique fingerprint.

Cite this