AnytimeNet: Controlling Time-Quality Tradeoffs in Deep Neural Network Architectures

Jung Eun Kim, Richard Bradford, Zhong Shao

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

2 Scopus citations

Abstract

Deeper neural networks, especially those with extremely large numbers of internal parameters, impose a heavy computational burden in obtaining sufficiently high-quality results. These burdens are impeding the application of machine learning and related techniques to time-critical computing systems. To address this challenge, we are proposing an architectural approach for neural networks that adaptively trades off computation time and solution quality to achieve high-quality solutions with timeliness. We propose a novel and general framework, AnytimeNet, that gradually inserts additional layers, so users can expect monotonically increasing quality of solutions as more computation time is expended. The framework allows users to select on the fly when to retrieve a result during runtime. Extensive evaluation results on classification tasks demonstrate that our proposed architecture provides adaptive control of classification solution quality according to the available computation time.

Original languageEnglish (US)
Title of host publicationProceedings of the 2020 Design, Automation and Test in Europe Conference and Exhibition, DATE 2020
EditorsGiorgio Di Natale, Cristiana Bolchini, Elena-Ioana Vatajelu
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages945-950
Number of pages6
ISBN (Electronic)9783981926347
DOIs
StatePublished - Mar 2020
Externally publishedYes
Event2020 Design, Automation and Test in Europe Conference and Exhibition, DATE 2020 - Grenoble, France
Duration: Mar 9 2020Mar 13 2020

Publication series

NameProceedings of the 2020 Design, Automation and Test in Europe Conference and Exhibition, DATE 2020

Conference

Conference2020 Design, Automation and Test in Europe Conference and Exhibition, DATE 2020
Country/TerritoryFrance
CityGrenoble
Period3/9/203/13/20

Keywords

  • adaptive neural network
  • cyber-physical system
  • machine learning
  • time-critical system
  • time-quality tradeoff

ASJC Scopus subject areas

  • Hardware and Architecture
  • Safety, Risk, Reliability and Quality
  • Modeling and Simulation
  • Electrical and Electronic Engineering

Fingerprint

Dive into the research topics of 'AnytimeNet: Controlling Time-Quality Tradeoffs in Deep Neural Network Architectures'. Together they form a unique fingerprint.

Cite this