BPNet: Branch-pruned conditional neural network for systematic time-accuracy tradeoff

Kyungchul Park, Chanyoung Oh, Youngmin Yi

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

6 Scopus citations

Abstract

Recently, there have been attempts to execute the neural network conditionally with auxiliary classifiers allowing early termination depending on the difficulty of the input, which can reduce the execution time or energy consumption without any or with negligible accuracy decrease. However, previous studies do not consider how many or where the auxiliary classifiers, or branches, should be added in a systematic fashion. In this paper, we propose Branch-pruned Conditional Neural Network (BPNet) and its methodology in which the time-accuracy tradeoff for the conditional neural network can be found systematically. We applied BPNet to SqueezeNet, ResNet-20, and VGG-16 with CIFAR-10 and 100. BPNet achieves up to 3.15× of speedup without any accuracy drop compared to the base networks.

Original languageEnglish
Title of host publication2020 57th ACM/IEEE Design Automation Conference, DAC 2020
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781450367257
DOIs
StatePublished - Jul 2020
Event57th ACM/IEEE Design Automation Conference, DAC 2020 - Virtual, San Francisco, United States
Duration: 20 Jul 202024 Jul 2020

Publication series

NameProceedings - Design Automation Conference
Volume2020-July
ISSN (Print)0738-100X

Conference

Conference57th ACM/IEEE Design Automation Conference, DAC 2020
Country/TerritoryUnited States
CityVirtual, San Francisco
Period20/07/2024/07/20

Keywords

  • And design space exploration
  • Conditional neural networks
  • Deep neural networks (DNNs)
  • Embedded systems

Fingerprint

Dive into the research topics of 'BPNet: Branch-pruned conditional neural network for systematic time-accuracy tradeoff'. Together they form a unique fingerprint.

Cite this