An Analytical Method to Determine Minimum Per-Layer Precision of Deep Neural Networks

Charbel Sakr, Naresh Shanbhag

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

Abstract

There has been growing interest in the deployment of deep learning systems onto resource-constrained platforms for fast and efficient inference. However, typical models are overwhelmingly complex, making such integration very challenging and requiring compression mechanisms such as reduced precision. We present a layer-wise granular precision analysis which allows us to efficiently quantize pre-trained deep neural networks at minimal cost in terms of accuracy degradation. Our results are consistent with recent findings that perturbations in earlier layers are most destructive and hence needing more precision than in later layers. Our approach allows for significant complexity reduction demonstrated by numerical results on the MNIST and CIFAR-10 datasets. Indeed, for an equivalent level of accuracy, our fine-grained approach reduces the minimum precision in the network up to 8 bits over a naive uniform assignment. Furthermore, we match the accuracy level of a state-of-the-art binary network while requiring up to 3.5 × lower complexity. Similarly, when compared to a state-of-the-art fixed-point network, the complexity savings are even higher (up to 14×) with no loss in accuracy.

Original languageEnglish (US)
Title of host publication2018 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2018 - Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages1090-1094
Number of pages5
ISBN (Print)9781538646588
DOIs
StatePublished - Sep 10 2018
Event2018 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2018 - Calgary, Canada
Duration: Apr 15 2018Apr 20 2018

Publication series

NameICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
Volume2018-April
ISSN (Print)1520-6149

Other

Other2018 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2018
CountryCanada
CityCalgary
Period4/15/184/20/18

Keywords

  • Deep learning
  • Neural networks
  • Precision. analysis

ASJC Scopus subject areas

  • Software
  • Signal Processing
  • Electrical and Electronic Engineering

Fingerprint Dive into the research topics of 'An Analytical Method to Determine Minimum Per-Layer Precision of Deep Neural Networks'. Together they form a unique fingerprint.

  • Cite this

    Sakr, C., & Shanbhag, N. (2018). An Analytical Method to Determine Minimum Per-Layer Precision of Deep Neural Networks. In 2018 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2018 - Proceedings (pp. 1090-1094). [8461702] (ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings; Vol. 2018-April). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICASSP.2018.8461702