Preprint · 2017 · Open access

Streamlined Deployment for Quantized Neural Networks

Yaman Umuroglu, Magnus Jahre

arXiv (Cornell University) · Published 12 September 2017 · DOI 10.48550/arxiv.1709.04060

Open PDFView at the publisherCite this paper

In brief

“Streamlined Deployment for Quantized Neural Networks” is a 2017 preprint by Yaman Umuroglu and Magnus Jahre, published in arXiv (Cornell University). OpenAlex counts 66 citations as of 19 November 2026. It is open access: the full text is free to read at arXiv (Cornell University).

Citations
66
Most cited in
2021 (13)
References
8
Authors
2

Abstract

Running Deep Neural Network (DNN) models on devices with limited computational capability is a challenge due to large compute and memory requirements. Quantized Neural Networks (QNNs) have emerged as a potential solution to this problem, promising to offer most of the DNN accuracy benefits with much lower computational cost. However, harvesting these benefits on existing mobile CPUs is a challenge since operations on highly quantized datatypes are not natively supported in most instruction set architectures (ISAs). In this work, we first describe a streamlining flow to convert all QNN inference operations to integer ones. Afterwards, we provide techniques based on processing one bit position at a time (bit-serial) to show how QNNs can be efficiently deployed using common bitwise operations. We demonstrate the potential of QNNs on mobile CPUs with microbenchmarks and on a quantized AlexNet, which is 3.5x faster than an optimized 8-bit baseline. Our bit-serial matrix multiplication library is available on GitHub at https://git.io/vhshn

Cite this paper

Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.

APA 7

Umuroglu, Y., & Jahre, M. (2017). Streamlined Deployment for Quantized Neural Networks. arXiv (Cornell University). https://doi.org/10.48550/arxiv.1709.04060

MLA 9

Umuroglu, Yaman, and Magnus Jahre. “Streamlined Deployment for Quantized Neural Networks.” arXiv (Cornell University), 2017. https://doi.org/10.48550/arxiv.1709.04060.

Chicago

Umuroglu, Yaman and Magnus Jahre. 2017. “Streamlined Deployment for Quantized Neural Networks.” arXiv (Cornell University). https://doi.org/10.48550/arxiv.1709.04060.

Harvard

Umuroglu, Y. and Jahre, M. (2017) ‘Streamlined Deployment for Quantized Neural Networks’, arXiv (Cornell University). doi:10.48550/arxiv.1709.04060.

IEEE

Y. Umuroglu and M. Jahre, “Streamlined Deployment for Quantized Neural Networks,” arXiv (Cornell University), 2017, doi: 10.48550/arxiv.1709.04060.

BibTeX

@misc{umuroglu2017streamlined,
  title     = {{Streamlined Deployment for Quantized Neural Networks}},
  author    = {Umuroglu, Yaman and Jahre, Magnus},
  howpublished = {arXiv (Cornell University)},
  year      = {2017},
  doi       = {10.48550/arxiv.1709.04060},
  url       = {https://doi.org/10.48550/arxiv.1709.04060}
}

Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)

Citations by year

YearCitationsShare of the best year
201711
201833
201933
202033
20211313
202277
20231212
202455
202588
20261111

Topic and keywords

Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications

  • neural network quantization
  • bit-serial computation
  • bitwise operations
  • AlexNet
  • low-precision inference
  • instruction set architecture

Work with this paper

Most-cited papers in Computer Science

All highly cited Computer Science papers

Questions about this paper

How do I cite this paper in APA style?

Umuroglu, Y., & Jahre, M. (2017). Streamlined Deployment for Quantized Neural Networks. arXiv (Cornell University). https://doi.org/10.48550/arxiv.1709.04060

How many times has this paper been cited?

66 times, according to OpenAlex on 19 November 2026. Google Scholar and Scopus count different sets of sources, so their numbers differ.

Is this paper free to read?

Yes. It is open access at arXiv (Cornell University): sign in and open the PDF from this page.

Who wrote this paper?

Yaman Umuroglu, Magnus Jahre.

What is the DOI of this paper?

10.48550/arxiv.1709.04060, permanently at https://doi.org/10.48550/arxiv.1709.04060. Sign in and open it from this page.

Bibliographic data from OpenAlex (CC0), last checked 19 November 2026. ResearchGuru does not host this paper; once you are signed in, the links open it at the publisher or the repository that does.