Tech 'n' Test 'n' ML Research

Category: Convolutional Neural Networks

  • PASM Paper presented at HiPEAC2019

    PASM Paper presented at HiPEAC2019

    And that’s the PASM paper presented.

    Me presenting PASM at HiPEAC2019

    Lots of interest and very good questions from the audience and the session chair Luca Fanucci (Università di Pisa @Unipisa). Thoroughly enjoyed it. #HiPEAC19#hipeac2019

  • Come and see my talk at HiPEAC 2019

    I am presenting my second Ph.D. publication entitled “Low Complexity Multiply-Accumulate Units for Convolutional Neural Networks with Weight-Sharing” at HiPEAC 2019.

    PASM in a CNN Layer

    I will be presenting in Session 12 Programming Models, Neural Networks.

    If you can’t make the talk, I’ll also be presenting a poster of the paper in the Student Poster Session.

    Finally, if you can’t make the conference, you can still read my paper for free on the ACM TACO web site.

  • Second Ph.D. Paper Published by ACM TACO

    Second Ph.D. Paper Published by ACM TACO

    Dr. David Gregg and I have had my second Ph.D. paper published. Entitled “Low Complexity Multiply-Accumulate Units for Convolutional Neural Networks with Weight-Sharing”, the ACM Transactions on Architecture and Code Optimization published it in their August 2018 Journal. The ACM also published it on their online server, which can be viewed for free! It can also be found on the arXiv.org pre-print server.


    Simplified weight-shared convolution with PASM

    Here are more details of the publication:
    Title: Low Complexity Multiply-Accumulate Units for Convolutional Neural Networks with Weight-Sharing
    Published in:     ACM Transactions on Architecture and Code Optimization (TACO) (Volume: 15, Issue: 3, Article 31)
    Date of Publication: August 2018
    Print ISSN: 1544-3566
    DOI: 10.1145/3233300
    Publisher: ACM

    ACM TACO Bibtex (should you wish to cite our paper):

    @article{Garland:2018:LCM:3274266.3233300,
 author = {Garland, James and Gregg, David},
 title = {Low Complexity Multiply-Accumulate Units for Convolutional Neural Networks with Weight-Sharing},
 journal = {ACM Trans. Archit. Code Optim.},
 issue_date = {August 2018},
 volume = {15},
 number = {3},
 month = sep,
 year = {2018},
 issn = {1544-3566},
 pages = {31:1--31:24},
 articleno = {31},
 numpages = {24},
 url = {http://doi.acm.org/10.1145/3233300},
 doi = {10.1145/3233300},
 acmid = {3233300},
 publisher = {ACM},
 address = {New York, NY, USA},
 keywords = {ASIC, CNN, FPGA, arithmetic hardware circuits, multiply accumulate, power efficiency},
}

    Published in: arXiv.org. arXiv Bibtex:

    @article{DBLP:journals/corr/abs-1801-10219,
  author    = {James Garland and David Gregg},
  title     = {Low Complexity Multiply-Accumulate Units for Convolutional Neural Networks with Weight-Sharing},
  journal   = {CoRR},
  volume    = {abs/1801.10219},
  year      = {2018},
  url       = {http://arxiv.org/abs/1801.10219},
  archivePrefix = {arXiv},
  eprint    = {1801.10219},
  timestamp = {Mon, 13 Aug 2018 16:47:23 +0200},
  biburl    = {https://dblp.org/rec/bib/journals/corr/abs-1801-10219},
  bibsource = {dblp computer science bibliography, https://dblp.org}
}

    My complete list of publications can also be seen on my research publications page.

  • First Paper Published of my PhD by IEEE CAL

    First Paper Published of my PhD by IEEE CAL

    Dr. David Gregg and I have had my first paper of my PhD, entitled “Low Complexity Multiply Accumulate Unit for Weight-Sharing Convolutional Neural Networks” published. The IEEE Computer Architecture Letters published it on 23 January 2017. Whilst waiting for the printed version, the IEEE has published it on their on-line pre-print server. It can also be found on the arXiv.org pre-print server. 

    Here are more details of the publication:
    Published in: IEEE Computer Architecture Letters ( Volume: PP, Issue: 99)
    Date of Publication: 23 January 2017
    Print ISSN: 1556-6056
    DOI: 10.1109/LCA.2017.2656880
    Publisher: IEEE
    Sponsored by: IEEE Computer Society

    Published in: arXiv.org
     @ARTICLE{2016arXiv160905132G, author = {{Garland}, J. and {Gregg}, D.}, title = “{Low Complexity Multiply Accumulate Unit for Weight-Sharing Convolutional Neural Networks}”, journal = {ArXiv e-prints}, archivePrefix = “arXiv”, eprint = {1609.05132}, keywords = {Computer Science – Neural and Evolutionary Computing}, year = 2016, month = aug, adsurl = {http://adsabs.harvard.edu/abs/2016arXiv160905132G}, adsnote = {Provided by the SAO/NASA Astrophysics Data System} }

    My complete list of publications can also be seen on my research publications page.

  • First Paper Accepted by arXiv.org today

    First Paper Accepted by arXiv.org today

    Dr. David Gregg and I have had my first PhD paper accepted by the pre-print server arXiv (pronounced archive). The paper, entitled “Low Complexity Multiply Accumulate Unit for Weight-Sharing Convolutional Neural Networks” is a 4 page paper, the PDF for which can be found by searching arxiv.org and directly at Comments welcome!