Elliot J. Crowley
Lecturer, University of Edinburgh
group · github · scholar

I am a Lecturer (Assistant Professor) in Machine Learning and Computer Vision at the School of Engineering in the University of Edinburgh. I lead the BayesWatch research group with Amos Storkey from the School of Informatics.

My research interests include:

  • making deep neural networks more efficient
  • simplifying architecture search
  • representation learning

Before, I was a postdoc at the School of Informatics in Edinburgh. I did my MEng and DPhil at the University of Oxford. For my DPhil, I worked with Andrew Zisserman on object recognition and retrieval in art.

Interested in doing a PhD in machine learning or computer vision? I am looking for a highly motivated and creative student to start a PhD in January 2021. This will be fully funded for UK/EU students. A solid academic record and strong programming skills are essential. Please email me a CV and a research proposal along with exam transcripts if you're interested.

Recent Papers

Neural Architecture Search without Training
J. Mellor, J. Turner, A. Storkey, E. J. Crowley
[pdf] [arXiv] [code]

Deep Kernel Transfer in Gaussian Processes for Few-shot Learning
M. Patacchiola, J. Turner, E. J. Crowley, M. O’Boyle, A. Storkey
[pdf] [arXiv] [code]

BlockSwap: Fisher-guided Block Substitution for Network Compression on a Budget
J. Turner*, E. J. Crowley*, M. O’Boyle, A. Storkey, G. Gray
ICLR, 2020
[pdf] [arXiv] [code]

Optimizing Grouped Convolutions on Edge Devices
P. Gibson, J. Cano, J. Turner, E. J. Crowley, M. O'Boyle, A. Storkey
ASAP, 2020
[pdf] [arXiv] [code]

* indicates equal contribution.
Thanks to Jack Turner for the website template.