Daniel Perry, Ph.D.


mug shot

experience

  • Applied Scientist at Amazon, 2018-present
  • See linkedin for a list of prior experience
  • background

    • Ph.D. Computing, University of Utah, 2017
    • MS Computer Science, University of Utah, 2008
    • Honors BS Computer Science, University of Utah, 2008

    research

    research interests

    • machine learning
    • artificial cognition
    • data mining
    • pattern recognition
    • image processing
    • visualization

    publications

    [google scholar profile]

    preprints:

    • A. de Wynter, D. Perry. "Optimal Subarchitecture Extraction For BERT". arxiv, Oct 2020.
    • D. Perry, V. Keshavarzzadeh, S. Elhabian, R. Kirby, M. Gleicher, R. Whitaker. "Visualization of topology optimization designs with representative subset selection". arxiv, Dec 2020, originally prepared for submission in 2017.

    conferences:

    • D. Perry, B. Osting, R. Whitaker. "Nystrom sketching". Accepted to ECML-PKDD 2017.
    • D. Perry, R. Whitaker. "Augmented leverage score sampling with bounds". Proceedings of ECML-PKDD 2016. oral and poster presentation.
    • M. Ghashami, D. Perry, and J. Phillips. "Streaming Kernel Principal Component Analysis." Proceedings of the 19th International Conference on Artificial Intelligence and Statistics, 2016. [poster] [paper] [preprint] [code]
    • D. Perry, A. Morris, N. Burgon, C. McGann, R. MacLeod, N. Marrouche, J. Cates. "Automatic left-atrial scar assessment in late gadolinium enhancement MRI". European Society of Cardiology Congress 2012 (poster presentation).
    • A. Morris, J. Cates, D. Perry, N. Burgon, N. Marrouche, E. Kholmovski. "Intensity inhomogeneity correction in LGE-MRI of AF patients is important for accurate LA wall tissue characterization". European Society of Cardiology Congress 2012 (poster presentation).
    • D. Perry, A. Morris, N. Burgon, C. McGann, R. MacLeod, J. Cates. "Automatic classification of scar tissue in late gadolinium enhancement cardiac MRI for the assessment of left-atrial wall injury after radiofrequency ablation". Proceedings of SPIE Medical Imaging, 83151D1-9, 2012. [paper] (oral presentation)
    • P. Anderson, W. Chao, D. Perry, T. Haslam, A. Au, J. Cates. "Evaluation of Inter-observer and Intra-observer Agreement in Left Atrial Segmentation Using Delayed Enhancement MRI for Patients with Atrial Fibrillation", University of Utah Undergraduate Research Abstracts, Vol. 11, p. 139, 2011. (abstract and poster presentation)

    journal articles:

    • D. Perry, R.M. Kirby, A. Narayan, R. Whitaker, "Allocation strategies for high fidelity models in the multifidelity regime", SIAM Journal of Uncertainty Quantification, 2019 (Submitted 2017). [paper]
    • Rashed Karim, R Housden, Mayuragoban Balasubramaniam, Zhong Chen, Daniel Perry, Ayesha Uddin, Yosra Al-Beyatti, Ebrahim Palkhi, Prince Acheampong, Samantha Obom, Anja Hennemuth, YingLi Lu, Wenjia Bai, Wenzhe Shi, Yi Gao, Heinz-Otto Peitgen, Perry Radau, Reza Razavi, Allen Tannenbaum, Daniel Rueckert, Josh Cates, Tobias Schaeffter, Dana Peters, Rob MacLeod, Kawal Rhode.
      "Evaluation of current algorithms for segmentation of scar tissue from late Gadolinium enhancement cardiovascular magnetic resonance of the left atrium: an open-access grand challenge".
      Journal of Cardiovascular Magnetic Resonance 2013, 15:105 (20 December 2013). [link]

    theses:

    • Ph.D. thesis: D. Perry, "Data Analysis and Visualization using Basis Selection for Matrix Approximation", School of Computing, University of Utah, 2017
    • Masters thesis: D. Perry, "Solving Geometric Constraint Problems with Monte Carlo Optimization", School of Computing, University of Utah, 2008.
    • Honors bachelors thesis: D. Perry, "Cloud Modeling and Rendering", School of Computing, University of Utah, 2007