Published multiple papers on deep learning, sparse neural network training, astronomy, and computer vision, including 'Dynamic Sparse Training with Structured Sparsity' (ICLR 2024) and 'Gradient Flow in Sparse Neural Networks and How Lottery Tickets Win' (AAAI 2022). Also involved in projects such as rapid classification of TESS planet candidates using convolutional neural networks.
Research Experience
Previously a Postdoctoral Research Fellow at the Vector Institute and University of Guelph, working with Prof. Graham Taylor, and a Visiting Researcher at Google Brain Toronto/Google AR Core. Past work includes exoplanet detection with NASA, medical imaging, and 3D computer vision methods for processing and recognizing objects in large point clouds.
Education
Completed his PhD at the University of Cambridge in 2018, supervised by Professor Roberto Cipolla and Dr. Antonio Criminisi, supported by a Microsoft Research Ph.D. Scholarship.
Background
Currently an Assistant Professor and Schulich Research Chair at the University of Calgary in the Department of Electrical and Software Engineering, leading the Calgary Machine Learning Lab. His primary research interests include efficient deep learning, specifically for computer vision problems, and sparse neural network training.
Miscellany
Teaches courses at the Schulich School of Engineering, University of Calgary, including ENSF 444: Machine Learning, SENG 401: Software Architecture, and ENSF 619 Special Topics: Learning Representations in Deep Neural Networks.