Tom Ginsberg
MSc Student at the University of Toronto & Vector Institute
Bio
I am a MSc student at the University of Toronto and Vector Institute under supervision of Prof Rahul G. Krishnan. I am currently interested on understanding and auditing the performance of machine learning algorithms under distribution shift with applications to the trustworthy deployment of ML in healthcare. I was previously an undergraduate student at the University of British Columbia in Engineering Physics and a visiting student at ETH Zurich. During my undergrad I spent several terms working on implementing automated diagnosis algorithms for medical imaging with the UBC Robotics and Control Lab under supervision of Prof Purang Abolmaesumi.
News
- Jan 2023 - Our paper A Learning Based Hypothesis Test for Harmful Covariate Shift has been accepted to ICLR 2023!
- Dec 2022 - I've submitted my MSc thesis! Identifying and Characterizing High Dimensional Covariate Shift with Learning Models
Research
Published
A Learning Based
Hypothesis Test for Harmful Covariate Shift
(Code)
Tom Ginsberg, Zhongyuan Liang and Rahul G. Krishnan
2023 International Conference on Learning Representations (ICLR)
Deep
Video Networks for Automatic Assessment of Aortic Stenosis in Echocardiography
Tom Ginsberg*, Ro-ee Tal*, Michael Tsang*, Calum Macdonald, Fatemeh Taheri Dezaki, John van der
Kuur, Christina Luong, Purang Abolmaesumi, Teresa Tsang
2021 International Workshop on Advances in Simplifying Medical Ultrasound (ASMUS)
Echo-Rhythm
Net: Semi-Supervised Learning For Automatic Detection of Atrial Fibrillation in Echocardiography
Fatemeh Taheri Dezaki*, Tom Ginsberg*, Christina Luong, Hooman Vaseli, Robert Rohling, Ken Gin,
Purang Abolmaesumi, Teresa Tsang
2021 IEEE 18th International Symposium on Biomedical Imaging (ISBI)
Echo-syncnet:
Self-supervised cardiac view synchronization in echocardiography
(Code)
Fatemeh Taheri Dezaki*, Christina Luong*, Tom Ginsberg, Robert Rohling, Ken Gin, Purang
Abolmaesumi, Teresa Tsang
IEEE Transactions on Medical Imaging ( Volume: 40, Issue: 8, Aug. 2021)
Peer Reviewed Workshops
A Learning Based
Hypothesis Test for Harmful Covariate Shift
(Code)
(Poster)
(Slides)
Tom Ginsberg, Zhongyuan Liang and Rahul G. Krishnan
Workshop on Distribution Shifts, 36th Conference on Neural Information Processing Systems (NeurIPS 2022).