Slice-based Learning: A Programming Model for Residual Learning in Critical Data Slices
In NeurIPS 2019.
Powerful Abstractions for Programming Your Training Data
Massive Multi-Task Learning: Bringing More Supervision to Bear
Weakly supervised classification of rare aortic valve malformations using unlabeled cardiac MRI sequences
In Nature Communications 2019.
Automated Training Set Generation for Aortic Valve Classification
Using weak-supervision, we learn probabilistic training labels for aortic valve MRIs.
In NeurIPS 2017, ML4H Workshop.