AIMI Journal Club: Understanding Failures of Deep Networks via Robust Feature Extraction - Sahil Singla, PhD Student
Event Details:
via Zoom - email aimicenter@stanford.edu for link
Stanford community & AIMI affiliates only - recording will be available to the public after the event
Paper:
Sahil S, Nushi B, Shah S, Kamar E, Horvitz E. Understanding Failures of Deep Networks via Robust Feature Extraction. arXiv:2012.01750
About:
Sahil Singla is a third year PhD student at the University of Maryland, College Park. Earlier, he received his undergraduate degree in Computer Science from IIT Delhi. His primary research interests are adversarial robustness and interpretability of deep neural networks. Much of his recent work has focused on provable defenses against adversarial attacks and interpretability using robust models with publications in ICML, ICLR, CVPR.
Contact Email:
aimicenter@stanford.edu
More Information:
Link to paper