Events

Physics ∩ ML Seminars

<< Summer 2021 Fall 2021 Spring 2022 >>
Subscribe your calendar or receive email announcements of events
Uncovering the Unknowns of Deep Neural Networks: Challenges and Opportunities
Date: Wednesday, December 1st
Time: 11:00 am
Place: Chamberlin 5280 (Zoom link also available for online participants who signed up on our mailing list)
Speaker: Sharon Li, University of Wisconsin-Madison
Abstract: The real world is open and full of unknowns, presenting significant challenges for machine learning (ML) systems that must reliably handle diverse, and sometimes anomalous inputs. Out-of-distribution (OOD) uncertainty arises when a machine learning model sees a test-time input that differs from its training data, and thus should not be predicted by the model. As ML is used for more safety-critical domains, the ability to handle out-of-distribution data are central in building open-world learning systems. In this talk, I will talk about challenges, methods, and opportunities on uncovering the unknowns of deep neural networks for reliable decision-making in an open world.
Host: Gary Shiu
Add this event to your calendar