IACS Seminar: What Are Useful Uncertainties in Deep Learning and How Do We Get Them? 9/11/20

Presented by Weiwei Pan, Harvard University Talk Description: While deep learning has demonstrable success on many tasks, the point estimates provided by standard deep models can lead to overfitting and provide no uncertainty quantification on predictions. However, when models are applied to critical domains such as autonomous driving, precision health care, or criminal justice, reliable measurements of a model’s predictive uncertainty may be as crucial as correctness of its predictions. At the same time,