Data Fest Online 2020 Uncertainty Estimation in ML track Speaker: Andrey Malinin, Yandex & HSE In this video we discuss how to assess the quality of uncertainty estimates. We discuss comparing models according to test-set negative log-likelihood as well as assessing error and anomaly detection via area under a precision-recall curve and ROC curve. Register and get access to the tracks: Join the community:
Hide player controls
Hide resume playing