search menu icon-carat-right cmu-wordmark

Knowing When You Don't Know: Engineering AI Systems in an Uncertain World

November 2020 Presentation
Eric Heim

This presentation provides a view of new research about artificial intelligence (AI) system engineering and uncertainty.

Watch

Abstract

In this work, we will benchmark modern techniques that quantify uncertainty. We'll also develop techniques to identify causes of uncertainty and efficiently update ML models to reduce uncertainty in their predictions.