search menu icon-carat-right cmu-wordmark

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

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

Software Engineering Institute

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.