Accession Number:

AD1111265

Title:

Research Review 2020, Knowing When You Don't Know: Engineering AI Systems in an Uncertain World

Descriptive Note:

[Technical Report, Briefing Charts]

Corporate Author:

CARNEGIE-MELLON UNIV PITTSBURGH PA

Personal Author(s):

Report Date:

2020-01-01

Pagination or Media Count:

14

Abstract:

In order for the DoD to leverage recent advances in AI, modern Machine Learning techniques need to be able to quantify, reason about, and rectify uncertainty in their predictions. In this work, we will benchmark modern techniques that quantify uncertainty, and develop techniques to identify causes of uncertainty and efficiently update ML models to reduce uncertainty in their predictions.

Descriptors:

Subject Categories:

  • Computer Programming and Software

Distribution Statement:

[A, Approved For Public Release]