Knowing When You Don't Know: Quantifying and Reasoning about Uncertainty in Machine Learning Models

Abstract

Our Work: Evaluating, Characterizing, Articulating, and Rectifying Uncertainty in ML models for the purpose of more informative and robust AI Systems.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Nov 14, 2022
Accession Number
AD1183582

Entities

People

  • Aarti Singh
  • Eric Heim
  • Jacob Oaks
  • John Kirchenbauer
  • Jon Helland
  • Zachary Lipton

Organizations

  • Carnegie Mellon University

Tags

DTIC Thesaurus Topics

  • Artificial Intelligence
  • Classification
  • Deep Learning
  • Detection
  • Detectors
  • Information Processing
  • Learning
  • Machine Learning
  • Materials
  • National Guard
  • National Security
  • Neural Networks
  • Probability
  • Probability Distributions
  • Software Development
  • South Carolina
  • Spine
  • Training
  • Uncertainty
  • Universities

Technology Areas

  • AI & ML
  • AI & ML - DoD AI Strategy
  • AI & ML - Neural Networks