technical paper

AAMAS 2020

May 11, 2020

Live on Underline

Not all Mistakes are Equal

DOI: 10.48448/024t-z268

In many tasks, classifiers play a fundamental role in the way an agent behaves. Most rational agents collect sensor data from the environment, classify it, and act based on that classification. Recently, deep neural networks (DNNs) have become the dominant approach to develop classifiers due to their excellent performance. When training and evaluating the performance of DNNs, it is normally assumed that the cost of all misclassification errors are equal. However, this is unlikely to be true in practice. Incorrect classification predictions can cause an agent to take inappropriate actions. The costs of these actions can be asymmetric, vary from agent-to-agent, and depend on context. In this paper, we discuss the importance of considering risk and uncertainty quantification together to reduce agents’ cost of making misclassifications using deep classifiers.

Downloads

Slides

Next from AAMAS 2020

technical paper

Efficient Deep Reinforcement Learning through Policy Transfer

AAMAS 2020

Tianpei Yang

11 May 2020

Similar lecture

poster

OPT-GAN: A Broad-Spectrum Global Optimizer for Black-box Problems by Learning Distribution

AAAI 2023

+4
Lin Wang and 6 other authors

11 February 2023

Stay up to date with the latest Underline news!

PRESENTATIONS

  • All Lectures
  • For Librarians
  • Resource Center
  • Free Trial
Underline Science, Inc.
1216 Broadway, 2nd Floor, New York, NY 10001, USA

© 2023 Underline - All rights reserved