Not all mistakes are equal

Murat Sensoy, Maryam Saleki, Simon Julier, Reyhan Aydoğan, John Reid

Research output: Chapter in Book/Conference proceedings/Edited volumeConference contributionScientificpeer-review

Abstract

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.

Original languageEnglish
Title of host publicationProceedings of the 19th International Conference on Autonomous Agents and Multiagent Systems, AAMAS 2020
EditorsBo An, Amal El Fallah Seghrouchni, Gita Sukthankar
PublisherInternational Foundation for Autonomous Agents and Multiagent Systems (IFAAMAS)
Pages1996-1998
ISBN (Electronic)9781450375184
Publication statusPublished - 2020
Event19th International Conference on Autonomous Agents and Multiagent Systems, AAMAS 2020 - Virtual, Auckland, New Zealand
Duration: 19 May 2020 → …

Publication series

NameProceedings of the International Joint Conference on Autonomous Agents and Multiagent Systems, AAMAS
Volume2020-May
ISSN (Print)1548-8403
ISSN (Electronic)1558-2914

Conference

Conference19th International Conference on Autonomous Agents and Multiagent Systems, AAMAS 2020
CountryNew Zealand
CityVirtual, Auckland
Period19/05/20 → …

Keywords

  • Cost-sensitive learning
  • Deep learning
  • Risk
  • Uncertainty

Fingerprint

Dive into the research topics of 'Not all mistakes are equal'. Together they form a unique fingerprint.

Cite this