On Evidence Capture for Accountable AI Systems

Wei Pang, Milan Markovic, Iman Naja, Chiu Pang Fung, Pete Edwards

Research output: Chapter in Book/Report/Conference proceedingPublished conference contribution

12 Downloads (Pure)

Abstract

This research explores evidence capture for accountable AI systems. First, different scopes of AI accountability are set out by extending existing classification. Based on these scopes, two important and fundamental questions in evidence capture are answered: what types of evidence need to be captured and how we can capture them to facilitate better AI accountability. We hope that this research can provide guidance on building better accountable AI systems with effective evidence capture and initiate further research along this line
Original languageEnglish
Title of host publicationCEUR Workshop Proceedings
EditorsKyle Martin, Nirmalie Wiratunga , Anjana Wijekoon
Pages33-39
Number of pages7
Volume2894
Publication statusPublished - 2 Jul 2021
EventSICSA Workshop on eXplainable Artificial Intelligence (XAI) 2021 -
Duration: 1 Jun 20211 Jun 2021
https://sites.google.com/view/sicsa-xai-workshop/home?authuser=0

Publication series

Name
ISSN (Electronic)1613-0073

Workshop

WorkshopSICSA Workshop on eXplainable Artificial Intelligence (XAI) 2021
Abbreviated titleXAI
Period1/06/211/06/21
Internet address

Bibliographical note

Conference Proceedings ISSN 16130073
CEUR Workshop Proceedings Volume 2894, Pages 33 - 392021 2021 SICSA eXplainable Artifical Intelligence Workshop, SICSA XAI 2021, Aberdeen, 1 June 2021, 169872

Keywords

  • Accountability
  • Artificial intelligence
  • Evidence capture

Cite this