Building more explainable artificial intelligence with argumentation

Building more explainable artificial intelligence with argumentation

Currently, much of machine learning is opaque, just like a “black box”. However, in order for humans to understand, trust and effectively manage the emerging AI systems, an AI needs to be able to explain its decisions and conclusions. In this paper, I propose an argumentation-based approach to expla...

Full description

Saved in:
Bibliographic Details
Main Authors: Zeng, Zhiwei, Miao, Chunyan, Leung, Cyril, Chin, Jing Jih
Other Authors: School of Computer Science and Engineering
Format: Conference or Workshop Item
Language:English
Published: 2020
Subjects:
Engineering::Computer science and engineering
Explainable AI
Argumentation
Online Access:https://www.aaai.org/ocs/index.php/AAAI/AAAI18/paper/view/16762
https://hdl.handle.net/10356/139223
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Nanyang Technological University
Language: English
id sg-ntu-dr.10356-139223
record_format dspace
spelling sg-ntu-dr.10356-1392232020-05-18T05:50:50Z Building more explainable artificial intelligence with argumentation Zeng, Zhiwei Miao, Chunyan Leung, Cyril Chin, Jing Jih School of Computer Science and Engineering Interdisciplinary Graduate School (IGS) The Twenty-Third AAAI/SIGAI Doctoral Consortium Engineering::Computer science and engineering Explainable AI Argumentation Currently, much of machine learning is opaque, just like a “black box”. However, in order for humans to understand, trust and effectively manage the emerging AI systems, an AI needs to be able to explain its decisions and conclusions. In this paper, I propose an argumentation-based approach to explainable AI, which has the potential to generate more comprehensive explanations than existing approaches. NRF (Natl Research Foundation, S’pore) MOH (Min. of Health, S’pore) Accepted version 2020-05-18T05:50:50Z 2020-05-18T05:50:50Z 2018 Conference Paper Zeng, Z., Miao, C., Leung, C., & Chin, J. J. (2018). Building more explainable artificial intelligence with argumentation. Proceedings of The Twenty-Third AAAI/SIGAI Doctoral Consortium. https://www.aaai.org/ocs/index.php/AAAI/AAAI18/paper/view/16762 https://hdl.handle.net/10356/139223 8044 8045 en © 2018 Association for the Advancement of Artificial Intelligence. All rights reserved. This paper was published in The Twenty-Third AAAI/SIGAI Doctoral Consortium and is made available with permission of Association for the Advancement of Artificial Intelligence. application/pdf
institution Nanyang Technological University
building NTU Library
country Singapore
collection DR-NTU
language English
topic Engineering::Computer science and engineering
Explainable AI
Argumentation
spellingShingle Engineering::Computer science and engineering
Explainable AI
Argumentation
Zeng, Zhiwei
Miao, Chunyan
Leung, Cyril
Chin, Jing Jih
Building more explainable artificial intelligence with argumentation
description Currently, much of machine learning is opaque, just like a “black box”. However, in order for humans to understand, trust and effectively manage the emerging AI systems, an AI needs to be able to explain its decisions and conclusions. In this paper, I propose an argumentation-based approach to explainable AI, which has the potential to generate more comprehensive explanations than existing approaches.
author2 School of Computer Science and Engineering
author_facet School of Computer Science and Engineering
Zeng, Zhiwei
Miao, Chunyan
Leung, Cyril
Chin, Jing Jih
format Conference or Workshop Item
author Zeng, Zhiwei
Miao, Chunyan
Leung, Cyril
Chin, Jing Jih
author_sort Zeng, Zhiwei
title Building more explainable artificial intelligence with argumentation
title_short Building more explainable artificial intelligence with argumentation
title_full Building more explainable artificial intelligence with argumentation
title_fullStr Building more explainable artificial intelligence with argumentation
title_full_unstemmed Building more explainable artificial intelligence with argumentation
title_sort building more explainable artificial intelligence with argumentation
publishDate 2020
url https://www.aaai.org/ocs/index.php/AAAI/AAAI18/paper/view/16762
https://hdl.handle.net/10356/139223
_version_ 1681056273300193280

Similar Items