Experiential AI Between Arts and Explainable AI

None, None; None, None; None, None; None, None; None, None; None, None

Experiential AI Between Arts and Explainable AI

Journal Article (2024)

Author(s)

Drew Hemment (The University of Edinburgh)

Dave Murray-Rust (TU Delft - Human Technology Relations)

Vaishak Belle (The University of Edinburgh)

Ruth Aylett (Heriot-Watt University)

Matjaz Vidmar (The University of Edinburgh)

Frank Broz (TU Delft - Interactive Intelligence)

DOI related publication

https://doi.org/10.1162/leon_a_02524 Final published version

To reference this document use

https://resolver.tudelft.nl/uuid:9697c61f-ab45-4e17-8bc2-36ae1d63ea2f

More Info

expand_more

Publication Year

2024

Language

English

Issue number

3

Volume number

57

Pages (from-to)

298-308

Downloads counter

311

Abstract

Experiential artificial intelligence (AI) is an approach to the design, use, and evaluation of AI in cultural or other real-world settings that foregrounds human experience and context. It combines arts and engineering to support rich and intuitive modes of model interpretation and interaction, making AI tangible and explicit. The ambition is to enable significant cultural works and make AI systems more understandable to nonexperts, thereby strengthening the basis for responsible deployment. This paper discusses limitations and promising directions in explainable AI, contributions the arts offer to enhance and go beyond explainability, and methodology to support, deepen, and extend those contributions.