Notes
Download notes on sufficient reason (Keynote at HCD for Intelligent Environments, BHCI, Belfast, 3rd July 2018, PDF, 4.7M)
Download the draft AIX Kitbag (first draft version for comments)
Abstract
In this talk I will pick up threads of research dating back to early work in the 1990s on gender and ethnic bias in black-box machine-learning systems, as well as more recent developments such as deep learning and concerns such as those that gave rise to the EPSRC human–like computing programme. In particular I will present nascent work on an AIX Toolkit (AI explainability): a structured collection of techniques designed to help developers of intelligent systems create more comprehensible representations of the reasoning. Crucial to the AIX Toolkit is the understanding that human–human explanations are rarely utterly precise or reproducible, but they are sufficient to inspire confidence and trust in a collaborative endeavour.
Keywords: artificial intelligence, interaction design, bias, explainability, user experience, UX, AI, HCI, trust
Related Publications
- A. Dix (1992). Human issues in the use of pattern recognition techniques. In Neural Networks and Pattern Recognition in Human Computer Interaction Eds. R. Beale and J. Finlay. Ellis Horwood. 429-451. http://alandix.com/academic/papers/neuro92/
- Dix, A. and Patrick, A. (1994). Query By Browsing. Proceedings of IDS’94: The 2nd International Workshop on User Interfaces to Databases, Ed. P. Sawyer. Lancaster, UK, Springer Verlag. 236-248. http://alandix.com/academic/papers/QbB-IDS94/
- Dix, A. (2016). Human-Like Computing. (personal report on the EPRC workshop of the same name) http://alandix.com/blog/2016/02/23/human-like-computing/
- A. Dix. (2016). Human-Like Computing and Human–Computer Interaction. Proc. Human Centred Design for Intelligent Environments (HCD4IE) Workshop. HCI2016. http://alandix.com/academic/papers/HCD4IE-2016-human-like/
- Alan Dix (2017). Activity Modelling for Low-Intention Interaction. Chapter 7 in The Handbook of Formal Methods in Human-Computer Interaction, Springer, pp.183–210. DOI: 10.1007/978-3-319-51838-1_7
|