How to Design for Intelligibility of Smart Systems (PAIR UX Symposium 2018)
798 views · Published 9 July 2018 · 31:34 · Indexed 23 September 2026
Channel: Google for Developers · 2018 · Science & Technology
Smart systems that apply complex reasoning and machine learning to make decisions and carry out actions are rapidly becoming part of everyday user interaction, yet so far most of these systems are like black boxes and not at all transparent. It has been shown that intelligibility can help users interact with a system more effectively, promote positive attitudes towards the system, increase their trust in the system's decisions and actions, and to gain a sense of controllability. My research has focused on providing explanations – textual and graphical – of the behaviour of intelligent systems to make these systems more intelligible. In this talk I will provide a brief overview of what we know about how to design for intelligibility so that users understand how an intelligent system works. Watch the rest of the PAIR UX Symposium talks here → http://bit.ly/2lMnjyt Subscribe to the Google Developers channel → http://goo.gl/mQyv5L
More from this channel
-
48:40
Google I/O 2009 - Developing On O3D: View From The Trenches
-
10:22
Socialwok on GWT
-
5:25
Google Chrome Extensions: Launch Event (part 2)
-
42:22
Concurrent Data & OT Alternatives
-
55:56
YouTube Developers Live: Gaming
-
25:27
Apps Script Office Hours - September 6, 2012
-
17:41
GDL Presents: Make Web Magic | Part II
-
48:21
Dartisans ep. 14: Dart Community Demos