
A Mini Symposium on Machine Learning for Human-Computer InteractionÂ
It is a pleasure to welcome you to a mini symposium on Machine Learning and Human-Computer Interaction, to be held at Aalto University, on June 12, 2018. The three speakers have signficantly contributed to the development of intelligent user interfaces and will share their experiences and visions of the development of this field. The event is hosted by Prof. Antti Oulasvirta and the User Interfaces research group at Aalto University (userinterfaces.aalto.fi) and the Finnish Center for Artificial Intelligence FCAI (www.fcai.fi). Aalto University and the University of Helsinki have joined forces in artificial intelligence research to work towards the next generation of AI that is interactive, dependable and data-efficient.Â
Time and place:
– June 12, 2018 at 09.30am – 11.55
– TU2 (TUAS, Maarintie 8, Espoo), Aalto UniversityÂ
Streaming:Â https://youtu.be/rSrs7QreTYQ
Speakers:
- Dr. Shumin Zhai, Google:Â “Progresses and Open Research Questions in Text Input – A Select Review”
- Professor Per Ola Kristensson, University of Cambridge: “A Design Engineering Approach for Evolving Interactive Systems
- Professor Roderick Murray-Smith, Glasgow University: “Stratified, Computational Interaction via Machine Learning”
Talk data (abstracts, bios) below.Â
Adjunct event: On June 11, 2018, at 12.00 (T2, Konemiehentie 2, Aalto University): The defense of MSc. Anna Feit. Thesis title “Assignment Problems for Optimizing Text Input”. Opponent: Dr. Shumin Zhai, Google. Link:Â http://elec.aalto.fi/en/midcom-serveattachmentguid-1e85371d2bffc4e537111e8973917f0885c13601360/anna_feit_notice_of_dissertation_defence2017_en.pdf
TALK DATA
1. Progresses and Open Research Questions in Text Input – A Select ReviewÂ
Shumin Zhai, GoogleÂ
Abstract: Developing smarter, more efficient, easy to learn, and fun to use keyboards has presented many fascinating human factors and machine intelligence research and design questions. For nearly 20 years I have been involved in the evolution of this area in different roles and approaches – traditional academic research, innovation start-up, and large-scale product development. In this talk I will review and synthesize some of the progress and open research questions my colleagues and I have contributed directly through both publications and product development, including the cost and benefit predictions and suggestions, the power of machine/statistical intelligence, the human performance models pertinent to the design of modern keyboards, spatial scaling effect in device sizes, the difficult trade-off in ease of learning vs. efficiency, and the challenges of evaluating the longitudinal effects of personalization and adaptation. Through this select research review, I will illustrate why the combination of machine intelligence and human factors holds the future of human-computer interaction, and information technology at large, yet the emphasis on data-based ML vs. HCI understanding-based design will continue to shift back and forth.
Bio: Shumin Zhai is a Principal Scientist at Google where he leads and directs research, design, and development of input methods and haptics systems. His research career has contributed to theoretical models and understandings of human-computer interaction as well as practical user interface designs and product innovations. He originated the sokgraph (“shorthand on keyboard graphsâ€) or “shape writing†hypothesis. With his then PhD student Per Ola Kristensson, and later engineers at Google he has led the research, design, and development of generations of modern smart keyboards, from the world’s first swiping-based keyboard to Google’s Gboard with nearly a billion installs today. His publications have won the ACM UIST Lasting Impact Award (with Per Ola Kristensson) and an IEEE Computer Society Best Paper Award ( with Johnny Accot and Rogier Woltjer). He served as Papers Co-chair of CHI 2005, and the 4th Editor-in-Chief of ACM Transactions on Computer-Human Interaction (2009-2015). He received his Ph.D. degree from the University of Toronto in 1995. In 2006, he was selected as one of ACM’s inaugural class of Distinguished Scientists. In 2010 he was named Member of the CHI Academy and Fellow of the ACM.
2. A Design Engineering Approach for Evolving Interactive Systems
Per Ola Kristensson, Cambridge University
Abstract: Interactive systems are often evaluated in A/B comparisons in which a new technique or system is evaluated against some kind of baseline. While such studies may demonstrate progress in relation to some preset criteria, such as performance, they are unable to identify robust evidence-based solution principles capable of informing the design of a variety of interactive systems. I will present a complementary methodology for designing, verifying and validating interactive systems grounded in design engineering and demonstrate how such an approach can result in robust and versatile solution principles.
Bio: Per Ola Kristensson is a University Reader in Interactive Systems Engineering in the Department of Engineering at the University of Cambridge and a Fellow of Trinity College, Cambridge. He is interested in designing intelligent interactive systems that enable people to be more creative, expressive and satisfied in their daily lives. His PhD thesis was on gesture keyboard technology for touchscreens and in 2007 he co-founded ShapeWriter, Inc. to commercialise this technology. He was the Director of Engineering of this company until it was acquired by Nuance Communications in 2010. ShapeWriter was selected as the 8th best iPhone application by Time magazine in 2008 and won a Google Android ADC50 developer award in the same year. He did his doctoral work at the Institute of Technology at Linköping University, Sweden and at IBM Almaden Research Center in San Jose, California, USA (Ph.D. Computer Science 2007). In 2008-2011 he was a Junior Research Fellow at the University of Cambridge (Darwin College) and in 2011-2014 he was a Lecturer at the University of St Andrews. He is an Honorary Associate Professor (Docent) in Computer and Systems Science at Stockholm University, Sweden and an Honorary Reader at the University of St Andrews. In 2013 he was recognised as an Innovator Under 35 (TR35) by MIT Technology Review and appointed a Member of the Royal Society of Edinburgh Young Academy of Scotland. In 2014 he won the ACM User Interface Software and Technology (UIST) Lasting Impact Award and the Royal Society of Edinburgh Early Career Prize in Physical Sciences, the Sir Thomas Makdougall Brisbane Medal. He is an Associate Editor of ACM Transactions on Computer-Human Interaction and ACM Transactions on Intelligent Interactive Systems.
3. Stratified, Computational Interaction via Machine Learning
Roderick Murray-Smith, Glasgow University
Abstract: I will present a control loop framework which enables humans to flexibly adapt their level of engagement in human–computer interaction loops by delegating varying elements of sensing, actuation and control to computational algorithms. I will give examples of the use of deep convolutional networks in: modelling and inferring hand pose, single pixel cameras for vision in non-visible wavelengths and in a music information retrieval system. In each case, I will explore how the user can adapt the nature of their closed-loop interaction, depending on context. I will also provide an outlook to how the closed-loop approach will change our approach to larger scale data science.Â
Bio: Roderick Murray-Smith is a Professor of Computing Science at Glasgow University, leading the Inference, Dynamics and Interaction research group, and heads the 50-strong Section on Information, Data and Analysis, which also includes the Information Retrieval, Computer Vision & Autonomous systems, and IDEAS Big Data groups. He works in the overlap between machine learning, interaction design and control theory. In recent years his research has included multimodal sensor-based interaction with mobile devices, mobile spatial interaction, AR/VR, Brain-Computer interaction and nonparametric machine learning. Prior to this he held positions at the Hamilton Institute, NUIM, Technical University of Denmark, M.I.T. (Mike Jordan’s lab), and Daimler-Benz Research, Berlin, and was the Director of SICSA, the Scottish Informatics and Computing Science Alliance (all academic CS departments in Scotland). He works closely with the mobile phone industry, having worked together with Nokia, Samsung, FT/Orange, Microsoft and Bang & Olufsen. He was a member of Nokia’s Scientific Advisory Board and a member of the Scientific Advisory Board for the Finnish Centre of Excellence in Computational Inference Research. He has co-authored three edited volumes, 29 journal papers, 18 book chapters, and 88 conference papers.