SICSA Summer School
Computational Interaction
Inference, optimisation and modelling for the engineering of interactive systems
22nd-26th June 2015
School of Computing Science, University of Glasgow
Themes
The theme of the summer school will be bringing computational tools to bear on enhancing interaction. This will encompass modelling of interaction, deriving and engaging with statistical models of content, automatic learning of preferences and computer-assisted optimisation of interfaces. Applied machine learning and appropriate quantitative analysis, suitable for real-time, closed-loop interactions will be key elements of the summer school school programme.The course content will include quantitative user modelling, machine learning, intelligent signal processing, crowdsourced and mass-scale interface optimisation techniques and automatic interface optimisation . The school will cover techniques interconnection of large statistical models and low-level interaction primitives, from optimising keyboards from language models, interface layout optimisation from preference learning, synthesising crowdsourced sensor data for ubiquitous computing, to optimising pointing and gesturing.
The distinctive flavour of the school will be in applying these techniques in concrete human-centred applications, with real-world data and real-time, online contexts.
There will be a strong focus on developing applied skills through practical sessions integrated into the school programme, which will give students practical experience in using well-grounded, cutting edge analysis, modelling and inference in engineering interactive systems.
One of the school outcomes will be a self-contained preprepared development and testing environment including development languages and libraries, datasets, links to online resources and the presented course content.
The summer school is sponsored by SICSA.
Speakers
The organising committee are:
Schedule
The summer school will begin at 9:30 on Monday 22nd June and close at 18:00 on Friday 26th June. There will be a mix of lectures and practical work, with presentations in the morning, followed by practical development sessions in the afternoon.Software
Software, data and documentation will be provided, but students should bring their own machines to participate in the practical exercises. The practical exercise will be primarily conducted in Python, using IPython notebooks.- The standard Python tutorial is here ; most programmers familiar with other languages should be able to pick Python very quickly.
- An introductory tutorial to IPython can be found here
- This is a very good set of tutorials on data processing and scientific visualisation in Python: Python Data Intro
- A video on using IPython with Pandas (the Python data manipulation library).
- A complete course on scientific analysis with Python
- scikit-learn (Python machine learning package) tutorial and introduction.
Topics
- Crash Course The school will open with an HCI-focused crash course on probability, statistics, machine learning and control theory. This will give the grounding in the basic concepts and skills in tools to apply these in practice. Students should have some basic familiarity with linear algebra and statistical notation, but nothing beyond a first-year undergraduate level. Students unfamiliar with machine learning might consider reviewing the introductory parts of the free online video lectures and textbook "Introduction to Statistical Learning" in advance of the school, although the later parts of this go beyond what will be covered in the school.
- Monday Crash course in machine learning, information theory and control theory from an HCI perspective. This course will give students the basic vocabulary and intuition for application in HCI, along with practical experience in using machine learning in interface problems.
- Tuesday Optimization methods can be used to find solutions to well-defined design problems. This course introduces the basic concepts and methods and shows applications that range from deciding a parameter of an interface to the construction of a whole interface design.
- Wednesday Gesture analysis. This course element will cover modelling of gestural behaviour and experimental data manipulation techniques.
- Thursday Control theory in HCI. This course will cover basic concepts in control theory, applied to HCI problems such as targeting and gesturing.
- Friday Learnind subjective functions. This course will cover machine learning and statistical modelling of user subjective functions (e.g. preferences) in interaction.
Poster session
There will be a poster session for students to briefly present their research on the evening on June 22nd. Attendees are requested to bring posters for this session (A1 format; poster boards will be provided).Credits
The summer school does not have a mechanism for awarding credits for participation. A formal certificate of completion will be issued to students who participate. along with a summary of the course topics and student engagement time. Propspective students may wish to verify with their own institution if they will award credit for a certain number of hours of participation, etc.Venue
The summer school will be held at the School of Computing Science, University of Glasgow, on Level 5 of the Sir Alwyn Williams Building. Students are requested to bring a laptop to engage in the interactive portions of the school -- lab machines are not availableTravel
The School of Computing Science is easily reached via the Hillhead Subway station. The nearest airport is Glasgow International Airport (GLA).Registration
Registration is available until May 15th 2015.Register online here
Fees
- Standard The standard registration fee is £250. This includes lunch and tea/coffee, but does not include any accommodation.
- SICSA For PhD students registered at SICSA institutions, registration is free; however, you must still formally register in advance. SICSA students will have to arrange their own travel and accommodation from local funds. There are a limited number of SICSA funded places available. [SICSA REGISTRATION CLOSED]
Payment
Registration fee payment details will be provided shortly. You may register online before payment, but registration will not be confirmed until payment has been processed.
Accommodation
The summer school can not provide accommodation for attending students. The University of Glasgow accommodation services have
some student hall rooms at £40-£60 per night, however, there are usually a limited number of places. The Queen Margaret Residences are well placed for travel to and from the summer school.
Alternatively, there are numerous hotels and B&Bs in the vicinity.
Contact
Contact John Williamson: jhw@dcs.gla.ac.uk with any questions relating to the summer school.
