BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Two talks on visual analytics - Advait Sarkar\, Rainbow Group
DTSTART:20140717T101500Z
DTEND:20140717T111500Z
UID:TALK53465@talks.cam.ac.uk
CONTACT:Alan Blackwell
DESCRIPTION:These talks will be presented at Diagrams 2014 and Visual Lang
 uages and Human-Centric Computing 2014.\n\n1. Teach & Try: end-user machin
 e learning in spreadsheets\n\nThe modern economy increasingly relies on ex
 ploratory data analysis. Much of this is dependent on data scientists – 
 expert statisticians who process data using statistical tools and programm
 ing languages. Our goal is to offer some of this analytical power to end-u
 sers who have no statistical training through simple interaction technique
 s and metaphors. We describe a spreadsheet-based interaction technique tha
 t can be used to build and apply sophisticated statistical models such as 
 neural networks\, decision trees\, support vector machines and linear regr
 ession. We present the results of an experiment demonstrating that our pro
 totype can be understood and successfully applied by users having no profe
 ssional training in statistics or computing\, and that the experience of i
 nteracting with the system leads them to acquire some understanding of the
  concepts underlying exploratory statistical modelling.\n\n2. Hunches and 
 Sketches: interacting with big data through approximate visualisations\n\n
 Information visualisation presents powerful techniques for data analytics.
  However\, rendering visualisations of big datasets is impractical on comm
 odity hardware. There is increasing interest in approaches where data samp
 ling and probabilistic algorithms are used to support faster processing of
  large datasets. This approach to approximate computation has not yet paid
  close attention to the way that approximate visualisations are perceived 
 and employed by human users\, as a specific variety of diagrammatic conven
 tion. Our intent is to apply this understanding of approximate visualisati
 ons as a diagrammatic class to mainstream data science and information vis
 ualisation research.
LOCATION:Rainbow Seminar Room (SS03)\, Computer Laboratory
END:VEVENT
END:VCALENDAR