BEGIN:VCALENDAR
PRODID:-//Columba Systems Ltd//NONSGML CPNG/SpringViewer/ICal Output/3.3-
 M3//EN
VERSION:2.0
CALSCALE:GREGORIAN
METHOD:PUBLISH
BEGIN:VEVENT
DTSTAMP:20120222T115833Z
DTSTART:20120229T140000Z
DTEND:20120229T153000Z
SUMMARY:Automatic Feature Generation for Machine Learning for Compilers
UID:{http://www.columbasystems.com/customers/uom/gpp/eventid/}c4w-gyyb7r9
 o-2ktfl5
DESCRIPTION:Speaker: Dr Hugh Leather. University of Edinburgh\n\nHost: Al
 asdair Rawsthorne\n\nAbstract: \n\nMachine learning has been shown to au
 tomate and in some cases outperform hand crafted compiler optimizations.
   Central to such an approach is that machine learning techniques typica
 lly rely upon summaries or features of the program.  The quality of thes
 e features is critical to the accuracy of the resulting machine learned 
 algorithm\; no machine learning method will work well with poorly chosen
  features.  However\, due to the size and complexity of programs\, theor
 etically there are an infinite number of potential features to choose fr
 om.  The compiler writer now has to expend effort in choosing the best f
 eatures from this space.\n\nThe main part of this talk describes the wor
 k I have done attack this problem\, developing a novel mechanism to auto
 matically find those features which most improve the quality of the mach
 ine learned heuristic.  The feature space is described by a grammar and 
 is then searched with genetic programming and predictive modeling.  This
  was the first work to consider the searching the feature space and the 
 results will show considerable improvement over human derived features.\
 n\nIn the latter part of the talk I will describe some of the current pr
 ojects I am working on.\n\n
STATUS:TENTATIVE
TRANSP:TRANSPARENT
CLASS:PUBLIC
LOCATION:Lecture Theatre 1.4\, Kilburn Building\, Manchester
END:VEVENT
END:VCALENDAR