BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Memento EPFL//
BEGIN:VEVENT
SUMMARY:IC Colloquium : Programming with Probabilistic Graphical Models
DTSTART:20141215T161500
DTEND:20141215T173000
DTSTAMP:20260407T091029Z
UID:b7832ce30d078ccc900111e85cf6519542c7990773e3afc36d0b40ac
CATEGORIES:Conferences - Seminars
DESCRIPTION:By : Martin Vechev - ETH ZurichVideo of his talkAbstract : \nT
 he increased availability of massive codebases (“Big Code”) creates an
  exciting opportunity for new kinds of programming tools based on probabil
 istic models. Enabled by these models\, tomorrow’s tools will provide pr
 obabilistically likely solutions to programming tasks that are difficult o
 r impossible to solve with traditional techniques.\nIn this talk\, I will 
 present a new approach for building such tools based on structured predict
 ion with graphical models\, and in particular\, conditional random fields.
   These are powerful machine learning techniques popular in computer visi
 on -- by connecting these techniques to programs\, our work enables new ap
 plications not previously possible.\nAs an example\, I will discuss JSNice
  (http://jsnice.org)\, a system that automatically de-minifies JavaScript 
 programs by predicting statistically likely variable names and types. Sinc
 e its release few months ago\, JSNice has become a popular tool in the Jav
 aScript community and is regularly used by thousands of developers worldwi
 de.Bio :\nMartin Vechev is a tenure-track assistant professor of Computer 
 Science at ETH Zurich where he leads the Software Reliability Lab (http://
 www.srl.inf.ethz.ch/). Prior to ETH\, he was a Research Staff Member at th
 e IBM T.J. Watson Research Center in New York (2007 - 2011). He obtained h
 is PhD from Cambridge University in 2008. His research are in program anal
 ysis\, program synthesis\, concurrency\, and applications of machine learn
 ing.More information 
LOCATION:BC 420 https://plan.epfl.ch/?room==BC%20420
STATUS:CONFIRMED
END:VEVENT
END:VCALENDAR