BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Memento EPFL//
BEGIN:VEVENT
SUMMARY:IC Colloquium : Machine Learning for Programming
DTSTART:20170223T101500
DTEND:20170223T113000
DTSTAMP:20260407T101353Z
UID:448be9a6a27972858f2192aeca8dd1d59b6d71c62c4bac49dc669baa
CATEGORIES:Conferences - Seminars
DESCRIPTION:By : Veselin Raychev - ETH Zurich\nIC Faculty candidate\n\nAbs
 tract :\nIn this talk I will discuss a new generation of software tools ba
 sed on probabilistic models learned from large codebases. These tools leve
 rage the massive effort already spent by thousands of programmers and make
  useful predictions about new\, unseen programs\, thus helping to solve im
 portant and difficult software tasks. As an example\, I will illustrate se
 veral such practical systems including statistical code completion\, deobf
 uscation and defect prediction. Two of these systems (jsnice.org and apk-d
 eguard.com) are freely available and already have thousands of users. In a
 ddition\, I will also present some of the core machine learning techniques
  underlying our tools. I will discuss new probabilistic models of code tha
 t are more precise than state-of-the-art neural networks while requiring f
 ewer computational resources to train and use.\n\nBio :\nVeselin Raychev o
 btained his PhD from ETH Zurich in 2016 on the topic of “Learning from L
 arge Codebases”. Before this\, he worked as a software engineer at Googl
 e on the public transportation routing algorithm of Google Maps as well as
  several other projects. His research interests include machine learning\,
  program analysis\, program synthesis and algorithms. \n\nMore informatio
 n\n\n 
LOCATION:BC 420 https://plan.epfl.ch/?room==BC%20420
STATUS:CONFIRMED
END:VEVENT
END:VCALENDAR