BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Memento EPFL//
BEGIN:VEVENT
SUMMARY:IC Colloquium: From Programs to Interpretable Deep Models\, and Ba
 ck
DTSTART:20181030T110000
DTEND:20181030T121500
DTSTAMP:20260406T152225Z
UID:994ac007c7a296cbad8c934fb034e0079f3b9da0edff86de0afe6f13
CATEGORIES:Conferences - Seminars
DESCRIPTION:By: Eran Yahav - Technion Israel Institute of Technology\nVide
 o of his talk\n\nAbstract:\nIn this talk\, we demonstrate how deep learnin
 g over programs is used to provide (preliminary) augmented programmer inte
 lligence. In the first part of the talk\, we show how deep learning over p
 rograms is used to tackle tasks like code completion\, code summarization\
 , and captioning.\nWe describe a general path-based representation of sour
 ce code that can be used across programming languages and learning tasks\,
  and discuss how this representation enables different learning algorithms
 . In the second part\, we describe techniques for extracting interpretable
  representations from deep models\, shedding light on what has actually be
 en learned in various tasks.\n\nBio:\nEran Yahav is a faculty member at th
 e Computer Science Department\, Technion\, Israel. His research interests 
 include program synthesis\, machine learning and information-retrieval tec
 hniques for PL\, program analysis\, abstract interpretation\, verification
 \, programming Languages\, and software engineering. He is a recipient of 
 an European Research Council (ERC) grant PRIME (Programming with Millions 
 of Examples). He is also a senior technology advisor at Codota. Prior to j
 oining Technion\, he was a research staff member at IBM Research.\n\n\nMor
 e information
LOCATION:BC 420 https://plan.epfl.ch/?room==BC%20420
STATUS:CONFIRMED
END:VEVENT
END:VCALENDAR