BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Imitation learning for structured prediction - Dr Andreas Vlachos
DTSTART:20190123T161500Z
DTEND:20190123T170000Z
UID:TALK115201@talks.cam.ac.uk
CONTACT:jo de bono
DESCRIPTION:In this talk\, I will introduce our work on imitation learning
 \, a learning paradigm originally developed to learn robotic controllers f
 rom demonstrations by humans\, e.g. autonomous helicopters from pilot's de
 monstrations. Recently\, algorithms for structure prediction were proposed
  under this paradigm and have been applied successfully to a number of tas
 ks such as dependency parsing\, information extraction\, coreference resol
 ution and semantic parsing. Key advantages are the ability to handle large
  output search spaces and to learn with non-decomposable loss functions. I
 n this talk I will give a detailed overview of imitation leaning\, discuss
  its relation to other learning paradigms\, describe some recent applicati
 ons\, including natural language generation\, abstract meaning representat
 ion parsing and its use in training recurrent neural networks.
LOCATION:Lecture Theatre 2\, Computer Laboratory
END:VEVENT
END:VCALENDAR