BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Meta-interpretive learning logic programs - Andrew Cropper\, Unive
 rsity of Oxford
DTSTART:20180313T140000Z
DTEND:20180313T150000Z
UID:TALK101104@talks.cam.ac.uk
CONTACT:Victor Gomes
DESCRIPTION:Meta-interpretive learning (MIL) is a form of machine\nlearnin
 g which induces logic programs from examples. MIL is based on a\nProlog me
 ta-interpreter but additionally resolves goals with\nhigher-order Horn cla
 uses\, and saves the higher-order substitutions to\nform logic programs. A
  basic MIL learner is only around 40 lines of\nProlog and is able to learn
  a wide range of recursive programs\, such\nas sorting algorithms and robo
 t strategies. I will give an overview of\nMIL\, including recent work on l
 earning higher-order programs and\nlearning minimal time-complexity progra
 ms.
LOCATION:FW26
END:VEVENT
END:VCALENDAR