Meta-interpretive learning logic programs

Add to your list(s) Download to your calendar using vCal

• Andrew Crooper, University of Oxford
• Thursday 03 May 2018, 14:00-15:00
• FW11.

If you have a question about this talk, please contact Victor Gomes.

This talk has been canceled/deleted

Meta-interpretive learning (MIL) is a form of machine learning which induces logic programs from examples. MIL is based on a Prolog meta-interpreter but additionally resolves goals with higher-order Horn clauses, and saves the higher-order substitutions to form logic programs. A basic MIL learner is only around 40 lines of Prolog and is able to learn a wide range of recursive programs, such as sorting algorithms and robot strategies. I will give an overview of MIL , including recent work on learning higher-order programs and learning minimal time-complexity programs.

This talk is part of the Logic and Semantics Seminar (Computer Laboratory) series.

This talk is included in these lists:

This talk is not included in any other list

Note that ex-directory lists are not shown.