Andrew Cropper


I am a junior research fellow at the University of Oxford.

I design machine learning algorithms that learn to write computer programs. I focus on inductive logic programming (ILP), which combines machine learning and mathematical logic.

I developed the ILP systems Metagol and Popper.

Email CV


Publications

DBLP Scholar

Journals

  1. Inductive general game playing
    A. Cropper, R. Evans, and M. Law
    Machine learning 2020
    slides code dataset
  2. Logical minimisation of metarules
    A. Cropper and S. Tourret
    Machine learning 2020
    slides code
  3. Learning higher-order logic programs
    A. Cropper, R. Morel, and S.H. Muggleton
    Machine learning 2020
    slides code
  4. Learning efficient logic programs
    A. Cropper and S.H. Muggleton
    Machine learning 2019
    slides code

Conferences

  1. Learning large logic programs by going beyond entailment
    A. Cropper and S. Dumančić
    IJCAI 2020
  2. Turning 30: new ideas in inductive logic programming
    A. Cropper, Dumančić, and S.H. Muggleton
    IJCAI 2020
  3. Forgetting to learn logic programs
    A. Cropper
    AAAI 2020
    slides code
  4. Learning higher-order programs through predicate invention
    A. Cropper, R. Morel, and S.H. Muggleton
    AAAI 2020
    slides
  5. Playgol: learning programs through play
    A. Cropper
    IJCAI 2019
    slides code
  6. SLD-resolution reduction of second-order horn fragments
    S. Tourret and A. Cropper
    JELIA 2019
  7. Typed meta-interpretive learning of logic programs
    R. Morel, A. Cropper, and L. Ong
    JELIA 2019
    slides code
  8. Derivation reduction of metarules in meta-interpretive learning
    A. Cropper and S. Tourret
    ILP 2018
    slides code
  9. Learning higher-order logic programs through abstraction and invention
    A. Cropper and S.H. Muggleton
    IJCAI 2016
    slides code
  10. Logic-based inductive synthesis of efficient programs
    A. Cropper
    IJCAI 2016
    slides
  11. Learning efficient logical robot strategies involving composable objects
    A. Cropper and S.H. Muggleton
    IJCAI 2015
    slides code
  12. Learning efficient logic programs
    A. Cropper
    IJCAI 2015
    slides
  13. Meta-interpretive learning of data transformation programs
    A. Cropper, A. Tamaddoni-Nezhad, and S.H. Muggleton
    ILP 2015
    slides code
  14. Typed meta-interpretive learning for proof strategies
    C. Farquhar, G. Grov, A. Cropper, S.H. Muggleton, and A. Bundy
    ILP 2015
  15. Can predicate invention compensate for incomplete background knowledge?
    A. Cropper and S.H. Muggleton
    SCAI 2015
    slides
  16. Logical minimisation of meta-rules within meta-interpretive learning
    A. Cropper and S.H. Muggleton
    ILP 2014
    slides

Workshops

  1. SLD-resolution reduction of second-order Horn fragments
    S. Tourret and A. Cropper
    Termgraph 2018
  2. Identifying and inferring objects from textual descriptions of scenes from books
    A. Cropper
    ICCSW 2014
    slides

Others

  1. Learning programs by learning from failures
    A. Cropper and R. Morel
    Under review
  2. Knowledge refactoring for program induction
    S. Dumančić and A. Cropper
    In preparation.
  3. Inductive logic programming at 30: a new introduction
    A. Cropper and S. Dumančić.
    In preparation.

Theses

  1. Efficiently learning efficient programs
    A. Cropper. PhD thesis, Imperial College London, 2017.
  2. Modelling stock volume using Twitter
    A. Cropper. MSc thesis, University of Oxford, 2011.

Talks