Symbolic metaprogram search improves learning efficiency and explains rule learning in humans

Autor: Joshua S. Rule, Steven T. Piantadosi, Andrew Cropper, Kevin Ellis, Maxwell Nye, Joshua B. Tenenbaum

Publikováno v: Nature Communications, Vol 15, Iss 1, Pp 1-16 (2024)

Abstract Throughout their lives, humans seem to learn a variety of rules for things like applying category labels, following procedures, and explaining causal relationships. These rules are often algorithmically rich but are nonetheless acquired with

Externí odkaz: https://doaj.org/article/95ebeef2ed6c4cfbadf7273793a67684

Forgetting to Learn Logic Programs

Autor: Andrew Cropper

Publikováno v: AAAI

Most program induction approaches require predefined, often hand-engineered, background knowledge (BK). To overcome this limitation, we explore methods to automatically acquire BK through multi-task learning. In this approach, a learner adds learned

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::1e218f1309d38b4e2992ef5e4e6f8b53
https://doi.org/10.1609/aaai.v34i04.5776

Learning programs with magic values

Autor: Céline Hocquette, Andrew Cropper

A magic value in a program is a constant symbol that is essential for the execution of the program but has no clear explanation for its choice. Learning programs with magic values is difficult for existing program synthesis approaches. To overcome th

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::9a4c3d7ab8db5eacbc2d49ec0a884fd1

SLD-Resolution Reduction of Second-Order Horn Fragments

Autor: Andrew Cropper, Sophie Tourret

Publikováno v: Logics in Artificial Intelligence-16th European Conference, JELIA 2019, Rende, Italy, May 7-11, 2019, Proceedings
Logics in Artificial Intelligence-16th European Conference, JELIA 2019, Rende, Italy, May 7-11, 2019, Proceedings, pp.259-276, 2019, ⟨10.1007/978-3-030-19570-0_17⟩
LNCS, LNAI, JELIA
JELIA 2019-European Conference on Logics in Artificial Intelligence
JELIA 2019-European Conference on Logics in Artificial Intelligence, May 2019, Rende, Italy. pp.259-276, ⟨10.1007/978-3-030-19570-0_17⟩
Logics in Artificial Intelligence ISBN: 9783030195694
JELIA

International audience; ()[0000−0002−6070−796X] and Andrew Cropper 2[0000−0002−4543−7199] Abstract. We present the derivation reduction problem for SLD-resolution, the undecidable problem of finding a finite subset of a set of clauses fro

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::1200222a7f1ff1819496be86550c0e92
https://hal.archives-ouvertes.fr/hal-02988015/file/jelia2019tc.pdf

Learning large logic programs by going beyond entailment

Autor: Andrew Cropper, Sebastijan Dumancic

Publikováno v: IJCAI

A major challenge in inductive logic programming (ILP) is learning large programs. We argue that a key limitation of existing systems is that they use entailment to guide the hypothesis search. This approach is limited because entailment is a binary

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::1d4fbbcb1e4b44b34bcb16dd19f2918b
http://arxiv.org/abs/2004.09855