Learning Higher-Order Logic Programs From Failures

Result code in IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F67985807%3A_____%2F22%3A00559054" target="_blank" >RIV/67985807:_____/22:00559054 - isvavai.cz</a>

Result on the web

<a href="https://dx.doi.org/10.24963/ijcai.2022/378" target="_blank" >https://dx.doi.org/10.24963/ijcai.2022/378</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.24963/ijcai.2022/378" target="_blank" >10.24963/ijcai.2022/378</a>

Result language

angličtina

Original language name

Learning Higher-Order Logic Programs From Failures

Original language description

Learning complex programs through inductive logic programming (ILP) remains a formidable challenge. Existing higher-order enabled ILP systems show improved accuracy and learning performance, though remain hampered by the limitations of the underlying learning mechanism. Experimental results show that our extension of the versatile Learning From Failures paradigm by higher-order definitions significantly improves learning performance without the666 burdensome human guidance required by existing systems. Our theoretical framework captures a class of higher-order definitions preserving soundness of existing subsumption-based pruning methods.

Czech name

—

Czech description

—

Type

D - Article in proceedings

CEP classification

—

OECD FORD branch

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Project

<a href="/en/project/EF18_053%2F0017594" target="_blank" >EF18_053/0017594: Supporting the internationalization of the Institute of Computer Science of the Czech Academy of Sciences</a><br>

Continuities

I - Institucionalni podpora na dlouhodoby koncepcni rozvoj vyzkumne organizace

Publication year

2022

Confidentiality

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Article name in the collection

Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence (IJCAI-22)

ISBN

978-1-956792-00-3

ISSN

—

e-ISSN

—

Number of pages

8

Pages from-to

2726-2733

Publisher name

International Joint Conferences on Artificial Intelligence

Place of publication

Vienna

Event location

Vienna

Event date

Jul 23, 2022

Type of event by nationality

WRD - Celosvětová akce

UT code for WoS article

—