Stanislav Purgal, David Cerna, Cezary Kaliszyk,
"Learning Higher-Order Programs without Meta-Interpretive Learning"
, in Lud De Raedt: Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence, {IJCAI-22}, Serie Main Track, International Joint Conferences on Artificial Intelligence Organization, Seite(n) 2726--2733, 7-2022
Original Titel:
Learning Higher-Order Programs without Meta-Interpretive Learning
Sprache des Titels:
Englisch
Original Buchtitel:
Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence, {IJCAI-22}
Original Kurzfassung:
Learning complex programs through textit{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 textit{Learning From Failures} paradigm by higher-order definitions significantly improves learning performance without the burdensome human guidance required by existing systems. Furthermore, we provide a theoretical framework capturing the class of higher-order definitions handled by our extension.
Sprache der Kurzfassung:
Englisch
Veröffentlicher:
International Joint Conferences on Artificial Intelligence Organization
Forschungs-