Safety Properties of Inductive Logic Programming

Gavin Leech*, Nandi Schoots, Joar Skalse

*Corresponding author for this work

Research output: Contribution to conferenceConference Paperpeer-review

Abstract

This paper investigates the safety properties of inductive logic programming (ILP), particularly as compared to deep learning systems.
We consider the following properties: ease of model specification; robustness to input change; control over inductive bias; verification of specifications; post-hoc model editing; transfer learning; and interpretability.
We find that ILP satisfies many of these properties in some domains.
Lastly, we propose a hybrid system using ILP as a preprocessor to generate specifications for other ML systems.
Original languageEnglish
Publication statusAccepted/In press - 2021
EventAAAI Workshop on Artificial Intelligence Safety 2021 -
Duration: 8 Feb 2021 → …

Workshop

WorkshopAAAI Workshop on Artificial Intelligence Safety 2021
Abbreviated titleSafeAI 2021
Period8/02/21 → …

Cite this