Generating contrastive explanations for inductive logic programming based on a near miss approach

DOI10.1007/s10994-021-06048-wOpenAlexW3202365497MaRDI QIDQ2163226

Ute Schmid, Johannes Rabold, Michael Siebers

Publication date: 10 August 2022

Published in: Machine Learning (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2106.08064

zbMATH Keywords

inductive logic programmingexplainable AIcontrastive explanationsnear miss examplesrelational concepts

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05)

Uses Software

• RelNN

Cites Work

• Prototype selection for interpretable classification
• A Prolog-like inference system for computing minimum-cost abductive explanations in natural-language interpretation
• Ultra-strong machine learning: comprehensibility of programs learned with ILP
• Beneficial and harmful explanatory machine learning
• The teaching size: computable teachers and learners for universal languages
• Explanation in artificial intelligence: insights from the social sciences
• Inductive Logic Programming: Theory and methods
• Unnamed Item
• Unnamed Item
• Unnamed Item

This page was built for publication: Generating contrastive explanations for inductive logic programming based on a near miss approach