Ultra-strong machine learning: comprehensibility of programs learned with ILP

DOI10.1007/s10994-018-5707-3zbMath1461.68191OpenAlexW2802751390WikidataQ129871407 ScholiaQ129871407MaRDI QIDQ1621886

Alireza Tamaddoni-Nezhad, Christina Zeller, Ute Schmid, Tarek R. Besold, Stephen H. Muggleton

Publication date: 12 November 2018

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

Full work available at URL: https://doi.org/10.1007/s10994-018-5707-3

zbMATH Keywords

inductive logic programmingcomprehensibilityultra-strong machine learning

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Logic programming (68N17)

Related Items (10)

Inductive logic programming at 30 ⋮ Generating contrastive explanations for inductive logic programming based on a near miss approach ⋮ Unnamed Item ⋮ Some thoughts on knowledge-enhanced machine learning ⋮ Making sense of sensory input ⋮ Making sense of raw input ⋮ Editable machine learning models? A rule-based framework for user studies of explainability ⋮ Beneficial and harmful explanatory machine learning ⋮ On cognitive preferences and the plausibility of rule-based models ⋮ Learning any memory-less discrete semantics for dynamical systems represented by logic programs

Uses Software

• Aleph
• FOIL
• GOLEM

Cites Work

• Unnamed Item
• Unnamed Item
• ILP turns 20. Biography and future challenges
• Meta-interpretive learning of higher-order dyadic datalog: predicate invention revisited
• Interpretable classifiers using rules and Bayesian analysis: building a better stroke prediction model
• Argument based machine learning
• Meta-interpretive learning: application to grammatical inference
• Analytical Inductive Functional Programming

This page was built for publication: Ultra-strong machine learning: comprehensibility of programs learned with ILP