Results 21 to 30 of about 134,060 (299)
Deep Inductive Logic Programming meets Reinforcement Learning [PDF]
International Conference on Logic Programming, 2023 One approach to explaining the hierarchical levels of understanding within a machine learning model is the symbolic method of inductive logic programming (ILP), which is data efficient and capable of learning first-order logic rules that can entail data ...
Andreas Bueff, Vaishak Belle
semanticscholar +1 more source
Towards integrating fuzzy logic capabilities into an ontology-based Inductive Logic Programming framework [PDF]
International Conference on Intelligent Systems Design and Applications, 2011 Josué Iglesias, Jens Lehmann
semanticscholar +2 more sources
Generating contrastive explanations for inductive logic programming based on a near miss approach [PDF]
Machine-mediated learning, 2021 In recent research, human-understandable explanations of machine learning models have received a lot of attention. Often explanations are given in form of model simplifications or visualizations. However, as shown in cognitive science as well as in early
Johannes Rabold, M. Siebers, Ute Schmid
semanticscholar +1 more source
A Critical Review of Inductive Logic Programming Techniques for Explainable AI [PDF]
IEEE Transactions on Neural Networks and Learning Systems, 2021 Despite recent advances in modern machine learning algorithms, the opaqueness of their underlying mechanisms continues to be an obstacle in adoption.
Zheng Zhang, L. Yilmaz, Bo Liu
semanticscholar +1 more source
Rule Learning over Knowledge Graphs: A Review [PDF]
Transactions on Graph Data and Knowledge, 2023 Compared to black-box neural networks, logic rules express explicit knowledge, can provide human-understandable explanations for reasoning processes, and have found their wide application in knowledge graphs and other downstream tasks.
Wu, Hong +4 more
doaj +1 more source
Turning 30: New Ideas in Inductive Logic Programming [PDF]
International Joint Conference on Artificial Intelligence, 2020 Common criticisms of state-of-the-art machine learning include poor generalisation, a lack of interpretability, and a need for large amounts of training data.
Andrew Cropper +2 more
semanticscholar +1 more source
Inductive logic programming at 30: a new introduction [PDF]
Journal of Artificial Intelligence Research, 2020 Inductive logic programming (ILP) is a form of machine learning. The goal of ILP is to induce a hypothesis (a set of logical rules) that generalises training examples. As ILP turns 30, we provide a new introduction to the field.
Andrew Cropper, Sebastijan Dumancic
semanticscholar +1 more source
المنطق الماصدقي: تاريخه وخصائصه وتطبيقاته [PDF]
Maǧallaẗ Kulliyyaẗ Al-ādāb Ǧāmiʿaẗ Būrsaʿīd, 2022 لم يُعرف التمييز بين حدي القضية - المفهوم والماصدق - بشکلٍ انفصالي کلٌ على حدة إلاَّ في وقتٍ متأخر؛ فکل قضية تتکون من حدين هما المفهوم والماصدق، والعلاقة بينهما عکسية کما نعلم؛ کلما زاد المفهوم قل الماصدق والعکس، لکن هذا لا يعني القول بأحدهما فقط دون ...
محمد سيد محمد أبوالعلا
doaj +1 more source
Extending Coinductive Logic Programming with Co-Facts [PDF]
Electronic Proceedings in Theoretical Computer Science, 2017 We introduce a generalized logic programming paradigm where programs, consisting of facts and rules with the usual syntax, can be enriched by co-facts, which syntactically resemble facts but have a special meaning.
Davide Ancona +2 more
doaj +1 more source