Katsumi Inoue

Meta-Interpretive Learning Using HEX-Programs

2019

Meta-Interpretive Learning (MIL) is a recent approach for Inductive Logic Programming (ILP) implemented in Prolog. Alternatively, MIL-problems can be solved by using Answer Set Programming (ASP), which may result in performance gains due to efficient …

Counterfactual Explanations for Learning From Interpretation Transitions

2025 · HAL (Le Centre pour la Communication Scientifique Directe)

<div> Counterfactual explanations are instrumental in helping humans gain insight into the decision-making processes of artificial intelligence systems by illustrating the effects of altering specific input variables. By presenting hypothetical scenarios, they foster transparency in …

Formally Explaining Decision Tree Models with Answer Set Programming

2026 · Electronic Proceedings in Theoretical Computer Science

Decision tree models, including random forests and gradient-boosted decision trees, are widely used in machine learning due to their high predictive performance. However, their complex structures often make them difficult to interpret, especially in safety-critical …

Towards End-to-End ASP Computation

2026 · Neurosymbolic Artificial Intelligence

We propose an end-to-end approach for Answer Set Programming (ASP) and linear algebraically compute stable models satisfying given constraints. The idea is to implement Lin-Zhao’s theorem together with constraints directly in vector spaces as numerical …