activity
20242026
collaborators

7 papers

cs.AI2026

PACE: A Neuro-Symbolic Framework for Plausible and Actionable Counterfactual Explanations

Pavel Iakovets, Liyanapathiranage Sudeepika Wajirakumari Samarathunga, Martin Thomas Horsch +1

Counterfactual explanations explain machine learning predictions by identifying minimal input changes that would alter a model's decision. Although many existing methods successful…

cond-mat.mtrl-sci2026

Artificial Intelligence in Materials Science and Engineering: Current Landscape, Key Challenges, and Future Trajectorie

Iman Peivaste, Salim Belouettar, Francesco Mercuri +15

Artificial Intelligence is rapidly transforming materials science and engineering, offering powerful tools to navigate complexity, accelerate discovery, and optimize material desig…

cond-mat.soft2025

Open questions on defining and computing the vapour-liquid surface tension by virial and test transformation approaches

Martin Thomas Horsch

This work addresses four problems in defining and computing the surface tension of vapour-liquid interfaces: (1) The apparent kinetic contribution to the surface tension, and what…

cond-mat.soft2025

Influence of the dividing surface notion on the formulation of Tolman's law

Martin Thomas Horsch

The influence of the surface curvature on the surface tension of small droplets at equilibrium with a surrounding vapour, or small bubbles at equilibrium with a surrounding liquid,…

cs.AI2024

Building Trustworthy AI: Transparent AI Systems via Large Language Models, Ontologies, and Logical Reasoning (TranspNet)

Fadi Al Machot, Martin Thomas Horsch, Habib Ullah

Growing concerns over the lack of transparency in AI, particularly in high-stakes fields like healthcare and finance, drive the need for explainable and trustworthy systems. While…

cs.AI2024

Symbolic-AI-Fusion Deep Learning (SAIF-DL): Encoding Knowledge into Training with Answer Set Programming Loss Penalties by a Novel Loss Function Approach

Fadi Al Machot, Martin Thomas Horsch, Habib Ullah

This paper presents a hybrid methodology that enhances the training process of deep learning (DL) models by embedding domain expert knowledge using ontologies and answer set progra…