activity
20102026
most citedQualitative Reasoning about Relative Direction on Adjustable Levels of Granularity

7 citations · 30 across the 12 of their papers we have counts for

collaborators
Showing cs.AIShow all

11 papers · 1 filter

cs.AI2026

NeSyCat Torch: A Differentiable Tensor Implementation of Categorical Semantics for Neurosymbolic Learning

Daniel Romero Schellhorn, Till Mossakowski, Björn Gehrke

Neurosymbolic semantics is fragmented: classical, fuzzy, probabilistic and neural systems each define truth by their own inductive rules. NeSyCat, extending ULLER, subsumes them un…

cs.AI2026

NeSyCat: A Monad-Based Categorical Semantics of the Neurosymbolic ULLER Framework

Daniel Romero Schellhorn, Till Mossakowski

ULLER (Unified Language for LEarning and Reasoning) offers a unified first-order logic (FOL) syntax, enabling its knowledge bases to be used directly across a wide range of neurosy…

cs.AI2026

The Possibility of Artificial Intelligence Becoming a Subject and the Alignment Problem

Till Mossakowski, Helena Esther Grass

The prospect of Artificial General Intelligence (AGI) is increasingly driving institutional decisions, and alignment of AGI is a hard problem. The currently dominant AI alignment s…

cs.AI2024

A fuzzy loss for ontology classification

Simon Flügel, Martin Glauer, Till Mossakowski +1

Deep learning models are often unaware of the inherent constraints of the task they are applied to. However, many downstream tasks require logical consistency. For ontology classif…

cs.AI20212 cited

Automated and Explainable Ontology Extension Based on Deep Learning: A Case Study in the Chemical Domain

Adel Memariani, Martin Glauer, Fabian Neuhaus +2

Reference ontologies provide a shared vocabulary and knowledge resource for their domain. Manual construction enables them to maintain a high quality, allowing them to be widely ac…

cs.AI20204 cited

Generic Ontology Design Patterns: Roles and Change over Time

Bernd Krieg-Brückner, Till Mossakowski, Mihai Codescu

In this chapter we propose Generic Ontology Design Patterns, GODPs, as a methodology for representing and instantiating ontology design patterns in a way that is adaptable, and all…