no code implementations • 17 Jul 2023 • Lauren Nicole DeLong, Ramon Fernández Mir, Zonglin Ji, Fiona Niamh Coulter Smith, Jacques D. Fleuriot
Biomedical datasets are often modeled as knowledge graphs (KGs) because they capture the multi-relational, heterogeneous, and dynamic natures of biomedical systems.
no code implementations • 14 Feb 2023 • Lauren Nicole DeLong, Ramon Fernández Mir, Jacques D. Fleuriot
As knowledge graphs are becoming a popular way to represent heterogeneous and multi-relational data, methods for reasoning on graph structures have attempted to follow this neurosymbolic paradigm.
1 code implementation • 9 Sep 2022 • Jiawei Zheng, Petros Papapanagiotou, Jacques D. Fleuriot
However, this data is typically characterised by noise and uncertainty, in contrast to the assumption of a deterministic event log required by conformance checking algorithms.
no code implementations • 8 Jul 2022 • Mark Chevallier, Matthew Whyte, Jacques D. Fleuriot
We introduce a theorem proving approach to the specification and generation of temporal logical constraints for training neural networks.
no code implementations • 17 Jun 2021 • Colleen E. Charlton, Michael Tin Chung Poon, Paul M. Brennan, Jacques D. Fleuriot
The interpretability of the black box machine learning models is evaluated using two post-hoc explanation techniques, LIME and SHAP.
BIG-bench Machine Learning Interpretable Machine Learning +1