- Herron, D., Jiménez-Ruiz, E. and Weyde, T. (2024). On the Potential of Logic and Reasoning in Neurosymbolic Systems using OWL-based Knowledge Graphs. Neurosymbolic Artificial Intelligence, 1.
Contact details
Address
Northampton Square
London EC1V 0HB
United Kingdom
About
Overview
David is a PhD student of Artificial Intelligence. His research focuses on neurosymbolic AI, a subfield of AI concerned with exploring ways of combining the neural (connectionist) and symbolic traditions of AI in order to get the best of both. Neural networks are good at (deep) learning; symbolic methods are good at knowledge representation (facts and rules) and reasoning (using logic). Neurosymbolic AI blends the two. David's research uses Semantic Web technologies (OWL ontologies and RDF knowledge graphs) as the symbolic components of hybrid, neurosymbolic systems in the application task of visual relationship detection in images. The central concern is to explore ways of leveraging the reasoning capabilities of OWL-based knowledge graphs to guide and enhance neural learning and otherwise deliver improved predictive performance.
David's research is subsidised by a studentship from City, University of London. His research is supervised by Dr. Ernesto Jimenez-Ruiz, Dr. Giacomo Tarroni and Dr. Tillman Weyde.
David on GitHub: https://djherron.github.io/
Qualifications
- MSc, Data Science, City, Univerity of London, UK
- MSc, Applied Statistics and Operational Research, Birkbeck, University of London, UK
- MBA (finance emphasis), Wilfrid Laurier University, Canada
- BMath (Computer Science & Statistics), University of Waterloo, Canada
- BA (English & History), Queen's University, Canada
Publications
Publications by category
Conference paper/proceedings
- Herron, D., Jiménez-Ruiz, E. and Weyde, T. (2023). On the Benefits of OWL-based Knowledge Graphs for Neural-Symbolic Systems. 17th International Workshop on Neural-Symbolic Learning and Reasoning 3-5 July, La Certosa di Pontignano, Siena, Italy.