Dr Jay Morgan

Tutor

Computer Science

j.p.morgan@swansea.ac.uk

Basic Welsh Speaker

Admin - 015
Ground Floor
Computational Foundry
Bay Campus

Research Links

https://orcid.org/0000-0003-3719-362X

ResearchGate

Google Scholar

Scopus

About

Dr Jay Paul Morgan received his PhD from the Department of Computer Science, Swansea University. This work develops methods of how to combine expert domain knowledge with Deep Neural Networks in many scientific areas. Jay, through this PhD, has worked in the domains of: Quantum Chemistry, Linguistics, and Astrophysics.

Later, Jay held a post-doctoral position at the University of Toulon, France, as part of the CNRS-LIS Laboratory. This work, in collaboration with the Paris-Meudon Observatory, investigated how preprocessing techniques can improve the imaging of our Sun.

Jay is now currently a Tutor in Computer Science at Swansea University, where he is part of the Theoretical Computer Science research group. Jay is also part of the Swansea Team Researching Online Grooming (STRONG) and Swansea Icons Norm Group (SING) hosted in Psychology.

Personal website

Areas Of Expertise

Deep Learning
Natural Language Processing

Career Highlights

Teaching Interests

Statistics

Machine Learning

Programming Languages

Publications

Research Highlights

Chaoui, A., Morgan, J., Paiement, A., & Aboudarham, J. (2024). Removing cloud shadows from ground-based solar imagery. Machine Vision and Applications, 35(6)
https://doi.org/10.1007/s00138-024-01607-2, SU Repository: https://cronfa.swan.ac.uk/Record/cronfa67663
Morgan, J., Morgan, J., Paiement, A., Williams, J., Wyner, A., & Seisenberger, M. (2018). A Chatbot Framework for the Children’s Legal Centre. In Frontiers in Artificial Intelligence and Applications (pp. 205-209).
https://doi.org/10.3233/978-1-61499-935-5-205, SU Repository: https://cronfa.swan.ac.uk/Record/cronfa48384
http://ebooks.iospress.nl/volumearticle/50853
Morgan, J. (2022). Strategies to use Prior Knowledge to Improve the Performance of Deep Learning (Subtitle) An Approach Towards Trustable Machine Learning Systems
https://doi.org/10.23889/SUthesis.59258, SU Repository: https://cronfa.swan.ac.uk/Record/cronfa59258
Morgan, J., Paiement, A., & Klinke, C. (2023). Domain-informed graph neural networks: A quantum chemistry case study. Neural Networks, 165, 938-952.
https://doi.org/10.1016/j.neunet.2023.06.030, SU Repository: https://cronfa.swan.ac.uk/Record/cronfa63771
Morgan, J., Crook, T., Morgan, J., Pauly, A., & Roggenbach, M. (2023). A Computability Perspective on (Verified) Machine Learning. In Recent Trends in Algebraic Development Techniques (pp. 63-80). Springer Nature Switzerland.
https://doi.org/10.1007/978-3-031-43345-0_3, SU Repository: https://cronfa.swan.ac.uk/Record/cronfa63849
Hepburn-Dickins, F., Jones, M., Edwards, M., Morgan, J., & Bell, S. (n.d.) SIGNN - Star Identification using Graph Neural Networks. In Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), Feb. 2025
SU Repository: https://cronfa.swan.ac.uk/Record/cronfa68091

All Research

Journal Articles

Chaoui, A., Morgan, J., Paiement, A., & Aboudarham, J. (2024). Removing cloud shadows from ground-based solar imagery. Machine Vision and Applications, 35(6)
https://doi.org/10.1007/s00138-024-01607-2, SU Repository: https://cronfa.swan.ac.uk/Record/cronfa67663
Morgan, J., Paiement, A., & Klinke, C. (2023). Domain-informed graph neural networks: A quantum chemistry case study. Neural Networks, 165, 938-952.
https://doi.org/10.1016/j.neunet.2023.06.030, SU Repository: https://cronfa.swan.ac.uk/Record/cronfa63771

Conference Contributions

Morgan, J., Crook, T., Morgan, J., Pauly, A., & Roggenbach, M. (2023). A Computability Perspective on (Verified) Machine Learning. In Recent Trends in Algebraic Development Techniques (pp. 63-80). Springer Nature Switzerland.
https://doi.org/10.1007/978-3-031-43345-0_3, SU Repository: https://cronfa.swan.ac.uk/Record/cronfa63849
Morgan, J., Morgan, J., Paiement, A., Williams, J., Wyner, A., & Seisenberger, M. (2018). A Chatbot Framework for the Children’s Legal Centre. In Frontiers in Artificial Intelligence and Applications (pp. 205-209).
https://doi.org/10.3233/978-1-61499-935-5-205, SU Repository: https://cronfa.swan.ac.uk/Record/cronfa48384
http://ebooks.iospress.nl/volumearticle/50853
Hepburn-Dickins, F., Jones, M., Edwards, M., Morgan, J., & Bell, S. (n.d.) SIGNN - Star Identification using Graph Neural Networks. In Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), Feb. 2025
SU Repository: https://cronfa.swan.ac.uk/Record/cronfa68091

Other Research Outputs

Morgan, J. (2022). Strategies to use Prior Knowledge to Improve the Performance of Deep Learning (Subtitle) An Approach Towards Trustable Machine Learning Systems
https://doi.org/10.23889/SUthesis.59258, SU Repository: https://cronfa.swan.ac.uk/Record/cronfa59258

Taught Modules

CSCM04 Software Team Project

The aim of this module is to provide students with the opportunity to apply their specialised knowledge to a realistic problem, and gain practical experience of the processes involved in the team-based production of software.