Kwabena Nuamah

Research Interests

My research interests include neuro-symbolic AI, knowledge representation, automated reasoning, question answering using inferences drawn from knowledge graphs, distributed learning and reasoning systems, and explainable AI. I am currently working on hybrid (neuro-symbolic) and compositional AI architectures.

I ran the FRANK Lab where we discuss ongoing research related to the FRANK (Functional Reasoner for Acquiring New Knowledge) question-answering system and related work including meta- and object-level inference and dealing with inconsistencies in the reasoning process of large language models (LLMs)

I am also a co-founder at Cognate Systems, a software company in Ghana.

Recent Activities/Awards

[ September 2024 ] Awarded a 9-month Opportunities Qualification Grant from Scotish Enterprise to begin work on commercialising ideas from my FRANK project.

[ January 2024 ] Awarded a 3-year University of Edinburgh Innovation Fellowship to explore a hybrid and compositional AI framework with an emphasis on translating research outputs into real-world applications. Watch interview on LinkedIn.

[ June 2023 ] Selected to participate in the 3-month Innovate UK ICURe Exploit programme.
We engaged with hundreds of individuals and companies globally to validate our ideas and commercial interest for our AI-based inference system. We were shortlisted for the Options Roundabout stage and our project was recommended for the spin-out route.

[ March 2023 ] Selected to participate in the 3-month Innovate UK ICURe Explore programme.

[ November 2021 ] Co-organised the Workshop on Knowledge Representation for Hybrid and Compositional AI (KRHCAI)
Kwabena Nuamah, Jeff Z. Pan, Pavan Kapanipathi and Efi Tsamoura. Organised in conjunction with KR 2021 (18th International Conference on Principles of Knowledge Representation and Reasoning).

Publications

Google Scholar Link

Nuamah, Kwabena and Bundy, Alan. ALIST: Associative Logic for Inference, Storage and Transfer. A Lingua Franca for Inference on the Web. 2023 (Under Review).
Bundy, Alan, and Nuamah, Kwabena. Unified Decomposition-Aggregation (UDA) Rules: Dynamic, Schematic, Novel Axioms. In International Conference on Intelligent Computer Mathematics (pp. 209-221). Springer, Cham., 2022
Ferguson, N., Guillou, Liane, Nuamah, Kwabena, and Bundy, Alan. Investigating the use of Paraphrase Generation for Question Reformulation in the FRANK QA System. 3rd International Workshop on HumanLike Computing (HLC). arXiv:2206.02737, 2022
Nuamah, Kwabena. Deep Algorithmic Question Answering: Towards a Compositionally Hybrid AI for Algorithmic Reasoning. Workshop on Knowledge Representation for Hybrid and Compositional AI, 2021
Fletcher, Thomas and Bundy, Alan and Nuamah, Kwabena. GPy-ABCD: A Configurable Automatic Bayesian Covariance Discovery Implementation. 8th ICML Workshop on Automated Machine Learning, 2021.
Nuamah, Kwabena, and Alan Bundy. Explainable Inference in the FRANK Query Answering System. ECAI 2020. IOS Press, 2020. 2441-2448.
Bundy, Alan, Kwabena Nuamah, and Christopher Lucas. Automated Reasoning in the Age of the Internet. International Conference on Artificial Intelligence and Symbolic Computation. Springer, Cham, 2018.
Nuamah, Kwabena, and Alan Bundy. Calculating Error Bars on Inferences from Web Data. Proceedings of SAI Intelligent Systems Conference. Springer, Cham, 2018.
Nuamah, Kwabena, Alan Bundy, and Christopher Lucas. "Functional Inferences Over Heterogeneous Data. International Conference on Web Reasoning and Rule Systems. Springer, Cham, 2016.

Student Supervision

Current Students

Najwa Alghamdi
Nick Ferguson
Ambrose Brown (Second Supervisor)
Weizhi Tang (Second Supervisor)

Past Students

Guifu Liu (Intern)
Thomas Fletcher (PhD)
Ruiqi (Ricky) Zhu (PhD)
Greg Brimble (MSc)
Yanzhou Li (MSc)