I am currently a research intern at the SMART Lab
of North Dakota State University, fortunate to be advised by
Prof. Armstrong Aboah.
I'm interested in building the next generation of medical AI systems.
In general,
I study and explore methods and techniques that can advance medical AI, by
leveraging multimodal approaches to learn representations from varied data modalities
and communicating the output through NLP.
I currently lead a group at ML Collective,
working on a project related to multilingual multimodal models and dataset curation methods within the African context.
In parallel, I lead another group focused on problems around self-supervised learning for small datasets in healthcare.
Prior to this, I received my bachelor's degree in Computer Science from the University for
Development Studies. After that, I spent some time as a research assistant, exploring generative
models and their applications in healthcare under the guidance of
Prof. Mohammed Ibrahim Daabo.
Outside my academic pursuits, I work as a full-stack engineer at
RGT
and enjoy growing things in my backyard.
| Oct. 2024 | I'll be serving as a reviewer for the Machine Learning for Health (ML4H) Symposium 2024 |
| Sep 2024 | I'll be serving as a reviewer for WiML workshop co-located with NeurIPS 2024 |
| Aug 2024 | Accepted into the Black in AI's Emerging Leaders in AI Scholar's program |
| Jul 2024 | I'll be presenting our work on Multimodal Multilingual African Dataset at ML Collective's 22nd Research Jam. |
| Jul 2024 | Joined SMART Lab @ NDSU as a Research Intern. |
| Jun 2024 | Joined @Black in AI Community. |
| Apr 2024 | Reviewing applications for Deep Learning Indaba 2024. |
| Nov 2023 | Started RA @ C.K.T University of Technology and Applied Sciences. |
The scope of Ghanaian Language; Twi datasets is insufficiently diverse, hindering a multitude of applications. To address this, we are curating a comprehensive corpus from literature, media, and synthetic data, covering formal, informal, and conversational registers. Using advanced data collection methods and rigorous validation, including transformer-based models and expert human verification, we ensure a high-quality data repository for robust NLP applications.
This research project focuses on enhancing the reliability of Residue Number System (RNS) arithmetic operations through the development of effective fault tolerance techniques. We also proposed a novel integrated fault-tolerant technique that combines redundant residues, modular checksums, and Reed-Solomon codes for error detection & correction. This integrated approach aims to improve fault coverage and reliability in RNS arithmetic operations compared to existing solutions, with manageable overhead.
B.Sc. Computer Science
