I'm a PhD candidate at the University of Sheffield, researching AI methodolgies for speech and
language technologies.
My focus is on continual learning and meta-learning, "learning to learn", for multimodal
systems with a focus on healthcare applications.
PhD Summary -
Artificial intelligence (AI) has exploded into the mainstream in recent years, paving the way
for
the development of large language models (LLM) and large multimodal models (MM).
These models are allowing for new and innovative ways of tackling societal problems. This
increased
use of LLMs and MMs is having a great influence in healthcare in many applications,
including prediction of patient outcomes, medical decision making, and the potential to fuse and
infer over a multitude of patient signals.
Consequently, the critical and high-impact nature of this environment is fuelling the need for a
model's ability to detect and adapt to adversarial behaviours over time.
Great strides have been made in incorporating LLMs into a healthcare setting.
These sophisticated models now possess the ability to surpass human performance in tasks such as
medical exams.
However, LLM training processes that focus on generalising across a particular data distribution
from a particular point in time are a cause for concern.
This style of model training is static, consequently paving the way for models that could become
misaligned with the environment in which they operate.
In this project, we look to learn and build mechanisms for combating a model's misalignment,
helping
models to continually learn.
The multimodal nature of medicine requires the development of MMs in order to process and
interpret
multiple types of data.
In collaboration with local healthcare organisations, this PhD project is aimed at harnessing
the
potential of LLMs and MMs in the medical domain to improve healthcare outcomes, enhance patient
care, and assist healthcare professionals.
It will in particular focus on how LLMs and MMs can be adopted to handle and interpret the
highly
granular data in medicine while ensuring the models remain robust to data changes and task
changes
over periods of time.
Publications
Understanding Inflicted Injuries in Young Children: Toward an Ontology-based Approach
Maikore, F., Mazumdar, S. Offiah, A., Hughes, A., Roychowdhury, S., Hocking, K., Lanfranchi, V. 2024, Nov.
PhD - Speech and Language Technologies in Artifical
Intelligence
September 2023 - Present
University of Wolverhampton
Masters of Arts - Computational Linguistics
Distinction (85%)
Research title: Identifying and Aligning Medical Claims with Evidenced-based Medicine
September 2021 - September 2023
Nottingham Trent University
Bachelor of Science (Hons) - Computer Systems Engineering
First Class (71%)
Research title: Semantic Framework for Intelligent Classification and Search of
Medical Articles
September 2009 - June 2013
Experience
Software Engineer
Data Language
Working as a Lead Software Engineer delivering data and software solutions for a wide range
of clients.
July 2014 - Present
Web Engineer
Bipolar UK
I built a mood disorder questionnaire for self-assessment of bipolar.
September 2022 - October 2022
Mobile Engineer
Bipolar UK
Crown required a mobile app for delivering specialised reports for meeting health and safety
requirements.
July 2019 - January 2021
Software Developer
Ontoba
Software development at Ontoba. Specialising in building semantic publishing systems and high
performance delivery of content through ontology-based customer driven applications.