Hello,

I am a PhD student in Computer Science at University College Dublin, working on machine learning and Explainable Artificial Intelligence (XAI). I am fortunate to be advised by Assoc. Prof. Georgiana Ifrim, and to be supported by Science Foundation Ireland (SFI) Centre for Reseach Training in Machine Learning.

My primary research interests are Interpretable Machine Learning and its application in Heathcare, Medicine, and Finance. In particular, I aspire to helping humans to communicate with machine learning systems by building tools to examine explanations of decisions made by machine learning (ML) models. Details of my current research is in my research summary and research statement. Topics that I currently focus includes:

• Evaluation: methods and metrics to quantitatively assess reasons for decisions made by ML models. Many ML-models, including deep learning models, are very complicated and unable to provide human being with explanations for their decisions. Scientists attempt to tackle this problem by provide post-hoc explanation methods (XAI methods), i.e. a method that aim to explain the model in question. However, these methods often creates another problem: they might not agree with each other. My research focuses on solving this problem by proposing a quantitative method and a metric to compare and assess these XAI methods.

• Knowledge: methods to learn new knowlege using machine learning system. With the proposed framework to evaluate XAI methods, my research aims to find out robust and legible explanations that can assist human in obtain new knowledge that was previously unknown, either by pointing out which part of the data is critical for a machine learning model, or troubleshooting a model by highlighting its inherent bias.

• Health Intelligence Application: machine learning for overcoming the knowledge and reasoning bottlenecks in biomedical and heathcare-related tasks: e.g. diagnosis, genetic understanding, antigen mapping, disease prevention, and sports analytics.

I also have broad interest in Responsible AI, Automated Reasoning, Deep Learning, Sequence Learning, and Time Series Analysis.