I am a Research Officer at the National Research Council of Canada (NRC), and an Adjunct at Dal in the Faculty of Computer Science. At the NRC, my work focuses on the developement of AI for design problems. In this context, my researching aims to understand and improve the ability of AI methods to learn from limited and costly data. Amongst other things, I am actively working on deep learning from limited and imbalanced data and observation-cost-sensitive reinforcement leanring.
From 2016 - 2018, I held a postdoc at the University of Alberta in the Alberta Machine Intelligence Institute where I studied with Dr. Osmar Zaiane in the Department of Computer Science and collaborated with Dr. Alvaro R. Osornio-Vargas in the Dept. of Paediatrics. Recently, I spend three months at Dalhousie University researching class imbalance and learning from rare cases with Dr. Luis Torgo, which are topics of great interest to me.
I completed my PhD thesis under the supervision of Dr. Nathalie Japkowicz and Dr. Christopher Drummond entitled A Framework for Manifold-Based Synthetic Oversampling. My Masters in Computer Science was done under the supervision of Dr. John Oommen in 2010. The dissertation is entitled Modelling and Classifying Stochastically Episodic Events. My research focuses on real-world collaborations in health science, security and industry, and uses these as a gateway to understand how machine learning and data mining algorithms are impacted by adverse data domains.
My goal as a researcher is to a) advance our understanding of the impacts of complex datasets properties, b) use this knowledge to develop more robust algorithms, and c) apply these algorithms to improve health outcomes and industrial efficiency. My currenlty research is also exploring deep reinforcement learning. Philosophically, I am interested in questions related to how AI can be used to help support a greener, more equitable society.