Tameem Adel was a research fellow at LCFI from 2017 – 2020 when he left to take up a lectureship at the University of Glasgow. His main research interests are machine learning and artificial intelligence, more specifically probabilistic graphical models, Bayesian learning and inference, medical applications of machine learning, deep learning and domain adaptation. He has also worked on developing transparent machine learning algorithms and on providing explanations of decisions taken by deep models.
He has obtained his PhD from University of Waterloo in 2014, advised by Prof. Ali Ghodsi. After that, he was a postdoctoral researcher at the Amsterdam Machine Learning Lab, advised by Prof. Max Welling.
TibGM: A Transferable and Information-Based Graphical Model Approach for Reinforcement Learning. Proceedings of the 36th International Conference on Machine Learning, PMLR 97:71-81, 2019. One of the challenges to reinforcement learning (RL) is scalable transferability among complex tasks. Incorporating a graphical model (GM), along with the rich family of related methods, as a basis for RL frameworks […]
Exploring Properties of the Deep Image Prior. NeurIPS Workshop on Solving inverse problems with deep networks, Vancouver, 2019. The Deep Image Prior (DIP, Ulyanov et al., 2017) is a fascinating recent approach for recovering images which appear natural, yet is not fully understood. This work investigates the properties of the early outputs of the DIP. First, […]
One-network Adversarial Fairness AAAI19, Thirty-Third AAAI Conference on Artificial Intelligence (2019) Honolulu, Hawaii, USA There is currently a great expansion of the impact of machine learning algorithms on our lives, prompting the need for ob- jectives other than pure performance, including fairness. Fair- ness here means that the outcome of an automated decision- making system should […]
Discovering Interpretable Representations for Both Deep Generative and Discriminative Models Tameem Adel, Zoubin Ghahramani, Adrian Weller, Proceedings of the 35th International Conference on Machine Learning, PMLR 80:50-59, 2018. Abstract Interpretability of representations in both deep generative and discriminative models is highly desirable. Current methods jointly optimize an objective combining accuracy and interpretability. However, this may […]
This project is developing processes to ensure that AI systems are transparent, reliable and trustworthy. As AI systems are widely deployed in real-world settings, it is critical for us to understand the mechanisms by which they take decisions, when they can be trusted to perform well, and when they may fail. This project addresses these […]
