Sebastian joined the Alan Turing Institute as an Enrichment Scheme Student. He is a second-year PhD student at the University of Manchester, supervised by Dr Hujun Yin, Prof. John Keane, and Prof. Mark Elliot. His research focuses on foundational aspects of Machine Learning related to lifelong learning and meta-learning (learning to learn), with publications at venues such as NeurIPS and ICLR. He works closely with Amazon’s Core Machine Learning Lab and previously worked as a data scientist for The Boston Consulting Group. He holds a BSc and MSc in Economics from the Stockholm School of Economics.
Sebastian focuses on key questions for enabling intelligent systems capable of dynamic adaption in non-stationary environments. His primary research interest lies in algorithms that learn how to learn from data, so called meta-learning. In contrast to classical learning, which focuses on solving a single task, meta-learning aims to develop agents that learn new tasks autonomously by drawing on previous experience. A key problem in meta-learning is deciding what information to share between tasks, when to share than information and what channels to use for the knowledge transfer.