Edinburgh Research Explorer

Dr Michael Burke

Research Associate

Profile photo

Research Interests

My research interests are in the development of probabilistic machine learning and computer vision tools to solve problems in robotics. Specifically, I am interested in building robot perception capabilities for shared autonomy through automatic and lightly supervised machine learning that aims to infer human needs with as little burden on the user as possible, by making use of Bayesian probabilistic sampling and approximation strategies and leveraging advances in representation learning. A particular focus of my work lies in building interpretable machine learning algorithms for robotics, along with explanatory mechanisms, so as to boost trust in and advance the deployment of complex robotic systems.

Qualifications

BEng in Electronics University of Pretoria 2004
MScEng in Electronics Stellenbosch University 2011
PhD in Information Engineering  University of Cambridge 2015

Biography

Michael Burke is a Research Associate at the Institute of Perception, Action and Behaviour at the University of Edinburgh, where he is currently building explainable AI systems for the ORCA HUB project. Prior to this, he led a team of 20 staff and students working on a range of projects in computer vision, machine learning and field robotics at the Mobile Intelligent Autonomous Systems group at the Council for Scientific and Industrial Research (CSIR), South Africa, a group he joined in 2009. He holds a visiting lecturer position at the University of Witwatersrand and has a PhD in statistical signal processing from the University of Cambridge, a Masters of Science in electronic engineering from Stellenbosch University and a Bachelors in electronic engineering from the University of Pretoria.

Research outputs

  1. From explanation to synthesis: Compositional program induction for learning from demonstration

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

  2. DepthwiseGANs: Fast Training Generative Adversarial Networks for Realistic Image Synthesis

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

View all (20) »

Research activities & awards

  1. Proceedings of the 2018 International Women in Science Without Borders (Event)

    Activity: Publication peer-review and editorial work typesEditorial activity

  2. 2016 Pattern Recognition Association of South Africa and Robotics and Mechatronics International Conference

    Activity: Participating in or organising an event typesParticipation in conference

View all (2) »

ID: 76426411