Dr Michael P. J. Camilleri (PhD (Data Science), M.Sc. AI, B.Sc. ICT (Hons))

Postdoctoral Research Associate

Biography

Background

Michael obtained a B.Sc. in Communications and Computer Engineering (University of Malta), before coming to Edinburgh to study for an M.Sc. in Artificial Intelligence and Robotics. Subsequently he worked in industry, returning to the University of Edinburgh for a PhD in Data Science, supervised by Prof. Chris Williams: his thesis centred around characterising the coupled and hierarchical nature of social interactions of group-housed lab mice. This also involved a collaboration with Prof. Andrew Zissermann and the VGG group at Oxford towards tracking and behaviour recognition from video.

Apart from a strong technical background in probabilistic modelling and deep learning, Michael has experience in various applied fields, including Robotics, Transport Modelling, Radio-Telescopes, Behaviour Modelling and above all Clinical Imaging (having been a researcher on the SCANDAN project leading to the Brain Health Dataset). He has worked across Industry and Academia, and is the author of several peer-reviewed journal and conference publications. He is also a full-time husband/father and enjoys volunteering at heritage railways (particularly Steam Locomotives).

More information in his personal website.

Responsibilities & affiliations

CHAI Scholar (School of Engineering)

School of Informatics (Visiting staff)

 

Open to PhD supervision enquiries?

Yes

Research summary

Michael's research interests lie at the intersection of Probabilistic Machine Learning and Deep Learning applied to Clinical Data, particularly medical imaging to predict future disease onset, but he is also motivated by general applications of computer vision, particularly to real-world problems. He is particularly intrigued by the problem of messy/un-curated data and how explicitly modelling its limitations can improve performance of models.

This article was published on