Michael P. J. Camilleri
Postdoctoral Research Associate
- CHAI Hub, School of Engineering, College of Science and Engineering
- AIAI, School of Informatics, College of Science and Engineering
Contact details
- Email: michael.p.camilleri@ed.ac.uk
Address
- Street
-
CHAI, Usher Building
The University of Edinburgh
5-7 Little France Road
Edinburgh BioQuarter ‒ Gate 3 - City
- Edinburgh
- Post code
- EH16 4UX
Background
I obtained a B.Sc. in Communications and Computer Engineering (University of Malta, 2011), before coming to Edinburgh to study for an M.Sc. in Artificial Intelligence and Robotics (2012). Subsequently I worked in industry, returning to the University of Edinburgh in 2017 for a PhD in Data Science, supervised by Prof. Chris Williams. My Doctoral 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, I have 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). I have worked across Industry and Academia, and in various disciplines, giving me a strong collaborative network that expands the breadth of my work. More information is available on my personal website.
On the personal side, I am a full-time husband/father and enjoy volunteering at heritage railways (particularly Steam Locomotives).
Qualifications
Ph.D. in Data Science, University of Edinburgh, 2023
M.Sc. in Artificial Intelligence, University of Edinburgh, 2013
B.Sc. ICT (Hons) in Communications and Computer Engineering, University of Malta, 2011
Responsibilities & affiliations
CHAI Scholar (School of Engineering)
School of Informatics (Visiting staff)
Open to PhD supervision enquiries?
Yes
Research summary
My 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 I am also motivated by general applications of computer vision, particularly to real-world problems. The problems of messy/un-curated data intrigue me particularly because it allows me to interact with domain experts to explicitly model the nuances and improve the performance of deep learning models.
Current research interests
Computer Vision for Medical Imaging, Prediction of Neurodegeneration, Probabilistic Modelling and CausalityKnowledge exchange
I prioritise working with real-world data especially health data that is collected in routine clinical settings. While this makes the tasks more challenging, it ensures that the data is already representative of what is already able to be collected, ensuring a faster path to deployment.