Working in Our Lab

The LILI lab develops machine learning/statistical methodology that enables interpretability of predictions and learning in inverse problems (where the information of interest is not directly measurable). Our applications are mostly in spatiotemporal data problems across: medical imaging (MRI reconstruction, image registration); disease progression modelling; computer vision and ecologicial monitoring.

Projects in our lab typically involve:

• Making theory supported proposals for model formulations that are implemented (in PyTorch/Jax) and evaluated on both synthetic and real data.
• Inter-disciplinary collaboration with domain experts, e.g. MR Physicists, Clinicians, Ecologists.
• Regular presentation of your own, and published works to the team.
• Respecting Occam’s razor and environmental concerns and justifying computational complexity.

If you want to work with us, you should have an understanding and be open to further training in probability, linear algebra, calculus and Python programming. Recommended reading material includes:

• Understanding Deep Learning by Simon Prince.
• Information Theory, Inference, and Learning Algorithms by David MacKay.
• Probabilistic Machine Learning: Advanced Topics by Kevin Murphy.
• Mathematics for Machine Learning by Marc Peter Deisenroth, A. Aldo Faisal, and Cheng Soon Ong.