-
-view learning that are robust under distribution shift and missing modalities. The key objectives include: Develop scalable Bayesian deep learning methods for uncertainty estimation in modern neural
-
analysis, contextual analysis, audio feature extraction, and machine learning models to identify and assess potentially dangerous content. Similarly, computer vision models are implemented to analyse images
-
methods dealing with model complexity - e.g., AIC, BIC, MDL, MML - can enhance deep learning. References: D. L. Dowe (2008a), "Foreword re C. S. Wallace", Computer Journal, Vol. 51, No. 5 (Sept. 2008
-
privacy constraints, robust solutions are essential. This PhD project will develop methods for building reliable medical imaging models that generalize across distribution shifts without retraining
-
to Fisher-Rao geometry and develop theoretical results characterising MML estimation under various regularity conditions. Aim 2: Development of Computational Methods for MML Design and implement efficient
-
that explicitly account for drift and open-set contamination. O2: Robust uncertainty estimation: Improve calibration and uncertainty reliability under drift (e.g., ensembles, Bayesian approximations, conformal
-
-Kolmogorov complexity (Wallace and Dowe, 1999a), it is possible to (e.g.) create a general hybrid of (none, some or) all of the above methods - and then (if we wish) to generalise that even further
-
DNA or RNA motif discovery is a popular biological method to identify over-represented DNA or RNA sequences in next generation sequencing experiments. These motifs represent the binding site
-
time. In this project, we propose a method for identifying and classifying such emerging asynchronous trends. The goal is to be able to predict how a new emerging trend will develop using similar
-
This project aims to develop robust algorithms capable of identifying and analyzing fingertips extracted from both static images and video footage. Machine learning techniques, particularly computer