Mainly interested in innovative applications to deep learning, especially vision related ones and expanding unsupervised learning via research in Variational Autoencoders and Generative Adversarial networks. Also, very interested in the area of explorative reinforcement learning, which can provide general purpose models that can then be applied to more specific areas.
Program synthesis, especially type-driven program synthesis. Inductive logic programming, especially meta-interpretive learning. In general, I am also interested in automated reasoning, type systems, SMT solvers, and declarative programming.
Theoretical notions behind computer science. In particular, automated reasoning and its relation to ontological management of data. Additionally, the mathematical and theoretical study of software modularity and other more general notions of modularity and elasticity.
The exploration of learning as both a tool to create solutions for data-rich problems and for the understandings of the underlying mechanisms that make learning, in a machine context, possible and plausible. This line of thought currently manifests as model analysis and manipulation for either robust representation learning or transfer learning.
Representation learning using deep neural networks. Representing sets, with applications to information retrieval, content-based recommendation and generative models. Adversarial learning for fair decision making.
Interested in probabilistic modelling applied on multi-modal biological data, such as methylation, expression and accessibility. I work in developing novel statistical methods dealing with corrupting mechanisms in the process of gathering such data with single cell technologies. Past interests include optimisation and machine vision.
Network Representation Learning, semi-supervised learning on networks, community detection and large scale clustering of attributed graphs. Bio-medical applications of such methods. For example, the analysis of Autism Spectrum Disorder.
Coming from a mathematical and statistical background means I am naturally interested in the theoretical underpinnings of machine learning algorithms. However, I am currently keen to learn more about the theoretical challenges that arise when applying such methods in the real world where there are limitations and hurdles, such as in medicine.
Bayesian approaches to deep learning, approximate inference, probabilistic programming languages and the application of these techniques to real world problems requiring the understanding of uncertainty.
Network representation learning, semi-supervised learning on networks, distributed algorithms for graph representation learning, large scale network analysis and community detection in attributed graphs.