Students

Carl Allen - 2016 intake

Carl Allen Machine Learning, (Deep) Reinforcement Learning and Learning to Learn abstractions, e.g. transfer, multi-task, curriculum, zero-shot learning, etc

Homepage

Antreas Antoniou - 2016 intake

Antreas Antoniou 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.

Homepage

Ivana Balazevic - 2016 intake

Ivana Balazevic Machine learning, natural language understanding, natural language generation, deep learning

Homepage

Artur Bekasov - 2016 intake

Artur Bekasov Machine learning, deep neural networks, representation learning, image and natural language understanding, unsupervised learning.

Homepage

Michael Camilleri - 2017 intake

Michael Camilleri Primarily in Bayesian Machine Learning, Time-Series Modelling and, to some extent, Deep Learning. Especially interested in the mathematical underpinnings of the above techniques.

Homepage

Juan Casanova - 2016 intake

Juan Casanova 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.

Homepage

Asa Cooper Stickland - 2017 intake

Asa Cooper Stickland Approximate Bayesian inference, generative models, Bayesian deep learning, and application of the previous topics to NLP.

Homepage

Luke Darlow - 2017 intake

Luke Darlow 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.

Homepage

Ryan Davies - 2015 intake

Ryan Davies Machine learning, neural networks and natural language processing, particularly for information extraction.

Homepage

Conor Durkan - 2016 intake

Conor Durkan Methods, tools, and applications for machine learning, including deep learning and content-based recommendation.

Homepage

Simão Eduardo - 2015 intake

Simão Eduardo Machine Learning, Unsupervised Learning, Graphical Models, (Deep) Neural Networks, Large-Scale/ Distributed Machine Learning and Optimisation. Applications in Text Mining, Computer Vision, Econometrics and Networks (Energy and Communications).

Homepage

Harrison Edwards - 2014 intake

Harrison Edwards 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.

Homepage

Elaine Farrow - 2017 intake

Elaine Farrow Natural language processing and machine learning. Particular interest in educational technology and interfaces that allow people without specialist training to achieve complex goals.

Homepage

Sorcha Gilroy - 2014 intake

Sorcha Gilroy Machine translation and natural language processing. Particular interest in semantic representations of sentences and formal languages of graphs.

Homepage

Maria Gorinova - 2016 intake

Maria Gorinova Probabilistic Programming Languages. Machine Learning for Source Code. Software Verification and Synthesis.

Homepage

Zack Hodari - 2016 intake

Zack Hodari Machine learning, Speech synthesis, Prosody, Generative models, Sampling speech from SPSS models, Expressive speech synthesis, Emotion recognition.

Homepage

Borislav Ikonomov - 2015 intake

Borislav Ikonomov Machine learning, Statistics, Natural language processing, Computer vision, Neuroinformatics, Quantum computing

Homepage

Miguel Jaques - 2017 intake

Miguel Jaques Neural networks, unsupervised learning, probabilistic modelling and their applications to image data.

Homepage

Andreas Kapourani - 2014 intake

Andreas Kapourani Machine learning, Bayesian statistics, probabilistic modelling of biological systems, computational epigenetics

Homepage

Rafael-Michael Karampatsis - 2014 intake

Rafael-Michael Karampatsis Sentiment analysis and opinion mining for social media, multilingual sentiment analysis, text mining, topic modeling and deep learning for social media, building an NLP pipeline for social media.

Homepage

Steven Kleinegesse - 2017 intake

Steven Kleinegesse Research interests mainly focus on new transfer learning solutions
or reinforcement learning.

Homepage

Jonathan Mallinson - 2015 intake

Jonathan Mallinson Computational linguistics, Compositional distributional semantics, sentiment analysis, semantic role labeling and paraphrase detection.

Homepage

Christos Maniatis - intake 2017

Christos Maniatis Machine learning , optimization and Statistics. Past interests include numerical linear algebra and machine vision.

Homepage

Paul Micaelli - 2017 intake

Paul Micaelli Machine Learning and probabilistic modeling of Big Data, Deep Learning for computer vision, and the non-game-theory applications of Reinforcement Learning.

Homepage

Charlie Nash - 2014 intake

Charlie Nash Probabilistic modelling, approximate inference, deep learning, vision as inverse graphics.

Homepage

Silviu Oprea - 2017 intake

Silviu Oprea Machine learning and computational semantics to study language, including language-independent representations of meaning, formal grammars and sentiment analysis. Working on mapping syntax constituents across different languages into a joint embedding space. Also looking at morphological variations and cultural marks, especially different ways of expressing happiness, sadness, humour or irony.

Homepage

James Owers - 2015 intake

James Owers Deep learning with application to harmonic instruments and music. Previous experience with fraud and image data.

Homepage

George Papamakarios - 2014 intake

George Papamakarios Probabilistic machine learning, approximate methods for Bayesian inference. Past interests have included optimization, computer vision, and parallel computing.

Homepage

Matt Pugh - 2014 intake

Matt Pugh High performance & distributed computing, data-representation & storage, non-volatile memory, computer vision, object recognition & classification, and machine learning.

Homepage

James Ritchie - 2017 intake

James Ritchie 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.

Homepage

Alexander Robertson - 2016 intake

Alexander Robertson Natural language processing, especially noisy user-generated text, language variation and change.

Homepage

Matt Rounds - 2015 intake

Matt Rounds Machine learning, deep neural networks, human-like computing, applications to computer vision, applications to neuroinformatics.

Homepage

Benedek Rózemberczki - 2016 intake

Benedek Rózemberczki Network representation learning, semi-supervised learning on networks, distributed algorithms for graph representation learning, large scale network analysis and community detection in attributed graphs.

Homepage

Philippa Shoemark - 2014 intake

Philippa Shoemark Computational linguistics, natural language processing, cognitive modelling, complex networks. Currently focused on linguistic alignment & spreading phenomena in social media, & agent-based models of language change.

Homepage

Christine Simpson - 2017 intake

Christine Simpson Machine learning, Bayesian inference and analysing data from gravitational wave detectors.

Homepage

Etienne Toussaint - 2017 intake

Etienne Toussaint Databases: query languages, relational and graph data, incomplete information. Logic in computer science, automata theory. Game theoric aspects of Blockchains.

Homepage

Clara Vania - 2014 intake

Clara Vania Machine Translation, Natural Language Understanding, Low-resource NLP, Unsupervised Learning and Representation Learning for NLP.

Homepage

Jennifer Williams - 2017 intake

Jennifer Williams Speech synthesis, prosodic modeling, speech recognition, deep learning, human speech perception

Homepage

Yanghao Wang - 2016 intake

Yanghao Wang Database theory and systems, big data processing and data mining.

Homepage