Machine Learning research in the Department of Computer Science evolves along the following directions
- Deep learning
- Large scale machine learning and big data
- Random forests and ensemble methods
- Proabilistic graphical models
- Bayesian optimisation
- Reinforcement learning
- Monte Carlo methods and randomised algorithms.
- Applications to control, games, language understanding, computer vision, speech, time series, and all types of structured and unstructured data.
The group is part of wider Machine Learning initiative at Oxford, which includes researchers in statistics (Yee Whye Teh, Arnaud Doucet, Chris Holmes) and information engineering (Michael Osborne,Steve Roberts,Frank Wood)
Recurrent Convolutional Neural Networks for Discourse Compositionality
Nal Kalchbrenner and Phil Blunsom
In Proceedings of the 2013 Workshop on Continuous Vector Space Models and their Compositionality. 2013.
Modelling‚ Visualising and Summarising Documents with a Single Convolutional Neural Network
Misha Denil‚ Alban Demiraj‚ Nal Kalchbrenner‚ Phil Blunsom and Nando de Freitas
No. arXiv:1406.3830. University of Oxford. 2014.