Machine Learning

Machine learning is the study of computational processes that find patterns and structure in data.

Our group is interested in a broad range of theoretical aspects of machine learning as well as applications. Much of the current excitement around machine learning is due to its impact in a broad range of applications. The applications considered in our research include astronomy, systems biology, neuroscience, natural language processing, robotics, and computer vision.

Faculty

Members Research interests
Chris Williams Gaussian processes, image interpretation, unsupervised learning, deep learning, time series models
Amos Storkey

Continuous time systems, deep learning, stochastic differential equations

Iain Murray Bayesian statistics, approximate inference, Markov chain Monte Carlo, scientific data analysis
Guido Sanguinetti Probabilistic modeling of biological systems, dynamics of regulatory networks, computational epigenetics, spatiotemporal systems
Charles Sutton Probabilistic modeling of large-scale computer systems, approximate inference, statistical processing of natural and programming languages
Nigel Goddard Probabilistic modeling of energy-related systems
Chris Bishop Graphical models, variational methods, pattern recognition
Michael Gutmann Efficient statistical learning, inference for complex models, unsupervised deep learning, natural image statistics, computational biology
Rico Sennrich Machine translation, natural language processing, deep learning
Arno Onken   Probabilistic models, in particular copula-based models; Dimensionality reduction techniques; Information theory; Applications to biological systems

Events

We have two journal reading groups: 

PIGS

PIGlets

We also have the following weekly:

Brainstorm Coffee 

Machine Learning Lunch

Joining the group

If you would like to join the machine learning group as a PhD student, please see this information:

Prospective Postgraduates

Occasionally we have openings for postdoctoral researchers. Please contact the individual lecturers directly about this.

Classes

As part of our MSc programme, we teach a large number of classes in machine learning, namely:

Introductory Applied Machine Learning

Probabilistic Modelling and Reasoning

Machine Learning and Pattern Recognition

Data Mining and Exploration

Neural Information Processing

Machine Learning Practical

Related Research @ Edinburgh

Many other research groups at Edinburgh work actively in related areas, including:

ILCC (statistical natural language processing)

IPAB (vision and robotics)

ICSA (self-managing compilers and computer systems)

BioSS (bioinformatics, statistics)

School of Mathematics (statistics)

Some of these links are represented by:

Informatics Research Programme on Machine Learning

Funding

We receive funding for our research from many sources, including:

Engineering and Physical Sciences Research Council

Microsoft Research 

PASCAL

Biotechnology and Biological Sciences Research Council