Alexander G. de G. Matthews

Learn More
Gaussian process classification is a popular method with a number of appealing properties. We show how to scale the model within a variational inducing point framework, out-performing the state of the art on benchmark datasets. Importantly, the variational formulation can be exploited to allow classification in problems with millions of data points, as we(More)
Gaussian process (GP) models form a core part of probabilistic machine learning. Considerable research effort has been made into attacking three issues with GP models: how to compute efficiently when the number of data is large; how to approximate the posterior when the likelihood is not Gaussian and how to estimate covariance function parameter posteriors.(More)
[1] Measurements have been made of the effect of compaction on water retention, saturated hydraulic conductivity, and porosity of two English soils: North Wyke (NW) grassland clay topsoil and Broadbalk silty topsoil, fertilized inorganically (PKMg) or with farmyard manure (FYM). As expected, the FYM topsoil had greater porosity and greater water retention(More)
The variational framework for learning inducing variables (Titsias, 2009a) has had a large impact on the Gaussian process literature. The framework may be interpreted as minimizing a rigorously defined Kullback-Leibler divergence between the approximating and posterior processes. To our knowledge this connection has thus far gone unre-marked in the(More)
SUMMARY Anaplastic large cell lymphoma of the breast is a rare malignancy associated with prosthetic breast implants. We present a case of a woman with no prior history of breast implants who developed anaplastic lymphoma kinase-1 negative anaplastic large cell lymphoma on a background of a previous benign cyst aspiration.
  • 1