In this paper we examine the problem of estimating the parameters of a multinomial distribution over a large number of discreteoutcomes,most of which do not appearin the training ...
We propose a novel strategy for training neural networks using sequential Monte Carlo algorithms. This global optimisation strategy allows us to learn the probability distribution...
We seek the scene interpretation that best explains image data. For example, we may want to infer the projected velocities (scene) which best explain two consecutive image frames ...
Gain control by divisive inhibition, a.k.a. divisive normalization, has been proposed to be a general mechanism throughout the visual cortex. We explore in this study the statisti...
We present a method for learning complex appearance mappings, such as occur with images of articulated objects. Traditional interpolation networks fail on this case since appearan...
We compare the ability of three exemplar-based memory models, each using three different face stimulus representations, to account for the probability a human subject responded &q...
Matthew N. Dailey, Garrison W. Cottrell, Thomas A....
The kernel-parameter is one of the few tunable parameters in Support Vector machines, controlling the complexity of the resulting hypothesis. Its choice amounts to model selection...
Nello Cristianini, Colin Campbell, John Shawe-Tayl...
There has been much recent work on measuring image statistics and on learning probability distributions on images. We observe that the mapping from images to statistics is many-to...