Current approaches to explicit user modelling are generally time consuming and tedious for the user. Oftentimes poor usability and overly long questionnaires deter the end user fro...
Semi-supervised learning (SSL), is classification where additional unlabeled data can be used to improve accuracy. Generative approaches are appealing in this situation, as a mode...
This paper examines the problem of finding an optimal policy for a Partially Observable Markov Decision Process (POMDP) when the model is not known or is only poorly specified. W...
Abstract. We address the problem of learning good features for understanding video data. We introduce a model that learns latent representations of image sequences from pairs of su...
Agents in a competitive interaction can greatly benefit from adapting to a particular adversary, rather than using the same general strategy against all opponents. One method of s...