Unexpected stimuli are a challenge to any machine learning algorithm. Here we identify distinct types of unexpected events, focusing on 'incongruent events' when 'g...
We present a new and efficient semi-supervised training method for parameter estimation and feature selection in conditional random fields (CRFs). In real-world applications suc...
This paper deals with automatically learning the spatial distribution of a set of images. That is, given a sequence of images acquired from well-separated locations, how can they ...
Following verbal route instructions requires knowledge of language, space, action and perception. We present MARCO, an agent that follows free-form, natural language route instruc...
Matt MacMahon, Brian Stankiewicz, Benjamin Kuipers
Most of the current WWW is made up of dynamic pages. The development of dynamic pages is a difficult and costly endeavour, out-of-reach for most users, experts, and content produce...