We propose a unified neural network architecture and learning algorithm that can be applied to various natural language processing tasks including: part-of-speech tagging, chunki...
Many Ubiquitous computing applications can be considered as planning and acting problems in environments characterised by uncertainty and partial observability. Such systems rely ...
- In this paper we propose a new methodology for Cost-Benefit analysis in a multiple time series prediction problem. The proposed model is evaluated in a real world application bas...
Severely resource-constrained devices present a confounding challenge to the functional programmer: we are used to having powerful ion facilities at our fingertips, but how can we...
Location services are essential to many applications running on a hybrid of wirelessly-networked mobile actors and static sensors, such as surveillance systems and the Pursuer and...