We present a learning framework for structured support vector models in which boosting and bagging methods are used to construct ensemble models. We also propose a selection metho...
Many of the difficulties users experience when working with interactive systems arise from misfits between the user's conceptualisation of the domain and device with which the...
In this paper we demonstrate that Long Short-Term Memory (LSTM) is a differentiable recurrent neural net (RNN) capable of robustly categorizing timewarped speech data. We measure ...
We introduce a process-centric ontological approach to relate observed properties to geo-processes that influence those observations. These relations are used to handle semantic he...
We describe a basic framework for studying dynamic scaling that has roots in dynamical systems and probability theory. Within this framework, we study Smoluchowski's coagulat...