In ubiquitous environments an increasing number of sensors capture information on users and an increasing number of actuators present information to users. In this paper we presen...
We propose a new neural network architecture, called Simple Recurrent Temporal-Difference Networks (SR-TDNs), that learns to predict future observations in partially observable en...
We present a simple, effective generalisation of variable order Markov
models to full online Bayesian estimation. The mechanism used is close
to that employed in context tree wei...
Networked computing systems continue to grow in scale and in the complexity of their components and interactions. Component failures become norms instead of exceptions in these en...
Abstract. We consider the design of online master algorithms for combining the predictions from a set of experts where the absolute loss of the master is to be close to the absolut...
Jacob Abernethy, John Langford, Manfred K. Warmuth