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 explore making virtual desktops behave in a more physically realistic manner by adding physics simulation and using piling instead of filing as the fundamental organizational s...
We are interested in the simulation and optimization of gas transport in networks. Different regions of the network may be modelled by different equations. There are three models...
We define a framework called the prismoid of resources where each vertex refines the λ-calculus by using a different choice to make explicit or implicit (meta-level) the defin...
Assigning the resources of a virtual network to the components of a physical network, called Virtual Network Mapping, plays a central role in network virtualization. Existing appr...