Many planning and design problems can be characterized as optimal search over a constrained network of conditional choices with preferences. To draw upon the advanced methods of c...
In this paper we present an automated method for classifying astronomical objects in multispectral wide-field images. The method is divided into three main tasks. The first one co...
Abstract. Application of neural networks for real world object recognition suffers from the need to acquire large quantities of labelled image data. We propose a solution that acq...
Concurrent and distributed systems have traditionally been modelled using nondeterministic transitions over configurations. The minism provides an abstraction over scheduling, net...
We propose a gossip-based distributed algorithm for Gaussian mixture learning, Newscast EM. The algorithm operates on network topologies where each node observes a local quantity ...