We propose a novel a framework for deriving approximations for intractable probabilistic models. This framework is based on a free energy (negative log marginal likelihood) and ca...
Abstract. Validation can be used to detect when over tting starts during supervised training of a neural network; training is then stopped before convergence to avoid the over ttin...
Several scientic bottlenecks have been identied in existing component-based approaches. em, we focus on the identication of a relevant abstraction for the component expression ...
Abstract-- In this paper, we consider the problem of optimal control for throughput utility maximization in cognitive radio networks with dynamic user arrivals and departures. The ...
With the popularity of "bag of visual terms" representations of images, many text indexing techniques have been applied in large-scale image retrieval systems. However, ...
Xiao Zhang, Zhiwei Li, Lei Zhang, Wei-Ying Ma, Heu...