Abstract. Learning algorithms relying on Gibbs sampling based stochastic approximations of the log-likelihood gradient have become a common way to train Restricted Boltzmann Machin...
We address the problem of fast, large scale sketch-based image retrieval, searching in a database of over one million images. We show that current retrieval methods do not scale w...
Mathias Eitz, Kristian Hildebrand, Tamy Boubekeur,...
Abstract--In wireless networks, important network functionalities such as power control, rate allocation, routing, and congestion control must be optimized in a coherent and integr...
We present a family of discrete isometric bending models (IBMs) for triangulated surfaces in 3-space. These models are derived from an axiomatic treatment of discrete Laplace oper...
Tuning SVM hyperparameters is an important step in achieving a high-performance learning machine. It is usually done by minimizing an estimate of generalization error based on the...