We present an approach to low-level vision that combines two main ideas: the use of convolutional networks as an image processing architecture and an unsupervised learning procedu...
Sample selection bias is a common problem in many real world applications, where training data are obtained under realistic constraints that make them follow a different distribut...
Abstract. Consider a system composed of n sensors operating in synchronous rounds. In each round an input vector of sensor readings x is produced, where the i-th entry of x is a bi...
Florent Becker, Sergio Rajsbaum, Ivan Rapaport, Er...
Pairwise coverage of factors affecting software has been proposed to screen for potential errors. Techniques to generate test suites for pairwise coverage are evaluated according ...
We show how to build hierarchical, reduced-rank representation for large stochastic matrices and use this representation to design an efficient algorithm for computing the largest...