In supervised learning, we commonly assume that training and test data are sampled from the same distribution. However, this assumption can be violated in practice and then standa...
We propose to study links between three important classification algorithms: Perceptrons, Multi-Layer Perceptrons (MLPs) and Support Vector Machines (SVMs). We first study ways to...
We propose a new Bayesian, stochastic tracking algorithm for the segmentation of blood vessels from 3D medical image data. Inspired by the recent developments in particle filterin...
David Lesage, Elsa D. Angelini, Isabelle Bloch, Ga...
In most computer systems, page fault rate is currently minimized by generic page replacement algorithms which try to model the temporal locality inherent in programs. In this pape...
Karlton Sequeira, Mohammed Javeed Zaki, Boleslaw K...
We present a new algorithm for the problems of genotype phasing and block partitioning. Our algorithm is based on a new stochastic model, and on the novel concept of probabilistic...