We introduce a new algorithm based on linear programming that approximates the differential value function of an average-cost Markov decision process via a linear combination of p...
This paper presents a novel method for reducing the dimensionality of kernel spaces. Recently, to maintain the convexity of training, loglinear models without mixtures have been u...
In this paper, we propose a Bayesian model and a Monte Carlo Markov chain (MCMC) algorithm for reconstructing images that consist of only few non-zero pixels. An appropriate distr...
Nicolas Dobigeon, Alfred O. Hero, Jean-Yves Tourne...
Neural networks are a useful alternative to Gaussian mixture models for acoustic modeling; however, training multilayer networks involves a difficult, nonconvex optimization that...
Exotic semirings such as the “(max, +) semiring” (R ∪ {−∞}, max, +), or the “tropical semiring” (N ∪ {+∞}, min, +), have been invented and reinvented many times s...