Decision trees and ensembles of decision trees are very popular in machine learning and often achieve state-of-the-art performance on black-box prediction tasks. However, popular variants such as C4.5, CART, boosted trees and random forests lack a probabilistic interpretation since they usually just specify an algorithm for training a model. We take a probabilistic approach where we cast the de...

This paper deals with the blind separation and reconstruction of source images frommixtures with unknown coefficients, in presence of noise. We address the blind source separation problem within the ICA approach, i.e. assuming the statistical independence of the sources, and reformulate it in a Bayesian estimation framework. In this way, the flexibility of the Bayesian formulation in accounting...

the estimation of velocity distribution plays a major role in the hydrodynamics of vegetated streams or rivers of extensive natural floodplains. the velocity profile in vegetated channels can be divided into three zones: uniform zone which is close to bed with uniform velocity distribution, logarithmic zone which involves the main channel with no vegetive cover and the transition zone that is a...

In the problem of selecting variables in a multivariate linear regression model, we derive new Bayesian information criteria based on prior mixing smooth distribution and delta distribution. Each them can be interpreted as fusion Akaike criterion (AIC) (BIC). Inheriting their asymptotic properties, our are consistent variable selection both large-sample high-dimensional frameworks. numerical si...

We study how 2nd order statistics (SOS) can be exploited in two signal processing problems, blind separation of binary sources and trained-based multi-user channel iden­ tification, in a Bayesian context where a prior on the mixing channel matrix is available. It is well known that the SOS of the received data permit to resolve the unknown mixing matrix, up to an orthogonal factor. In a Bayesia...

We consider a continuous-time Markov chain model of SIR disease dynamics with two levels of mixing. For this so-called stochastic households model, we provide two methods for inferring the model parameters-governing within-household transmission, recovery, and between-household transmission-from data of the day upon which each individual became infectious and the household in which each infecti...

Bayesian variable selection becomes more and more important in statistical analyses, in particular when performing variable selection in high dimensions. For survival time models and in the presence of genomic data, the state of the art is still quite unexploited. One of the more recent approaches suggests a Bayesian semiparametric proportional hazards model for right censored time-to-event dat...

archaeological excavations on the western part of the central iranian plateau, known as the qazvin plain provides invaluable information about the sedentary communities from early occupation to the later prehistoric era. despite the past archeological data, chronological studies mostly rely on the relative use of the bayesian modeling for stratigraphically-related radiocarbon dates. the current...