To explore the Perturb and Combine idea for estimating probability densities, we study mixtures of tree structured Markov networks derived by bagging combined with the Chow and Liu maximum weight spanning tree algorithm, or by pure random sampling. We empirically assess the performances of these methods in terms of accuracy, with respect to mixture models… (More)
The goal of this research is to improve probabilistic reasoning in high-dimensional problems.
The recent explosion of high dimensionality in datasets for several domains has posed a serious challenge to existing Bayesian network structure learning algorithms. Local search methods represent a solution in such spaces but suffer with small datasets. MMHC (Max-Min Hill-Climbing) is one of these local search algorithms where a first phase aims at… (More)
The transformation of Euler-Lagrange systems, with the variable of position as output, in order to solve some interesting problem as the design of observer is considered in this paper. First, we will provide a necessary and sufficient condition, which ensures the transformation of such system into some structure affine in the velocities, as well as a method… (More)
BACKGROUND Clinical selectivity of antidepressants with pharmacological specificity still remains under debate. METHOD In the open trial presented below, the effects of fluoxetine, a selective serotonin re-uptake inhibitor (SSRI), were compared across two groups of depressive inpatients contrasted on their symptomatological expression (agitated/anxious… (More)
The aim of this paper is to focus on methodological problems related to clinical studies on the onset of action of antidepressants, especially moclobemide. The methodological discussion proposed focuses on: --global efficacy as a function of time; --proposals for a specific approach to the study of the onset of action; --quality of the response and onset of… (More)