Dear all, I am pleased to announce a talk by Sergio Luengo-Sanchez from the Technical University of Madrid. The 20-minutes talk will be held this Friday (September 29) at 11am in the IDSIA meeting room (Manno, Galleria 1 building). [Full Title of the Talk] Clustering based on Bayesian networks with Gaussian and angular predictors. Applications in Neuroscience [Abstract] The study of plethora of phenomena requires the measurement of their magnitude and direction. Probabilistic clustering of these data is typically tackled by means of mixtures of Gaussians although they tend to underperform due to their inability to handle periodicity of directional data. To address this problem several distributions have been proposed to cluster bivariate cylindrical data and multivariate data having one circular variable. However, data is usually multidimensional and consists of a large number of linear and directional variables. In the present talk, an approach based on exploiting the conditional independence assumptions encoded by a Bayesian network enabling efficient clustering of multivariate directional-linear data, even when there is more than one directional variable, by means of the structural expectation-maximization algorithm is introduced. An application for neuroscience to cluster dendritic spines according to a set of morphological features that combine directional and linear variables is presented. Bests, Alessandro _________________________________ Alessandro Antonucci IDSIA Dalle Molle Institute for Artificial Intelligence Via Cantonale (Galleria 2) CH-6928, Manno-Lugano, CH mail: alessandro(a)idsia.ch skype: alessandro.antonucci tel: +41 916108515 web: www.idsia.ch/~alessandro _________________________________