Professor in Artificial Intelligence Head of Machine Learning Group, Intelligent Systems Institute for Computing and Information Sciences (iCIS) Faculty of Science, Radboud University Nijmegen
Title: Bayesian regression and classification with multivariate sparsifying priors
Abstract: Many regression and classification problems in neuroimaging and bioinformatics belong to the class “large p, small n”: many variables, just a few data points. Popular methods for handling such problems include L1-regularization and spike-and-slab variable selection. These methods are univariate when it comes to determine which variables are selected. In this talk I will present multivariate extensions that allow for the incorporation of (spatio-temporal) constraints and lead to smooth importance maps. I will discuss how to arrive at efficient algorithms for (approximate) inference and will illustrate the methods on fMRI analysis and EEG source localization.
Marcel Van Gerven,
Assistant Professor, Department of Artificial Intelligence, Donders Centre for Cognition, Donders Institute for Brain, Cognition and Behaviour, Radboud University Nijmegen
Title: Bayesian structural connectivity estimation
Abstract: Structural brain networks are used to model white-matter connectivity between spatially segregated brain regions. The presence, location and orientation of these white matter tracts can be derived using diffusion-weighted magnetic resonance imaging in combination with probabilistic tractography. Unfortunately, as of yet, none of the existing approaches provide an undisputed way of inferring brain networks from the streamline distributions which tractography produces. State- of-the-art methods rely on an arbitrary threshold or, alternatively, yield weighted results that are difficult to interpret. In this talk, I will introduce a generative model that explicitly describes how structural brain networks lead to observed streamline distributions. This allows us to draw principled conclusions about brain networks, which we validate using simultaneously acquired resting-state functional MRI data. Inference may be further informed by means of a prior which combines connectivity estimates from multiple subjects. Based on this prior, we obtain networks that significantly improve on the conventional approach. I will end by describing our current work, which makes the model suitable for connectivity-based parcellation.
Associate Professor, Section for Cognitive Systems, DTU Informatics
Title: Modeling Brain Connectivity by Non-parametric Bayesian Relational Models
Abstract: Functional and diffusion magnetic resonance imaging have become key non-invasive measuring modalities in order to quantify the brains functional (i.e., effective) and structural connectivity respectively. In this talk we will discuss how non-parametric Bayesian models for complex networks can be used to extract prominent patterns of connectivity in these functional and structural brain networks.
Lars Kai Hansen
Professor, Section for Cognitive Systems, DTU Informatics
Title: Mind reading: Model sparsity and interpretation
Abstract: Model interpretation is of importance in the neuroimaging context, and is conventionally based on a ‘brain map’ derived from the classification model. In this work we focus on the relative influence of model regularization parameter choices on both the model generalization, the reliability of the spatial patterns extracted from the classification model, and the ability of the resulting model to identify relevant brain networks defining the underlying neural encoding of the experiment.