Diego Sona is a researcher at the Fondazione Bruno Kessler (FBK) in the Neuroinformatics Laboratory (NILab) and visiting scientist at the Istituto Italiano di Tecnologia (IIT) leading the Biomedical Imaging team in the Pattern Analysis and Computer Vision (PAVIS) department.
He received the Ph.D degree in Computer Science in 2002 from the University of Pisa with a thesis on modeling of artificial neural networks through formal methods. From 2002 to 2008 he served as researcher in the Adaptive Advisory Systems Group at the Istituto Trentino di Cultura, investigating machine learning models for structured data and contextual processing, with main application to information retrieval and text data management. In 2008 he moved to the Neuroinformatics Laboratory at FBK, studying multivariate pattern analysis methods for brain decoding and brain mapping from functional brain imaging. In 2010 he became tenured researcher at FBK. From 2008 to 2011 he has been guest researcher at the Center for Mind/Brain Sciences in the University of Trento. Since 2011 he joined as a visiting scientist the Pattern Analysis and Computer Vision department at the Istituto Italiano di Tecnologia leading the activities in biomedical imaging.
His research is on machine learning and pattern recognition methods, with application to various domains, like information retrieval, structured data analysis, computer vision, neuroimaging and biomedical imaging. The most significant recent research activity spans various automatic methods for animal phenotyping, ranging from video and signal analysis for social and non-social behavior understanding, to the investigation of corresponding neuronal correlates: from functional and structural brain imaging down to the analysis of meso-scale neuronal network populations.
He has co-authored more than 70 peer-reviewed publications, published in refereed journals and international conferences and served as reviewer for several international journals and conferences.
My main research interest has always been on machine learning and its application to real problems. Since some years now I am interested on the design of novel solutions allowing to investigate the multiple facets of behavioral phenotyping. This allows to explore many aspects of neuroscience and biology domains: from the phenotyping of social and non-social behaviors to the investigation of corresponding brain correlates, from the characterization of cells and neuronal network connectivity to the analysis of the manifestations of certain mental diseases (such as schizophrenia, autism, etc.), through structural and functional brain imaging. In this perspective, the research on biomedical data analysis currently carried out by my team can be seen as organized around three main research lines: