My name is Concha Bielza.

 I am professor in the Department of Artificial Intelligence at the School of Computer Science of UPM.

 I co-lead the Computational Intelligence Group.

 This is a research group devoted to modelization from statistical and machine learning perspectives and also devoted to heuristic optimization.

 I am also co-director of the Ellis Unit Madrid, an important application area since 2009 is Data-Driven Neuroscience, where we build models from data to answer different research questions.

 A major line of research has been in neuroanatomy with different contributions.

 As the classification of cortical and gabaergic interneurons according to their morphology.

 This is a hard problem since neuroanatomists dont agree on the nomenclature.

 Hence, this supervised classification problem doesn't have instances with clear labels, which is very, very challenging from the machine learning point of view.

 We have tried to identify similar groups of dendritic spines.

 The spatial distribution of synopsis along dendritic networks has been also studied the simulation of dendritic trees of pyramidal cells, or the wiring economy.

 Also for this kind of cells testing the hypothesis that our arborizations optimize brain connectivity in terms of total wiring length.

 The second main line of research is in neurological diseases where we have tried to search for genetic biomarkers in Alzheimer disease or the classification of task related mental activity from Magnetoencephalography data, which is very relevant in brain computer interface and in Parkinson's disease.

 We have identified different subtypes with motor, and non-motor symptoms or the prediction of the dementia development.

 And also we have tried to predict genetic health related quality of life measure with five dimensions mobility, self-care, usual activities, pain, discomfort and anxiety, depression by using the very, very specific quality of life Parkinson Disease Questionnaire.

 In epilepsy, we have tried to predict the outcome of temporal lobe epilepsy surgery to see whether the patient will fully recover from epilepsy or not by using clinical variables and also pathological on neuropsychological evaluations.

 We have also implemented an open machine learning and a statistical web framework with neuroscience applications, and this is called NeuroSuites Some of the works have been published in top journals like Nature Reviews Neuroscience or Nature Neuroscience.

 And also always we have preferred models that are called Bayesian networks because they are interpretable, and this is very important in building unexplainable artificial intelligence where humans can trust on intelligent systems and avoid biases and discriminative and opaque outcomes.

 Our work in neuroscience has been framed within two major projects of ten years duration.

 one starting in 2009, the Cajal Blue Brain Project, funded by the Spanish Ministry on the second from 2013 to this year 2023, The Human Brain Project.

 This is a FET flagship of the European Commission where we have been involved from the very beginning in the ramp up phase and in the three specific grant agreements In this projetcs, currently we are developing a genetic addressing toolbox with a web interface and a plugin for the Brain Atlas view of EBRAINS.

 EBRAINS is the digital brain research infrastructure created by the Human Brain Project in this case, and massive Bayesian networks are used for interactively learning gene regulatory networks from gene expression.

 Data extracted from the Atlas.

 I think it students have a great opportunity to gain insights from the application of machine learning to all kinds of data that are available nowadays generated by different neural technologies like morphological, electrophysiological, molecular clinical data, etc.

 I think that we have done our bit in a student education by offering to book data driven computational neuroscience, machine learning and statistical models.

 This book was published in 2020 by Cambridge University
Press and has more than 700 pages.