Mathematical Methods and Models in Machine Learning

Artificial Intelligence is profoundly and quickly changing the technological profile of our society and yet machine learning, its disruptive spearhead, although filled with brilliant heuristic solutions has almost no theoretical basis from a strictly scientific point of view. The gap between the increasing performance of deep learning and its understanding is therefore a very relevant scientific theme that calls for a strong participation in research efforts from the fields of Mathematics and Mathematical Physics. The identification of the correct mathematical models and their analysis is of fundamental importance toward the discovery of a theory that could allow to exploit at best the potential and understand the limits of this technology. The purpose of the conference is to present recent results on mathematical methods and models related to machine learning and link researchers coming from different areas.