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.

Mathematical Methods and Models in Machine Learning

Pierluigi Contucci;Diego Alberici;Francesco Camilli;Emanuele Mingione;Daniele Tantari
2020

Abstract

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.
Luigi Ambrosio, Michele Benzi, Pierluigi Contucci, Diego Alberici, Jean Barbier, Francesco Camilli, Emanuele Mingione, Daniele Tantari
File in questo prodotto:
Eventuali allegati, non sono esposti

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11585/789074
 Attenzione

Attenzione! I dati visualizzati non sono stati sottoposti a validazione da parte dell'ateneo

Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus ND
  • ???jsp.display-item.citation.isi??? ND
social impact