The 2019 edition of the School organized by the Mathematics Research Center 'Ennio De Giorgi' will focus on Mathematical and Computational Aspects of Machine Learning and will take place from October 7 to October 11, 2019 at the Scuola Normale Superiore (Pisa). Details are as follows.
Title: Mathematical and Computational Aspects of Machine Learning
Description: The School will introduce an approach to the study of machine learning methods. Enhanced by large collected databases and improved computational power, these techniques have made spectacular progress in fields like image recognition and have even reached the ability to surpass humans in certain tasks and in games like Go.
Still, the conceptual mechanisms on which such forms of learning work are largely not understood. Moreover, there is a complete lack of prediction ability, not only on the efficiency of machine learning, but also on its ability to work at all on a new problem. All this calls for a strong commitment on the part of the mathematical community. The School aims at connecting international experts at the forefront of research on the mathematical and computational aspects of the problem with interested scholars, especially those in the young generations.
Courses: The programme includes 5 minicourses of 6 hours each.
- Jean Barbier (ICTP Trieste): Mean field theory of high-dimensional Bayesian inference title and abstract
- Philipp Grohs (University of Vienna): Approximation theory, Numerical Analysis and Deep Learning title and abstract
- Gabriel Peyré (ENS and CNRS, Paris): Optimal Transport for Data Science title and abstract
- Lars Ruthotto (Emory University): Numerical Methods for Deep Learning title and abstract
- Stefano Soatto (with Alessandro Achille) (UCLA): Representation Learning title and abstract
The Scientific Committee:
Luigi Ambrosio (Scuola Normale Superiore)
Michele Benzi (Scuola Normale Superiore)
Pierluigi Contucci (Università di Bologna)
Fabrizio Lillo (Università di Bologna)
The programme will include also up to 12 short communications of 20 minutes each. When registering, each prospective participant who wishes to deliver a short communication is invited to submit the title and abstract of his/her talk together with a reference letter of his/her advisor or post-doc mentor. The reference letter should be sent directly by the letter writer by e-mail to: email@example.com
The Scientific Committee will then make the final selection and give an answer within 15th August 2019.
The full list of participants will be posted at a later time, within September 15.
Time: 7 October - 11 October 2019
Application deadline: 31st July 2019.
For further details, application procedures and financial support see the School website.