Laura Meneghetti -- A Reduced Order Approach for Artificial Neural Networks Applied to Object Recognition Room: Meeting Room (7th floor)

Emanuele Pavia -- An invitation to derived algebraic geometry Room: Meeting Room (7th floor)

Emanuel Carneiro -- When analysis meets number theory Room: Meeting Room (7th floor)

Andrea Braides -- A game of scales Room: Meeting Room (7th floor)

Ugo Bruzzo -- Moduli Room: Room 128-129 (1st floor)

Jacopo Stoppa -- Complex Geometry Room: Room 128-129 (1st floor)

Stefano Pasquali -- Stability and instability phenomena in fluids Room: Room 128-129 (1st floor)

Sebastian Goldt -- Elements of a modern theory for deep neural networks Room: Room 128-129 (1st floor) Deep neural networks are complex functions composed of a large number of simple units called neurons. Their remarkable success in machine learning, where they excel in high-dimensional problems when they have a large number of parameters, has challenged classical theories of learning. Understanding how learning emerges from the interaction of millions of neurons presents a deep theoretical challenge for mathematicians, physicists and statisticians. In this talk, I will give a brief introduction into what neural networks are and how they learn. Then I will argue that a modern theory of deep learning will have to explain how learning emerges from the interplay of network architecture, the learning algorithm, and the structure of the training data.

Antonio Lerario -- Convex bodies and algebraic geometry Room: Room 005 (ground floor) In this seminar I will discuss some interesting and unexpected connections between the problem of counting the number of solutions to a system of algebraic equations and computing the volume of a certain convex set associated to the system -- magically they turn out to be essentially the same problem!

Luca Talamini -- Hyperbolic Conservation Laws Room: Room 005 (ground floor)

Marcello Porta -- Mathematical Quantum Statistical Physics Room: Room 005 (ground floor)