Speaker: Prof. Stéphane Mallat, Collège de France- Báo cáo trực tiếp

Talk title: Multiscale Random Models of Deep Neural Networks

Time: 15:00 - 16:30, Monday, April 24, 2023.

Seminar: Hybrid seminar (onsite at VIASM and online) [Registration here]

Abstract: Deep neural networks have spectacular applications but remain mostly a mathematical mystery. An outstanding issue is to understand how they circumvent the curse of dimensionality to generate or classify data. Inspired by the renormalization group in physics, we explain how deep networks can separate phenomena which appear at different scales, and capture scale interactions. It provides high-dimensional model, which approximate the probability distribution of complex physical fields such as turbulences. Learning becomes similar to a compressed sensing problem, where low-dimensional discriminative structures are identified with random projections. Applications to image classification are shown.

Bio: Stéphane Mallat is an applied mathematician, Professor at the Collège de France on the chair of Data Sciences. He is a member of the French Academy of sciences, of the Academy of Technologies and a foreign member of the US National Academy of Engineering. He was a Professor at the Courant Institute of NYU in New York for 10 years, then at Ecole Polytechnique and Ecole Normale Supérieure in Paris. He also was the co-founder and CEO of a semiconductor start-up company. Stéphane Mallat received many prizes for his research in machine learning, signal processing and harmonic analysis. He developed the multiresolution wavelet theory and algorithms at the origin of the compression standard JPEG-2000, and sparse signal representations in dictionaries through matching pursuits. He currently works on mathematical models of deep neural networks, for data analysis and physics.