Data Science Lecture Series: Stéphane Mallat

Stephane Mallat
Friday, February 9, 2018 - 14:00
Buchanan 1920
Department of Statistics and Applied Probability and GRAPHIQ present the 2nd Distinguished Lecture Series in Data Science Date/Time: February 9, 2018 at 2:00 pm Location: Buchanan 1920, UC Santa Barbara Live stream: http://live.id.ucsb.edu/ Speaker: Stéphane Mallat (Professor, École Normale Supérieure, France) Title: Learning Physics with Deep Neural Networks Abstract: Machine learning amounts to find low-dimensional models governing the properties of high dimensional functionals. This could almost be called physics. Algorithms have considerably improved in the last 10 years through the processing of massive amounts of data. In particular, deep neural networks have spectacular applications, to image classification, medical, industrial and physical data analysis. We show that the approximation capabilities of deep convolution networks come from their ability to compute invariant at different scales over possibly high-dimensional groups including diffeomorphisms. We shall study the mathematical properties of simplified deep convolutional networks computed with wavelet. We give applications to regression of molecular energies in quantum chemistry. We shall also introduce low-dimensional non-Gaussian intermittent models for statistical physics, with applications to Ising and high Reynold turbulences through cosmological data.