Thu, 12 Nov 2020
16:00 -
17:00
Virtual
Understanding Concentration and Separation in Deep Neural Networks
Stéphane Mallat
(College de France)
Further Information
Abstract
Deep convolutional networks have spectacular performances that remain mostly not understood. Numerical experiments show that they classify by progressively concentrating each class in separate regions of a low-dimensional space. To explain these properties, we introduce a concentration and separation mechanism with multiscale tight frame contractions. Applications are shown for image classification and statistical physics models of cosmological structures and turbulent fluids.