Stéphane Mallat: "Deep Generative Networks as Inverse Problems"

New Deep Learning Techniques 2018

"Deep Generative Networks as Inverse Problems"
Stéphane Mallat, École Normale Supérieure

Abstract: Generative Adversarial Networks and Variational Auto-Encoders provide impressive image generations from Gaussian white noise, which are not well understood. We show that such generations do not require to learn a discriminator or an encoder. They are computed with a scattering transform which preserve the deformation properties of image synthesis. The deep convolutional network generator is calculated as the solution of a regularized inverse problem. We show that this approach also applies to time-series and audio synthesis, thus providing an alternative to recurrent neural networks and wavenets. Numerical results will be shown on images and audio signals.

Joint work with Tomas Angles and Mathieu Andreux, École Normale Supérieure, Collège de France.

Institute for Pure and Applied Mathematics, UCLA
February 6, 2018

For more information: http://www.ipam.ucla.edu/programs/workshops/new-deep-learning-techniques/?tab=overview

Видео Stéphane Mallat: "Deep Generative Networks as Inverse Problems" канала Institute for Pure & Applied Mathematics (IPAM)