Скачать с ютуб Stéphane Mallat: Modeling Deep Networks: Network Learning for Image Processing в хорошем качестве

Stéphane Mallat: Modeling Deep Networks: Network Learning for Image Processing

Recording of Stéphane Mallat’s (Collège de France) talk on November 18, 2021, at the EPFL Seminar Series in Imaging. Abstract. Deep neural network learning from data has taken over image processing. Not just for classificaiton and regression but also for denoising and inverse problems. Is it the end of geometric models and understanding ? Deep network models are high-dimensional and must be analyzed in a probabilistic framework. Yet they must also take into account image properties, including multiscale structures and symmetries. The lecture takes an information theory point of view, and shows that the underlying mathematics are closely related to statistical physics. We introduce a general class of interpretable neural network models through the renormalisation group and multiscale wavelet transforms, with applications to image generation and classification. See upcoming talks on: imagingseminars.org The EPFL Seminar Series in Imaging is run by EPFL Center for Imaging: imaging.epfl.ch