BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Memento EPFL//
BEGIN:VEVENT
SUMMARY:Unsupervised Learning and Deep Generative Networks
DTSTART:20180323T140000
DTEND:20180323T144500
DTSTAMP:20260407T091605Z
UID:a48d3d3aa55ed36f81c14413551d922afb777fe08a094f7bbb4f2aa1
CATEGORIES:Conferences - Seminars
DESCRIPTION:Stéphane Mallat\nSummary\nGenerative convolutional networks h
 ave obtained spectacular results to synthesize complex signals such as ima
 ges\, speech\, music\, with barely any mathematical understanding. This le
 cture will move towards this world by beginning from well relatively under
 stood maximum entropy modelization. We shall review deep Generative networ
 ks such as GAN and Variational Encoders\, which can synthesize realization
 s of non-stationary processes or highly complex processes such as speech o
 r music. We will show that they can be simplified by defining the estimati
 on as an inverse problem. It builds a bridge with  maximum entropy estima
 tion. Applications will be shown on images\, speech and music generation.\
 n\nBiography\nStéphane Mallat has made fundamental contributions to the d
 evelopment of wavelet theory. He has also done work in applied mathematics
 \, signal processing\, music synthesis\, and image segmentation. He has de
 veloped (with Yves Meyer) the multi-resolution analysis construction for c
 ompactly supported wavelets\, which made the implementation of wavelets pr
 actical for engineering applications. He has also developed (with Sifen Zh
 ong) the wavelet transform modulus maxima method for image characterizatio
 n. He has introduced the scattering transform that constructs invariance f
 or object recognition purposes. Stéphane Mallat is the author of A Wavele
 t Tour of Signal Processing\, a common text in applied mathematics and eng
 ineering courses. He has held teaching positions at New York University\, 
 Massachusetts Institute of Technology\, École polytechnique\, and at the 
 École normale supérieure. He is currently Professor of Data Science at C
 ollège de France.
LOCATION:CE 1 6 https://plan.epfl.ch/?room==CE%201%206
STATUS:CONFIRMED
END:VEVENT
END:VCALENDAR