BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//132.216.98.100//NONSGML kigkonsult.se iCalcreator 2.20.4//
BEGIN:VEVENT
UID:20260602T064126EDT-4571z93pRj@132.216.98.100
DTSTAMP:20260602T104126Z
DESCRIPTION:We would like to emphasize that all faculty\, students and post
 docs are invited to attend the talks.\n\nMoreover\, if desired\, we would 
 like to offer assistance on traveling to the CRM via metro—if there is int
 erest\, we may organize traveling as a group.\n\nIf you would like to sign
  up to the mailing list\, please contact scarpa.carlo [at] uqam.ca\n\nTitl
 e: Elements of compressed sensing with deep generative models\n\nAbstract:
  Compressed sensing (CS) is an impressive modern theory in applied mathema
 tics that has revolutionized signal processing. CS permits recovery of hig
 h-dimensional structured signals from random\, underdetermined and corrupt
 ed linear measurements. Typically\, the measurement matrix of the linear s
 ystem is random (e.g.\, has independent identically distributed Gaussian e
 ntries)\, and recovery is guaranteed with high probability on its realizat
 ion. On the other hand\, deep generative models have garnered renown for t
 heir impressive ability to effectively model the manifold of natural image
 s. Such models are frequently comprised of alternating compositions of aff
 ine transformations and piecewise linear nonlinearities. Recently\, it was
  proved that this type of generative model can serve as the underlying str
 ucture for compressed sensing problems. In this talk we provide a foundati
 onal understanding of compressed sensing\, an overview of deep learning re
 levant to the design of effective natural signal modelling\, and highlight
  the key elements that connect these seemingly disparate topics.\n\nZoom l
 ink: on request\n\nFree coffee ☕ and cookies 🍪 will be offered after the t
 alk.\n\nVenue: Salle 4336-4384\, Pav. André Aisenstadt\, UdeM\n
DTSTART:20230328T180000Z
DTEND:20230328T190000Z
SUMMARY:Postdocs at CRM Seminar- Aaron Berk (91������)
URL:/mathstat/channels/event/postdocs-crm-seminar-aaro
 n-berk-mcgill-university-347203
END:VEVENT
END:VCALENDAR