BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//wp-events-plugin.com//7.2.3.1//EN
TZID:Europe/Paris
X-WR-TIMEZONE:Europe/Paris
BEGIN:VEVENT
UID:5694@i2m.univ-amu.fr
DTSTART;TZID=Europe/Paris:20230317T143000
DTEND;TZID=Europe/Paris:20230317T153000
DTSTAMP:20241120T200149Z
URL:https://www.i2m.univ-amu.fr/evenements/hamiltonian-monte-carlo-bayesia
 n-optimization-for-sparse-deep-neural-networks/
SUMMARY:Lotfi Chaari (IRIT-ENSEEIHT\, Toulouse): Hamiltonian Monte Carlo Ba
 yesian optimization for sparse deep neural networks
DESCRIPTION:Lotfi Chaari: The performance of a deep neural network strongly
  depends on the optimization method used during the learning process. In s
 upervised learning\, the essence of most architectures is to build an opti
 mization model and learn the parameters from the available training data. 
 In this sense\, regularization is usually employed for the sake of stabili
 ty or uniqueness of the solution. When non-smooth regularizers such as the
  l1 norm are used to promote sparse networks\, this optimization becomes d
 ifficult due to the non-differentiability of the target criterion\, which 
 may also be non-convex. We propose a Bayesian optimization framework based
  on an MCMC scheme that allows efficient sampling even for non-smooth ener
 gy function. We demonstrate that using the proposed method for image class
 ification leads to high-accuracy results that cannot be achieved using cla
 ssical optimizers.\n[su_spacer size="10"]\n\n\nSéminaire Signal et Appren
 tissage[su_spacer size="10"]
ATTACH;FMTTYPE=image/jpeg:https://www.i2m.univ-amu.fr/wp-content/uploads/2
 023/02/Lotfi_Chaari.png
CATEGORIES:Séminaire,Signal et Apprentissage
LOCATION:I2M Chateau-Gombert - CMI\, 39 Rue Joliot Curie\, Marseille\, 1301
 3\, France
X-APPLE-STRUCTURED-LOCATION;VALUE=URI;X-ADDRESS=39 Rue Joliot Curie\, Marse
 ille\, 13013\, France;X-APPLE-RADIUS=100;X-TITLE=I2M Chateau-Gombert - CMI
 :geo:0,0
END:VEVENT
BEGIN:VTIMEZONE
TZID:Europe/Paris
X-LIC-LOCATION:Europe/Paris
BEGIN:STANDARD
DTSTART:20221030T020000
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
TZNAME:CET
END:STANDARD
END:VTIMEZONE
END:VCALENDAR