Focaliser sur:  Cacher les contributions
S'authentifier

Journée(s) Machine Learning et Physique Nucléaire

29–30 oct. 2019
Orsay
Fuseau horaire Europe/Paris

O. Stezowski

Session

Machine Learning en Physique Nucléaire

30 oct. 2019, 09:00
Bâtiment 108, 1er étage (Orsay)

Bâtiment 108, 1er étage

Orsay

Documents de présentation

Aucun document.

  1. 9. Intelligence artificielle et machine learning pour l'étude de réacteurs et de scénarios électro-nucléaires
    Marc ERNOULT (IPNO)
    30/10/2019 09:00
  2. 12. Algorithme d'auto-apprentissage sur des signaux de courant issus de détecteurs silicium.
    Marin Chabot (Institut de physique Nucléaire d'Orsay)
    30/10/2019 09:30
  3. 11. GPU, Machine Learning et Online
    Vincent LAFAGE (CNRS)
    30/10/2019 10:00
  4. 10. Machine Learning @ ILL
    Paolo Mutti (ILL)
    30/10/2019 10:30

    Recently, by using deep learning methods, computers are able to surpass or come close to matching human performance on image analysis and pattern recognition. This advanced method could also help interpreting data from neutron scattering experiments. Those data contain rich scientific information about structure and dynamics of materials under investigation, and deep learning could help...

    Go to contribution page
  5. 13. Tracking particles in an active target
    Thomas ROGER (GANIL)
    30/10/2019 11:30
  6. 16. learning to unmix in gamma-ray spectrometry
    Jiaxin Xu (LMRE / IRSN)
    30/10/2019 11:45

    In the context of gamma-ray spectrum analysis, spectral unmixing tackles the activity estimation problem as an inverse problem, where individual activities appear as mixing weights related to individual spectra. Current approaches are agnostic to the available archive of past measurements, which bring valuable information to perform accurate radionuclide activity estimation. For that purpose,...

    Go to contribution page
  7. 14. Taming nuclear complexity using deep neural networks
    Raphael-David Lasseri (CEA)
    30/10/2019 12:00
  8. 15. NPB, MCMC, GPE and other funny acronyms
    Alessandro Pastore (University of York)
    30/10/2019 12:30

    In my talk i will discuss parameter estimate of a simple liquid drop model using at first simple Monte Carlo methods. The goal is to capture the correlations in the residuals and get a better estimate of error bars.
    I will then apply Gaussian Process Emulator to investigate how to study the chi2 surface and speed up the convergence process.

    Go to contribution page
Ordre du jour en construction...