Login

4th ATLAS Machine Learning Workshop

11–15 Nov 2019
CERN
Europe/Zurich timezone

Session

Public

11 Nov 2019, 09:00
6/2-024 - BE Auditorium Meyrin (CERN)

6/2-024 - BE Auditorium Meyrin

CERN

114
Show room on map

Presentation materials

There are no materials yet.

  1. 34. Introduction
    Amir Farbin (University of Texas at Arlington (US)), Dan Guest (University of California Irvine (US))
    11/11/2019, 13:00
  2. 36. Dark Machines
    Bob Stienen
    11/11/2019, 13:27
  3. 30. A deep neural network for simultaneous estimation of b quark energy and resolution for the CMS experiment
    Nadezda Chernyavskaya (Eidgenoessische Tech. Hochschule Zuerich (CH))
    11/11/2019, 13:45

    (note that speaker has to finish before 4pm)

    Go to contribution page
  4. 33. DNNLikelihood
    Riccardo Torre (CERN)
    11/11/2019, 14:10

    We introduce the DNNLikelihood, a novel framework to easily encode, through Deep Neural Networks (DNN), the full experimental information contained in complicated likelihood functions (LFs). We show how to efficiently parametrize the LF, treated as a multivariate function of parameters and nuisance parameters with high dimensionality, as an interpolating function in the form of a DNN...

    Go to contribution page
  5. 32. A deep neural network-based tagger to search for new long-lived particle states decaying to jets
    Vilius Cepaitis (Imperial College (GB))
    11/11/2019, 15:05
  6. 26. Fast Machine Learning Inference on FPGAs for Trigger and DAQ with hls4ml
    Sioni Paris Summers (CERN)
    11/11/2019, 15:35
    Public

    Invited talk

    Go to contribution page
  7. 31. ML Inference in CMSSW
    Huilin Qu (Univ. of California Santa Barbara (US))
    15/11/2019, 14:00
  8. 37. Distributed training and optimization
    Dr Jean-Roch Vlimant (California Institute of Technology (US))
    15/11/2019, 14:35
  9. 2. Adversarial training for ttH(bb) classification
    Paul Glaysher (DESY)
    15/11/2019, 15:35
    Public

    Event classification trained on Monte Carlo data can lead to a training bias towards the generator of the training sample, typically evaluated as a systematic error by comparing to an alternative generator model.
    For the case of the search for a top-quark pair produced in association with a Higgs boson decaying to bottom-quark at the LHC, we demonstrate how adversarial domain adaptation can...

    Go to contribution page
  10. 35. Machine Learning for BSM
    Andrea Wulzer (CERN and EPFL)
    15/11/2019, 16:05
  11. 45. GPUs in Reconstruction
    Dr Charles Leggett (Lawrence Berkeley National Lab (US))
    15/11/2019, 16:40
Building timetable...