Focus on:  Hide Contributions
Login

IML Machine Learning Working Group: open topic

→ Europe/Zurich
222/R-001 (CERN)

222/R-001

CERN

200
Show room on map
Description

Agenda under development. If you like to present, please contact iml.coordinators@cern.ch

    • 14:00 → 15:00
      Seminar
      • 14:00
        EP-IT data science seminar: Soumith Chintala (Facebook): Automatic Differentiation and Deep Learning PLEASE JOIN THIS SESSION THROUGH WEBCAST FROM THE SEMINAR PAGE 1h

        https://indico.cern.ch/event/689421/

        Statistical learning has been getting more and more interest from the particle-physics community in recent times, with neural networks and gradient-based optimization being a focus.

        In this talk we shall discuss three things:

        • automatic differention tools: tools to quickly build DAGs of computation that are fully differentiable. We shall focus on one such tool "PyTorch".

        • Easy deployment of trained neural networks into large systems with many constraints: for example, deploying a model at the reconstruction phase where the neural network has to be integrated into CERN's bulk data-processing C++-only environment

        • Some recent models in deep learning for segmentation and generation that might be useful for particle physics problems.

        Please note that a Webcast retransmission will be available for this Seminar.

        Seminar agenda page
        webcast
    • 15:00 → 18:00
      Regular IML meeting
Powered by Indico v3.3.2-pre