ETH Zürich DLSC: Physics-Informed Neural Networks - Limitations and Extensions

Поділитися
Вставка
  • Опубліковано 2 лис 2024

КОМЕНТАРІ • 9

  • @dholgadom
    @dholgadom 4 місяці тому +3

    Excellent PINN classes with real application examples!!

  • @피클모아태산
    @피클모아태산 Рік тому +2

    Great overview of PINN in 2023

  • @uqyge
    @uqyge Рік тому +3

    great course

  • @ezyxas
    @ezyxas Рік тому +1

    Thank you for the great lecture. Question: I understand how periodic boundary conditions can work with discretized PINNs, but how are they supposed to fork with fully connected networks (continuous PINNs that use Autograd)?

  • @rito_ghosh
    @rito_ghosh Рік тому

    Wonderful course. Can we please have the slides for each lecture?

    • @CAMLabETHZurich
      @CAMLabETHZurich  3 місяці тому

      All the slides are now available on our course webpage: camlab.ethz.ch/teaching/deep-learning-in-scientific-computing-2023.html

  • @NiccolòMaffezzoli
    @NiccolòMaffezzoli 11 місяців тому

    Can the slides be made available for private use ? Thanks

    • @CAMLabETHZurich
      @CAMLabETHZurich  3 місяці тому

      All the slides are now available on our course webpage: camlab.ethz.ch/teaching/deep-learning-in-scientific-computing-2023.html

  • @afrahnajib1218
    @afrahnajib1218 Рік тому

    There is only one like which you may not care about? please share more!