Group Abstract Group Abstract

Message Boards Message Boards

[WSS18] Teaching neural networks to solve partial differential equations

POSTED BY: Anurag Kamal
2 Replies
Posted 2 years ago

Thanks for your useful post. However, could you please enlighten some parts of your post?

  1. In fact, I think the "Equation 2: Time-varying non-linear PDEs: Fick's first law of diffusion" is actually the "linear" Heat PDE and it is not nonlinear!

  2. The initial and boundary considitins in the NDSolve[] for Equation 2 are not consistent!

  3. What is "x_0" there?

  4. However, it is possible to correct all such typos, the main issue is that, where is the final function for "predicting"? I mean, give a very simple example in which by receiving a new input coefficient, then we can get the result (not just one figure).

Attachments:
POSTED BY: Faz 1

enter image description here -- you have earned Featured Contributor Badge enter image description here Your exceptional post has been selected for our editorial column Staff Picks http://wolfr.am/StaffPicks and Your Profile is now distinguished by a Featured Contributor Badge and is displayed on the Featured Contributor Board. Thank you!

POSTED BY: EDITORIAL BOARD
Reply to this discussion
Community posts can be styled and formatted using the Markdown syntax.
Reply Preview
Attachments
Remove
or Discard