# Nonlinear PDE with neural network

**URL:** <https://discourse.julialang.org/t/nonlinear-pde-with-neural-network/60358>\
**Category:** Numerics\
**Tags:** question, diffeq, flux, pde\
**Created:** [May 1, 2021, 4:26am UTC](https://discourse.julialang.org/t/nonlinear-pde-with-neural-network/60358 "2021-05-01T04:26:33Z")\
**Posts on this page:** 2\
**Page:** 1

<div class="post-metadata">

**Author:** ![narayan](https://avatars.discourse-cdn.com/v4/letter/n/22d042/32.png) [@narayan](https://discourse.julialang.org/u/narayan)\
**Post date:** [May 1, 2021, 4:26am UTC](https://discourse.julialang.org/t/nonlinear-pde-with-neural-network/60358/1 "2021-05-01T04:26:33Z")

</div>

can we solve nonlinear PDE with the package NeuralPDE.jl? If yes, then how?

---

<div class="post-metadata">

**Author:** ![ChrisRackauckas](https://sea2.discourse-cdn.com/julialang/user_avatar/discourse.julialang.org/chrisrackauckas/32/77_2.png) [@ChrisRackauckas](https://discourse.julialang.org/u/ChrisRackauckas)\
**Post date:** [May 1, 2021, 11:10am UTC](https://discourse.julialang.org/t/nonlinear-pde-with-neural-network/60358/2 "2021-05-01T11:10:09Z")

</div>

Just define a nonlinear PDE and solve it? I don’t get the question. The docs even have tutorials with nonlinear PDEs in there:

[https://neuralpde.sciml.ai/dev/pinn/low\_level/](https://neuralpde.sciml.ai/dev/pinn/low_level/)