# Lotka Volterra Neural ODE

**URL:** <https://discourse.julialang.org/t/lotka-volterra-neural-ode/133159>\
**Category:** Machine Learning\
**Tags:** neural-network\
**Created:** [October 15, 2025, 5:16am UTC](https://discourse.julialang.org/t/lotka-volterra-neural-ode/133159 "2025-10-15T05:16:24Z")\
**Posts on this page:** 1\
**Showing post:** 3

<div class="post-metadata">

**Author:** ![affans](https://sea2.discourse-cdn.com/julialang/user_avatar/discourse.julialang.org/affans/32/11911_2.png) [@affans](https://discourse.julialang.org/u/affans)\
**Post date:** [October 15, 2025, 4:00pm UTC](https://discourse.julialang.org/t/lotka-volterra-neural-ode/133159/3 "2025-10-15T16:00:36Z")

</div>

You may also want to see this [thread](https://discourse.julialang.org/t/why-do-we-need-3-chains-to-solve-a-pde-using-neuralpde/108136). When using the `PhysicsInformedNN` interface, you could use different NN to represent each solution. When using the `NNODE` interface, you can use a single NN with multiple outputs to represent each solution. I see that you are not using either interface and rolling your own solution, so I am not sure if my reply really helps.

---

_[View the full topic](https://discourse.julialang.org/t/lotka-volterra-neural-ode/133159)._