# Training of a universal differential equation on multiple initial states and mini-batches

**URL:** https://discourse.julialang.org/t/training-of-a-universal-differential-equation-on-multiple-initial-states-and-mini-batches/132174
**Category:** General Usage
**Created:** [September 8, 2025, 12:08pm UTC](https://discourse.julialang.org/t/training-of-a-universal-differential-equation-on-multiple-initial-states-and-mini-batches/132174 "2025-09-08T12:08:37Z")
**Posts on this page:** 2
**Page:** 1

<div class="post-metadata">

### Author: ![Xhemal\_Kodragjini](https://sea2.discourse-cdn.com/julialang/user_avatar/discourse.julialang.org/xhemal_kodragjini/32/218573_2.png) [@Xhemal\_Kodragjini](https://discourse.julialang.org/u/Xhemal_Kodragjini)
#### Post date: [September 8, 2025, 12:08pm UTC](https://discourse.julialang.org/t/training-of-a-universal-differential-equation-on-multiple-initial-states-and-mini-batches/132174/1 "2025-09-08T12:08:37Z")

</div>

Hi,  
I am training a UDE controlled by an input signal as part of my thesis. To be able to get a more generalized neural network on multiple data, I want to train on around 1000 different initial states and use mini-batches on the go.  
I was not able to find some example of training with multiple initial states so far. Is there any available? If not, what approach should be used?

Many thanks in advance

---

<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: [October 24, 2025, 1:20pm UTC](https://discourse.julialang.org/t/training-of-a-universal-differential-equation-on-multiple-initial-states-and-mini-batches/132174/2 "2025-10-24T13:20:07Z")

</div>

It’s very common to do it, but yeah… I’m surprised… I don’t see a tutorial on it 😅. Did you end up writing something? I’d like to make sure we make it into a tutorial