# How to normalize the input when solving ODE system by NeuralPDE

**URL:** <https://discourse.julialang.org/t/how-to-normalize-the-input-when-solving-ode-system-by-neuralpde/102045>\
**Category:** General Usage\
**Tags:** ode, neural-network\
**Created:** [July 24, 2023, 9:59pm UTC](https://discourse.julialang.org/t/how-to-normalize-the-input-when-solving-ode-system-by-neuralpde/102045 "2023-07-24T21:59:58Z")\
**Posts on this page:** 2\
**Page:** 1

<div class="post-metadata">

**Author:** ![Ethan\_Tran](https://sea2.discourse-cdn.com/julialang/user_avatar/discourse.julialang.org/ethan_tran/32/49198_2.png) [@Ethan\_Tran](https://discourse.julialang.org/u/Ethan_Tran)\
**Post date:** [July 24, 2023, 9:59pm UTC](https://discourse.julialang.org/t/how-to-normalize-the-input-when-solving-ode-system-by-neuralpde/102045/1 "2023-07-24T21:59:58Z")

</div>

For training data by the neural network in machine learning, the data should be normalized before using the neural network to train.  
So do we have any function to normalize (scale) the input before training and solving by NeuralPDE?

---

<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:** [July 25, 2023, 8:55am UTC](https://discourse.julialang.org/t/how-to-normalize-the-input-when-solving-ode-system-by-neuralpde/102045/2 "2023-07-25T08:55:22Z")

</div>

Not automatically. One can use the normalization layers in the machine learning libraries though.