# JuliaSimModelOptimiser, UDEs, network and model connection

**URL:** https://discourse.julialang.org/t/juliasimmodeloptimiser-udes-network-and-model-connection/107569
**Category:** Machine Learning
**Tags:** juliasim
**Created:** [December 13, 2023, 2:19pm UTC](https://discourse.julialang.org/t/juliasimmodeloptimiser-udes-network-and-model-connection/107569 "2023-12-13T14:19:17Z")
**Posts on this page:** 2
**Page:** 1

<div class="post-metadata">

### Author: ![rpex](https://sea2.discourse-cdn.com/julialang/user_avatar/discourse.julialang.org/rpex/32/204786_2.png) [@rpex](https://discourse.julialang.org/u/rpex)
#### Post date: [December 13, 2023, 2:19pm UTC](https://discourse.julialang.org/t/juliasimmodeloptimiser-udes-network-and-model-connection/107569/1 "2023-12-13T14:19:17Z")

</div>

When I use [Neural Automated Model Discovery for Autocompleting Models with Prior Structural Information from JuliaSimModelOptimiser](https://help.juliahub.com/jsmo/stable/tutorials/autocomplete/).

How is the neural network connected with the incomplete model? Is it:

\frac{d states}{dt} = model\_{incomplete}(states) + model\_{network}(states)

Can I control this connection through JuliaSimModelOptimizer? Or do I always have to provide a network that uses the same number of inputs, outputs and states?

---

<div class="post-metadata">

### Author: ![SebastianM-C](https://sea2.discourse-cdn.com/julialang/user_avatar/discourse.julialang.org/sebastianm-c/32/2480_2.png) [@SebastianM-C](https://discourse.julialang.org/u/SebastianM-C)
#### Post date: [December 13, 2023, 3:24pm UTC](https://discourse.julialang.org/t/juliasimmodeloptimiser-udes-network-and-model-connection/107569/2 "2023-12-13T15:24:32Z")

</div>

Currently the way the network is connected is not very flexible (it’s just added to all states as you mentioned), but we are looking to improve that.