# NeuralODE Layer Strategy

**URL:** <https://discourse.julialang.org/t/neuralode-layer-strategy/71297>\
**Category:** New to Julia\
**Tags:** machine-learning, differentialequation\
**Created:** [November 11, 2021, 12:49am UTC](https://discourse.julialang.org/t/neuralode-layer-strategy/71297 "2021-11-11T00:49:41Z")\
**Posts on this page:** 1\
**Showing post:** 4

<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:** [November 12, 2021, 6:32am UTC](https://discourse.julialang.org/t/neuralode-layer-strategy/71297/4 "2021-11-12T06:32:08Z")

</div>

You weren’t returning the array you were creating in `pend`.

```julia
function pend(u)
    θ = u[1]
    dθ = u[2]
    [dθ,-(g/L)*sin(θ)]
end

```

is fine. Then you probably want to do multiple shooting here.

---

_[View the full topic](https://discourse.julialang.org/t/neuralode-layer-strategy/71297)._