# ForwardDiffSensitivity Faster than Adjoint Methods

**URL:** <https://discourse.julialang.org/t/forwarddiffsensitivity-faster-than-adjoint-methods/102652>\
**Category:** General Usage\
**Created:** [August 9, 2023, 8:54pm UTC](https://discourse.julialang.org/t/forwarddiffsensitivity-faster-than-adjoint-methods/102652 "2023-08-09T20:54:08Z")\
**Posts on this page:** 1\
**Showing post:** 9

<div class="post-metadata">

**Author:** ![George\_Stepaniants](https://sea2.discourse-cdn.com/julialang/user_avatar/discourse.julialang.org/george_stepaniants/32/47230_2.png) [@George\_Stepaniants](https://discourse.julialang.org/u/George_Stepaniants)\
**Post date:** [August 10, 2023, 4:30pm UTC](https://discourse.julialang.org/t/forwarddiffsensitivity-faster-than-adjoint-methods/102652/9 "2023-08-10T16:30:50Z")

</div>

@ChrisRackauckas apologies for the confusion. I realized that the control input was not causing the latency issue, so I simplified the model to just be a simple neural ODE that accepts an initial condition, no control.

I am however very concerned with the following post [Composing a Neural ODE with another Neural Network](https://discourse.julialang.org/t/composing-a-neural-ode-with-another-neural-network/102682)  
which seems to show a huge slowdown when I optimize a neural ODE composed with a neural network. This is the main problem I am trying to resolve.

---

_[View the full topic](https://discourse.julialang.org/t/forwarddiffsensitivity-faster-than-adjoint-methods/102652)._