# Computing the jacobian of NN while using Lux

**URL:** <https://discourse.julialang.org/t/computing-the-jacobian-of-nn-while-using-lux/93059>\
**Category:** Modelling & Simulations\
**Created:** [January 17, 2023, 12:02am UTC](https://discourse.julialang.org/t/computing-the-jacobian-of-nn-while-using-lux/93059 "2023-01-17T00:02:34Z")\
**Posts on this page:** 1\
**Showing post:** 7

<div class="post-metadata">

**Author:** ![clm](https://sea2.discourse-cdn.com/julialang/user_avatar/discourse.julialang.org/clm/32/45923_2.png) [@clm](https://discourse.julialang.org/u/clm)\
**Post date:** [August 22, 2024, 2:17pm UTC](https://discourse.julialang.org/t/computing-the-jacobian-of-nn-while-using-lux/93059/7 "2024-08-22T14:17:05Z")

</div>

Lux now allows nested AD to be done pretty seemlessly. See the announcement [here](https://discourse.julialang.org/t/nested-ad-with-lux-etc/113573). Lux also supports batched jacobians (batched\_jacobian), which might be helpful depending on your use case.

---

_[View the full topic](https://discourse.julialang.org/t/computing-the-jacobian-of-nn-while-using-lux/93059)._