# Best way to learn differentiable computing?

**URL:** <https://discourse.julialang.org/t/best-way-to-learn-differentiable-computing/50955>\
**Category:** Machine Learning\
**Created:** [November 29, 2020, 7:59pm UTC](https://discourse.julialang.org/t/best-way-to-learn-differentiable-computing/50955 "2020-11-29T19:59:59Z")\
**Posts on this page:** 2\
**Page:** 1

<div class="post-metadata">

**Author:** ![StatisticalMouse](https://sea2.discourse-cdn.com/julialang/user_avatar/discourse.julialang.org/statisticalmouse/32/43370_2.png) [@StatisticalMouse](https://discourse.julialang.org/u/StatisticalMouse)\
**Post date:** [November 29, 2020, 7:59pm UTC](https://discourse.julialang.org/t/best-way-to-learn-differentiable-computing/50955/1 "2020-11-29T19:59:59Z")

</div>

What would be the best resource to get started?  
Also, what would be the ‘state of the art’ in this area right now?

---

<div class="post-metadata">

**Author:** ![Tamas\_Papp](https://sea2.discourse-cdn.com/julialang/user_avatar/discourse.julialang.org/tamas_papp/32/25949_2.png) [@Tamas\_Papp](https://discourse.julialang.org/u/Tamas_Papp)\
**Post date:** [November 30, 2020, 3:52pm UTC](https://discourse.julialang.org/t/best-way-to-learn-differentiable-computing/50955/2 "2020-11-30T15:52:28Z")

</div>

For understanding the theory, I would start with the relevant chapter in

> **[Numerical Optimization](https://link.springer.com/book/10.1007/978-0-387-40065-5)**

Then

[https://mitmath.github.io/18337/#lecture-11-differentiable-programming-and-neural-differential-equations](https://mitmath.github.io/18337/#lecture-11-differentiable-programming-and-neural-differential-equations)

is a nice intro.

For a recent overview on the ecosystem,

> **[Glue AD for Full Language Differentiable Programming - Stochastic Lifestyle](https://www.stochasticlifestyle.com/glue-ad-for-full-language-differentiable-programming/)**
>
> No design choice will be the best choice for all possible users. That’s a statement that is provocative but at the same time I think everyone would easily agree with it. But that should make us all question whether it’s a good idea to ever try and...

There are many more resources if you have specific questions.