Best way to learn differentiable computing?

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

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

Then

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

is a nice intro.

For a recent overview on the ecosystem,

There are many more resources if you have specific questions.