I am struggling to implement automatic differentiation in a plug-in library... can anybody help? No one has ever tried to add it at all, and it is a pain to find the derivative or the integral by hand.

I am struggling to implement automatic differentiation in a plug-in library... can anybody help? No one has ever tried to add it at all, and it is a pain to find the derivative or the integral by hand.

0

The Deriv class in jlb.ulb does first and second derivatives of simple functions to a power, such as sin(z)^n. Other functions could be added.

These derivatives are courtesy of https://www.derivative-calculator.net/

The Deriv class in jlb.ulb does first and second derivatives of simple functions to a power, such as sin(z)^n. Other functions could be added. These derivatives are courtesy of https://www.derivative-calculator.net/
edited Jun 11 at 2:24 pm

0

But what if there was a way to apply the algorithms of automatic differentiation from https://github.com/autodiff/autodiff

in Ultra Fractal?

But what if there was a way to apply the algorithms of automatic differentiation from https://github.com/autodiff/autodiff in Ultra Fractal?

0

Someone would need to write an UF equivalent which is definitely possible (albeit not with the nice syntax that you get in modern C++).

Someone would need to write an UF equivalent which is definitely possible (albeit not with the nice syntax that you get in modern C++).

Ultra Fractal author

0

Then I had something in my head, a neuron activation of sorts: what if we used dual numbers, as well as nodes, forward mode and reverse mode autodifferentiation in UF?

Then I had something in my head, a neuron activation of sorts: what if we used dual numbers, as well as nodes, forward mode and reverse mode autodifferentiation in UF?

0

So where do we begin, @ultrafractal ? First of all, we can think of a few ways to accomplish this: through nodes, for example.

So where do we begin, @ultrafractal ? First of all, we can think of a few ways to accomplish this: through nodes, for example.

0
128
views
5
replies
3
followers
live preview
Enter at least 10 characters.
WARNING: You mentioned %MENTIONS%, but they cannot see this message and will not be notified
Saving...
Saved
All posts under this topic will be deleted ?
Pending draft ... Click to resume editing