Personal website Rudolf Adamkovič

Home / Deep learning / Automatic differentiation


Pros and cons

Pros:

  • fast execution
  • exact results 1

Cons:

  • requires prior evaluation and caching of itermediate results
  • no symbolic representation of the derivative

Footnotes:

1

Ignoring e.g. floating point precision loss.


© 2025 Rudolf Adamkovič under GNU General Public License version 3.
Made with Emacs and secret alien technologies of yesteryear.