A operator overloading, tape-based, reverse-mode AD
65 Stars
Updated Last
1 Year Ago
Started In
March 2017


CI Stable Docs Latest Docs

No Longer Maintained

This project is no longer actively maintained, as it has been thoroughly superceeded by other AD projects in the Julia ecosystem.


Nabla.jl is a reverse-mode automatic differentiation package targetting machine learning use cases. As such, we have (for example) prioritised support for linear algebra optimisations and higher-order functions over the ability to take higher-order derivatives (Nabla currently only supports first-order derivatives).

The latest docs, and code in the examples folder, best indicate how to use the package. Given the early stage of development, we anticipate a number of bugs and performance issues. If you encounter any of these or have any particular feature requests, please raise an issue and let us know.