ocramz/ad-delcont
Reverse-mode automatic differentiation with delimited continuations
This project helps Haskell developers implement reverse-mode automatic differentiation within their applications. By using delimited continuations, it takes a computational graph (your code) and efficiently produces the gradients of a function with respect to its inputs. This tool is for Haskell programmers who need to calculate derivatives for optimization, machine learning, or scientific computing tasks.
No commits in the last 6 months.
Use this if you are a Haskell developer looking for a way to perform reverse-mode automatic differentiation directly within your Haskell codebase.
Not ideal if you are not a Haskell developer or if you need forward-mode automatic differentiation.
Stars
16
Forks
2
Language
Haskell
License
BSD-3-Clause
Category
Last pushed
Jul 03, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/ocramz/ad-delcont"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
JonathanRaiman/theano_lstm
:microscope: Nano size Theano LSTM module
google/tangent
Source-to-Source Debuggable Derivatives in Pure Python
ahrefs/ocannl
OCANNL: OCaml Compiles Algorithms for Neural Networks Learning
yoshoku/numo-openblas
Numo::OpenBLAS builds and uses OpenBLAS as a background library for Numo::Linalg
statusfailed/catgrad
a categorical deep learning compiler