ameritusweb/ParallelReverseAutoDiff
Parallel Reverse Mode Automatic Differentiation in C# for Custom Neural Network Development
This library helps C# developers build and train custom neural networks for machine learning applications. It takes a JSON description of your network's architecture and efficiently calculates gradients for updating the network's weights, even leveraging GPUs for faster computations. It's designed for developers creating bespoke AI models rather than using off-the-shelf frameworks.
No commits in the last 6 months.
Use this if you are a C# developer building a custom neural network from scratch and need a high-performance, parallelized solution for automatic differentiation.
Not ideal if you prefer using established machine learning frameworks like TensorFlow or PyTorch, or if you are not comfortable with C# development.
Stars
9
Forks
1
Language
C#
License
LGPL-2.1
Category
Last pushed
May 21, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/ameritusweb/ParallelReverseAutoDiff"
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