jewelltaylor/camlgrad
Toy autograd engine in OCaml with Apple Accelerate backend
This project helps machine learning practitioners or researchers define and train neural networks, specifically multi-layer perceptrons, in OCaml. You can input raw data, define your network architecture, and then calculate predictions and errors. The output is a trained model and optionally, a visual diagram of the network's computation flow, helping you understand how data transforms.
No commits in the last 6 months.
Use this if you are an OCaml developer or researcher who needs a lightweight, customizable automatic differentiation engine for building and experimenting with neural networks on Apple hardware.
Not ideal if you prefer widely adopted machine learning frameworks like TensorFlow or PyTorch, or if you are not comfortable working within the OCaml ecosystem.
Stars
30
Forks
—
Language
OCaml
License
—
Category
Last pushed
Jul 31, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/jewelltaylor/camlgrad"
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