tanaymeh/nadl
A small framework that can perform automatic differentiation to calculate first-order gradients of numpy arrays.
This is a basic automatic differentiation library designed for developers who want to calculate first-order gradients of numerical operations. You input numerical data as NumPy arrays, define operations using the library's tensor object, and it outputs the gradients with respect to those inputs. It's for Python developers building or experimenting with machine learning algorithms from scratch.
No commits in the last 6 months.
Use this if you are a Python developer looking to understand or implement automatic differentiation for simple numerical operations without relying on larger deep learning frameworks.
Not ideal if you need high-performance gradient calculations, advanced machine learning features, or GPU acceleration for complex models, as this is a basic, educational implementation.
Stars
18
Forks
3
Language
Python
License
MIT
Category
Last pushed
May 08, 2022
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/tanaymeh/nadl"
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