mohamedrxo/simplegrad

SimpleGrad – a minimal NumPy-based autograd and neural network framework for learning automatic differentiation and basic deep learning concepts.

/ 100

Experimental

This library helps developers understand how automatic differentiation, a core concept in machine learning, works from the ground up. It takes numerical data as input and allows users to build simple neural networks and compute gradients for learning. It's designed for software developers, students, or researchers who are learning the foundational mechanics of deep learning frameworks.

No commits in the last 6 months.

Use this if you are a developer learning the underlying principles of machine learning libraries like PyTorch or TensorFlow.

Not ideal if you are looking for a high-performance, production-ready machine learning framework for building complex models.

deep-learning-education autodiff-learning neural-network-fundamentals machine-learning-concepts framework-internals

No License Stale 6m No Package No Dependents

Maintenance 2 / 25

Adoption 4 / 25

Maturity 7 / 25

Community 0 / 25

How are scores calculated?

Stars

Forks

—

Language

Jupyter Notebook

License

—

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

Explore ML Frameworks

All categories Trending ML Framework directory Insights