Marviel/lab-grad
An Automated Differentiation library (like Pytorch🔥) in Typescript, for educational purposes.
This is an educational tool for anyone interested in understanding how neural networks learn. It takes basic mathematical operations and shows you how an 'autograd' system calculates the necessary adjustments for a neural network to learn a task, like solving the XOR problem. It's designed for students or enthusiasts learning about machine learning concepts.
No commits in the last 6 months.
Use this if you are studying the foundational math behind neural networks and want to see an automatic differentiation engine in action, directly in your browser.
Not ideal if you need a production-ready system to build or run neural networks in a browser for real-world applications; look into alternatives like ONNX for that.
Stars
22
Forks
1
Language
TypeScript
License
—
Category
Last pushed
Jan 18, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/Marviel/lab-grad"
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