CMU-IDeeL/new_grad
A new lightweight auto-differentation library that directly builds on numpy. Used as a homework for CMU 11785/11685/11485.
This project is a lightweight automatic differentiation library designed for students learning deep learning concepts. It takes standard numerical data (like NumPy arrays) and calculates the gradients needed to train machine learning models. It's intended for students enrolled in deep learning courses who want to understand the core mechanics of how modern deep learning frameworks compute gradients.
No commits in the last 6 months.
Use this if you are a student in a deep learning course looking to build and understand an automatic differentiation engine from scratch, without the complexities of advanced tensor classes.
Not ideal if you are a practitioner or researcher needing a robust, production-ready deep learning framework for large-scale model training.
Stars
40
Forks
11
Language
Python
License
—
Category
Last pushed
Feb 07, 2022
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/CMU-IDeeL/new_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