What it does
Autograd automatically calculates derivatives, the measure of how a result changes when its inputs change, for ordinary Python and NumPy code. This is the core maths behind training neural networks.
It handles loops, if-statements and other normal code, and can take derivatives of derivatives. Its main intended use is gradient-based optimisation, a step-by-step way of improving a model.
The README includes examples such as simple neural networks and a fluid simulation.
Who it's for
Researchers and programmers who write their own machine learning or optimisation code in Python.
Can I use it without coding?
Developers only. It's a Python code library. New to this? Start here.
Can I run it?
- Cost
- FreeNothing to pay or sign up for.
- Computer
- An ordinary computer is fine
- Privacy
- Runs on your own device: your data stays with you
- API key
- Not needed
Try it
Using Claude Code, Cursor or another AI coding assistant? Paste the prompt and it will walk you through the setup.New to this?
Before you install
- Only download from the official GitHub page. Copies with similar names exist for many popular projects.
- License (MIT): Very permissive: free to use, change and share, including for business.
- More on staying safe