trekhleb/micrograd-ts

🤖 A TypeScript version of karpathy/micrograd — a tiny scalar-valued autograd engine and a neural net on top of it

38
/ 100
Emerging

This tool helps software developers understand the core mechanics of neural networks and how they learn. It takes basic mathematical operations and builds them into a simple neural network structure. The output is a clear visualization of how derivatives are calculated and how a network trains by adjusting its internal parameters.

No commits in the last 6 months.

Use this if you are a software developer who wants to deeply understand the foundational math behind neural networks and backpropagation, especially in a TypeScript environment.

Not ideal if you are looking for a high-level library to build complex neural networks for production applications without needing to understand the underlying math.

neural-networks machine-learning-education backpropagation deep-learning-fundamentals typescript-development
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 9 / 25
Maturity 16 / 25
Community 13 / 25

How are scores calculated?

Stars

72

Forks

9

Language

TypeScript

License

MIT

Last pushed

Sep 10, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/trekhleb/micrograd-ts"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.