javascript-machine-learning/mnist-neural-network-deeplearnjs

🍃 Using a Neural Network to recognize MNIST digets in JavaScript.

19
/ 100
Experimental

This project helps you build a system that can automatically identify handwritten digits. You feed it images of individual numbers, and it tells you which digit (0-9) it believes it is. This is useful for anyone working with data entry, form processing, or educational applications involving handwritten numerical input.

No commits in the last 6 months.

Use this if you need a basic demonstration of how to classify handwritten numerical images using a neural network within a web browser environment.

Not ideal if you need to recognize more complex shapes, text, or objects beyond simple handwritten digits, or if you require production-grade accuracy for critical systems.

handwriting-recognition digit-classification image-processing data-entry-automation
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 7 / 25
Maturity 8 / 25
Community 4 / 25

How are scores calculated?

Stars

25

Forks

1

Language

JavaScript

License

Last pushed

Dec 28, 2017

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/javascript-machine-learning/mnist-neural-network-deeplearnjs"

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