https://github.com/victorqribeiro/digitRecognition

Implementation of a digit recognition using my Neural Network with the MNIST data set.
https://github.com/victorqribeiro/digitRecognition

classification javascript machine-learning mnist multilayer-perceptron neural-network

Last synced: 18 days ago
JSON representation

Implementation of a digit recognition using my Neural Network with the MNIST data set.

• Host: GitHub
• URL: https://github.com/victorqribeiro/digitRecognition
• Owner: victorqribeiro
• License: mit
• Created: 2019-04-11T19:23:25.000Z (over 5 years ago)
• Default Branch: master
• Last Pushed: 2019-10-15T22:45:32.000Z (about 5 years ago)
• Last Synced: 2024-08-01T00:50:17.243Z (3 months ago)
• Topics: classification, javascript, machine-learning, mnist, multilayer-perceptron, neural-network
• Language: JavaScript
• Homepage: https://victorribeiro.com/digitRecognition/
• Size: 2.06 MB
• Stars: 22
• Watchers: 2
• Forks: 3
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

        
# Digit Recognition

Implementation of a digit recognition using a neural network with [MNIST](http://lorenhoward.com/articles/mnist-handwritten-dataset-json/)

![Digit Recognition](screenshot.png)

Live version [here](https://victorribeiro.com/digitRecognition)

## About

I made this experiment to test how long it would take to train my neural network with MNIST and how accurate it would be at the end. Turns out I have a long way to go.

## How to use it

Draw the digit on the white rectangle (try to use to whole area) and press predict for the neural network indentify the digit. Press clear to clear the white drawing area.