https://github.com/primaryobjects/colorbot
A neural network color bot that uses machine learning (artificial intelligence) to categorize pictures as red, green, or blue overall. Uses node.js and mongodb.
https://github.com/primaryobjects/colorbot
Last synced: 10 months ago
JSON representation
A neural network color bot that uses machine learning (artificial intelligence) to categorize pictures as red, green, or blue overall. Uses node.js and mongodb.
- Host: GitHub
- URL: https://github.com/primaryobjects/colorbot
- Owner: primaryobjects
- Created: 2013-05-30T16:54:11.000Z (over 12 years ago)
- Default Branch: master
- Last Pushed: 2020-08-28T22:20:16.000Z (over 5 years ago)
- Last Synced: 2024-10-29T22:50:29.115Z (about 1 year ago)
- Language: JavaScript
- Size: 6.74 MB
- Stars: 25
- Watchers: 6
- Forks: 14
- Open Issues: 0
-
Metadata Files:
- Readme: readme.md
Awesome Lists containing this project
README
ColorBot Neural Network
=======================
## Demo
http://colorbot.herokuapp.com
## About
ColorBot Neural Network uses machine learning (ie., artificial intelligence) to learn which pictures are generally red, green, or blue overall. It does this by using a trained neural network, which functions similar to the human brain.
The neural network (we'll call it the 'brain') was initially trained to 100% accuracy on a collection of 258 images. Each image was labeled as being red, green, or blue in nature. The brain used backpropagation to reduce the errors until it arrived at the target accuracy rate.
Once training was complete, the brain tried guessing the color on 470 images that it's never seen before. On this test set, the brain achieved an accuracy of 97.6%. Not bad!
The app uses node.js, mongodb, and twitter bootstrap.
## Configuration
Set the environment variable `MONGO_URL` to your database connection string.
#### Linux
```bash
export MONGO_URL=mongodb://
```
#### Windows
```bash
SET MONGO_URL=mongodb://
```
Then run the app.
```bash
node app
```