https://github.com/anthonyray/littlebrain
Multi-layer Neural Network in Javascript
https://github.com/anthonyray/littlebrain
Last synced: 11 months ago
JSON representation
Multi-layer Neural Network in Javascript
- Host: GitHub
- URL: https://github.com/anthonyray/littlebrain
- Owner: anthonyray
- Created: 2014-11-29T15:53:28.000Z (over 11 years ago)
- Default Branch: master
- Last Pushed: 2015-01-09T17:21:11.000Z (over 11 years ago)
- Last Synced: 2024-04-15T09:15:23.623Z (about 2 years ago)
- Language: JavaScript
- Homepage:
- Size: 762 KB
- Stars: 16
- Watchers: 5
- Forks: 1
- Open Issues: 1
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# LittleBrain
A simple implementation of a multi-layer neural network using backpropagation algorithm in javascript.
See this library in action [here](http://reinette.io/littlebrain) !
## API
To instantiate a new neural network, just require the network class in the library.
```javascript
var neural = require('../lib/network')
var network = new neural.Network()
```
Next, you can add layers to your neural network thanks to the ```addLayer``` method.
This method takes two parameters :
- numNeurons : number of neurons to create for the given layer
- numInputs : optional, determines the number of input for each given neurons in the layer. If this argument is not specified, the number of input will be the number of neurons from the previous layer.
For instance :
```javascript
network.addLayer(10, 20) // Hidden layer, 10 neurons, 20 inputs
network.addLayer(2) // Output layer, 2 neurons
```
It is now time to train the neural network with training data. The training method uses the backpropagation algorithm. Careful ! this method can take time ...
Two stop conditions are implemented :
- The mean square error is below a threshold (errThreshold)
- We iterated over 100 000 times
```javascript
network.train([
// inputs outputs
[ zero, [0, 0] ],
[ one, [0, 1] ],
[ two, [1, 0] ],
[ three, [1, 1] ]
]);
```
Once the neural network is trained, you can pass it input data and get the output with the process method :
```javascript
var outputs = network.process(zero);
```
## Example
I made a website that uses this neural network to predict a drawn digit between 0 and 3. You can check it out [here](http://reinette.io/littlebrain) !
## Serialization
Instead of training the neural network everytime, I added a function to serialize/deserialize the neural network for later use.
```javascript
network.serialize();
// The deserialization needs to know how many inputs the neural network has. This is the first argument of the method.
network.deserialize(20,data);
```
## About
Feel free to contribute !