node-neural-network

node-neural-network

Node-neural-network is a javascript neural network library for node.js and the browser, its generalized algorithm is architecture-free, so you can build and train basically any type of first order or even second order neural network architectures. It's based on Synaptic.

This library includes a few built-in architectures like multilayer perceptrons, multilayer long-short term memory networks (LSTM), liquid state machines or Hopfield networks, and a trainer capable of training any given network, which includes built-in training tasks/tests like solving an XOR, completing a Distracted Sequence Recall task or an Embedded Reber Grammar test, so you can easily test and compare the performance of different architectures.

The algorithm implemented by this library has been taken from Derek D. Monner's paper:

A generalized LSTM-like training algorithm for second-order recurrent neural networks

There are references to the equations in that paper commented through the source code.

####Introduction

If you have no prior knowledge about Neural Networks, you should start by reading this guide.

####Demos

• Solve an XOR
• Discrete Sequence Recall Task
• Learn Image Filters
• Paint an Image
• Self Organizing Map
• Read from Wikipedia

The source code of these demos can be found in this branch.

####Getting started

• Neurons
• Layers
• Networks
• Trainer
• Architect

##Overview

###Installation

#####In node You can install lucasBertola/node-neural-network with npm:

npm install node-neural-network --save

#####In the browser Just include the file NodeNeuralNetwork.min.js from /dist directory with a script tag in your HTML:

<script src="NodeNeuralNetwork.min.js"></script>

###Usage

var NodeNeuralNetwork = require('node-neural-network'); // this line is not needed in the browser
var Neuron = NodeNeuralNetwork.Neuron,
	Layer = NodeNeuralNetwork.Layer,
	Network = NodeNeuralNetwork.Network,
	Trainer = NodeNeuralNetwork.Trainer,
	Architect = NodeNeuralNetwork.Architect;

Now you can start to create networks, train them, or use built-in networks from the Architect.

###Gulp Tasks

• gulp: runs all the tests and builds the minified and unminified bundles into /dist.
• gulp build: builds the bundle: /dist/NodeNeuralNetwork.js.
• gulp min: builds the minified bundle: /dist/NodeNeuralNetwork.min.js.
• gulp debug: builds the bundle /dist/NodeNeuralNetwork.js with sourcemaps.
• gulp dev: same as gulp debug, but watches the source files and rebuilds when any change is detected.
• gulp test: runs all the tests.

###Examples

#####Perceptron

This is how you can create a simple perceptron:

.

function Perceptron(input, hidden, output)
{
	// create the layers
	var inputLayer = new Layer(input);
	var hiddenLayer = new Layer(hidden);
	var outputLayer = new Layer(output);

	// connect the layers
	inputLayer.project(hiddenLayer);
	hiddenLayer.project(outputLayer);

	// set the layers
	this.set({
		input: inputLayer,
		hidden: [hiddenLayer],
		output: outputLayer
	});
}

// extend the prototype chain
Perceptron.prototype = new Network();
Perceptron.prototype.constructor = Perceptron;

Now you can test your new network by creating a trainer and teaching the perceptron to learn an XOR

var myPerceptron = new Perceptron(2,3,1);
var myTrainer = new Trainer(myPerceptron);

myTrainer.XOR(); // { error: 0.004998819355993572, iterations: 21871, time: 356 }

myPerceptron.activate([0,0]); // 0.0268581547421616
myPerceptron.activate([1,0]); // 0.9829673642853368
myPerceptron.activate([0,1]); // 0.9831714267395621
myPerceptron.activate([1,1]); // 0.02128894618097928

#####Long Short-Term Memory

This is how you can create a simple long short-term memory network with input gate, forget gate, output gate, and peephole connections:

function LSTM(input, blocks, output)
{
	// create the layers
	var inputLayer = new Layer(input);
	var inputGate = new Layer(blocks);
	var forgetGate = new Layer(blocks);
	var memoryCell = new Layer(blocks);
	var outputGate = new Layer(blocks);
	var outputLayer = new Layer(output);

	// connections from input layer
	var input = inputLayer.project(memoryCell);
	inputLayer.project(inputGate);
	inputLayer.project(forgetGate);
	inputLayer.project(outputGate);

	// connections from memory cell
	var output = memoryCell.project(outputLayer);

	// self-connection
	var self = memoryCell.project(memoryCell);

	// peepholes
	memoryCell.project(inputGate);
	memoryCell.project(forgetGate);
	memoryCell.project(outputGate);

	// gates
	inputGate.gate(input, Layer.gateType.INPUT);
	forgetGate.gate(self, Layer.gateType.ONE_TO_ONE);
	outputGate.gate(output, Layer.gateType.OUTPUT);

	// input to output direct connection
	inputLayer.project(outputLayer);

	// set the layers of the neural network
	this.set({
		input: inputLayer,
		hidden: [inputGate, forgetGate, memoryCell, outputGate],
		output: outputLayer
	});
}

// extend the prototype chain
LSTM.prototype = new Network();
LSTM.prototype.constructor = LSTM;

These are examples for explanatory purposes, the Architect already includes Multilayer Perceptrons and Multilayer LSTM network architectures.

##Contribute

node-neural-network is an Open Source project. Anybody in the world is welcome to contribute to the development of the project.

If you want to contribute feel free to send PR's, just make sure to run the default gulp task before submiting it. This way you'll run all the test specs and build the web distribution files.

<3