Tuesday, July 11, 2017

Encog-Node: Simple Machine Learning on Node.js

Before I got into serious Machine Learning and Computer Vision coding (which I mostly use Python for), I did a lot of my development on Node.js. Few years back (around 2012), I was trying to add a simple neural network to one of my Node.js applications. I looked around, but couldn't find a satisfactory node module which was lightweight and flexible. Around that time, I came across the Encog Machine Learning framework, which was created by Jeff Heaton, and was one of the most popular Machine Learning libraries for Java at the time. I noticed that there was a Javascript version of the Encog library, which worked surprisingly well, and set myself on to porting that to Node.js.

I released the first version of Encog-Node in early 2012, and the latest version v0.3.0 is now available from NPM - https://www.npmjs.com/package/encog-node, and is recommended for anyone who wants to add lightweight, simple machine learning capabilities to their Node.js applications.

GitHub user Rui Cardoso contributed a lot for the latest release, with restructuring and cleaning up the codebase, and adding more examples.

You can install it by simply running,
 npm install encog-node  
in your node application.


Here's an example code to get a simplest neural network working on Node.js
 var ENCOG = require('encog-node');  
    
 var XOR_INPUT = [  
   [0, 0],  
   [1, 0],  
   [0, 1],  
   [1, 1]  
 ];  
    
 var XOR_IDEAL = [  
   [0],  
   [1],  
   [1],  
   [0]  
 ];  
    
 var network = ENCOG.networks.basic.create([  
   ENCOG.layers.basic.create(ENCOG.activationFunctions.sigmoid.create(), 2, 1),  
   ENCOG.layers.basic.create(ENCOG.activationFunctions.sigmoid.create(), 3, 1),  
   ENCOG.layers.basic.create(ENCOG.activationFunctions.sigmoid.create(), 1, 0)  
 ]);  
    
 network.randomize();  
    
 var train = ENCOG.trainers.propagation.create(network, ENCOG.errorFunctions.linear.create(), XOR_INPUT, XOR_IDEAL, "RPROP", 0, 0);  
    
 var iteration = 1;  
    
 do {  
   train.iteration();  
   var trainResultString = "Training Iteration #" + iteration + ", Error: " + train.error;  
   console.log(trainResultString + "\n");  
   iteration++;  
 } while (iteration < 1000 && train.error > 0.01);  
    
 var input = [0, 0];  
 var output = [];  
    
 console.log("Testing neural network: \n");  
    
 for (var i = 0; i < XOR_INPUT.length; i++) {  
   output = network.compute(XOR_INPUT[i]);  
   var testResultString = "Input: " + String(XOR_INPUT[i][0]) +  
     " ; " + String(XOR_INPUT[i][1]) +  
     "  Output: " + String(output[0]) +  
     "  Ideal: " + String(XOR_IDEAL[i][0]);  
   console.log(testResultString + "\n");  
 }  

Which will output,
 >node index.js  
 Training Iteration #1, Error: 0.33306242864283925  
 Training Iteration #2, Error: 0.30684930995968274  
 Training Iteration #3, Error: 0.2816136873215376  
 Training Iteration #4, Error: 0.2614275886340755  
 ..........  
 ..........  
 ..........  
 Training Iteration #44, Error: 0.010807377445510056  
 Training Iteration #45, Error: 0.005187735146628829  
 Testing neural network  
 Input: 0 ; 0  Output: 0.000056493461985276595  Ideal: 0  
 Input: 1 ; 0  Output: 0.9995493238264583  Ideal: 1  
 Input: 0 ; 1  Output: 0.9987763730629743  Ideal: 1  
 Input: 1 ; 1  Output: 0.08974271940228784  Ideal: 0  

More examples and instructions available at the NPM Page of the Encog-Node package.
And, you can get the source code from the GitHub page.

Feel free to use, test, improve, and contribute to the code.

Related links:





Build Deeper: The Path to Deep Learning

Learn the bleeding edge of AI in the most practical way: By getting hands-on with Python, TensorFlow, Keras, and OpenCV. Go a little deeper...

Get your copy now!

No comments:

Post a Comment