wink-perceptron

Multi-class averaged perceptron

$3

Wink Perceptron is a fast and effective way to learn linearly separable patterns from either dense or sparse data. Its averaging function results in better generalization compared to the vanilla implementation of perceptron.

$3

Use npm to install:

npm install wink-perceptron --save

$3

Here is an example of predicting type of iris plant from the Iris Data Set.

``javascript
// Load training data — the Iris Data Set obtained from
// UCI Machine Learning Repository; it has been converted
// into JSON format.
// You may need to update the path in the "require" statement
// according to your working directory.
const trainingExamples = require( 'wink-perceptron/sample-data/iris-train.json' );
// Initialize a test data sample.
const testData = {
setosa: { sepalLength: 4.9, sepalWidth: 3, petalLength: 1.4, petalWidth: 0.2 },
versicolor: { sepalLength: 6.4, sepalWidth: 3.2, petalLength: 4.5, petalWidth: 1.5 },
virginica: { sepalLength: 7.2, sepalWidth: 3.6, petalLength: 6.1, petalWidth: 2.5 }
};

// Load wink perceptron.
var winkPerceptron = require( 'wink-perceptron' );
// Instantiate wink perceptron.
var perceptron = winkPerceptron();
// Define configurtaion.
perceptron.defineConfig( { shuffleData: true, maxIterations: 21 } );
// Learn from training data.
perceptron.learn( trainingExamples );

// Attempt prediction for each iris plant type.
console.log( perceptron.predict( testData.setosa ) );
// -> Iris-setosa
console.log( perceptron.predict( testData.versicolor ) );
// -> Iris-versicolor
console.log( perceptron.predict( testData.virginica ) );
// -> Iris-virginica
``
Try experimenting with this example on Runkit in the browser.

$3

Check out the perceptron API documentation to learn more.

$3

If you spot a bug and the same has not yet been reported, raise a new issue or consider fixing it and sending a pull request.

$3

Wink is a family of open source packages for Statistical Analysis, Natural Language Processing and Machine Learning in NodeJS. The code is thoroughly documented for easy human comprehension and has a test coverage of ~100% for reliability to build production grade solutions.

$3

wink-perceptron is copyright 2017-18 GRAYPE Systems Private Limited.

It is licensed under the terms of the MIT License.