npm package discovery and stats viewer.

Discover Tips

  • General search

    [free text search, go nuts!]

  • Package details

    pkg:[package-name]

  • User packages

    @[username]

Sponsor

Optimize Toolset

I’ve always been into building performant and accessible sites, but lately I’ve been taking it extremely seriously. So much so that I’ve been building a tool to help me optimize and monitor the sites that I build to make sure that I’m making an attempt to offer the best experience to those who visit them. If you’re into performant, accessible and SEO friendly sites, you might like it too! You can check it out at Optimize Toolset.

About

Hi, 👋, I’m Ryan Hefner  and I built this site for me, and you! The goal of this site was to provide an easy way for me to check the stats on my npm packages, both for prioritizing issues and updates, and to give me a little kick in the pants to keep up on stuff.

As I was building it, I realized that I was actually using the tool to build the tool, and figured I might as well put this out there and hopefully others will find it to be a fast and useful way to search and browse npm packages as I have.

If you’re interested in other things I’m working on, follow me on Twitter or check out the open source projects I’ve been publishing on GitHub.

I am also working on a Twitter bot for this site to tweet the most popular, newest, random packages from npm. Please follow that account now and it will start sending out packages soon–ish.

Open Software & Tools

This site wouldn’t be possible without the immense generosity and tireless efforts from the people who make contributions to the world and share their work via open source initiatives. Thank you 🙏

© 2024 – Pkg Stats / Ryan Hefner

mlp

v1.1.0

Published

multilayer perceptron which can be trained using the backpropagation algorithm

Downloads

13

Readme

mlp

implementation of a multilayer perceptron which can be trained using the backpropagation algorithm

installation

npm install mlp

Using browserify, mlp can be used in a browser as well.

how to use

initialize a new perceptron

// create the perceptron
var MLP = require('mlp');
var mlp = new MLP(2,3);

// add hidden layers and initialize
mlp.addHiddenLayer(5);
mlp.addHiddenLayer(5);
mlp.init();

The amount and dimensions of the hidden layers has to correspond with the problem, you want to solve (think about overfitting)...

train the perceptron

// create a training set
mlp.addToTrainingSet([2, 1], [1, 0, 0]);
mlp.addToTrainingSet([0, 1], [1, 0, 0]);
mlp.addToTrainingSet([3, 4], [0, 1, 0]);
mlp.addToTrainingSet([2, 3], [0, 1, 0]);
mlp.addToTrainingSet([1, 0], [0, 0, 1]);
mlp.addToTrainingSet([3, 1], [0, 0, 1]);

// train the perceptron
var learnRate = 0.5;
var error = Number.MAX_VALUE;
while (error > 0.01) {
	error = mlp.train(learnRate);
}

Depending on the training set, the learn rate and the structure of the perceptron, this step may take a while. If necessary, you can add additional exit conditions to the loop (e.g. a maximum number of iterations).

If you want to restart the training, you have to clear the training set and to reset the weights:

mlp.clearTrainingSet();
mlp.resetWeights();

classify element

var elementToClassify = [1, 1];
var classification = mlp.classify(elementToClassify);

The vector classification contains in each component the probability that the element belongs to the associated class.

export and import of mlp data

After training the perceptron, you can export the weights to save them for later use:

var data = mlp.exportToJson();

The export is a simple JSON object that can be imported again as follows:

mlp.setWeights(data);

Changelog

1.1.0 / 2016-06-30

Add methods exportToJson and setWeights to export and import a perceptron.

License

Copyright (c) 2015-2016 Ulf Biallas. Licensed under the [MIT license][MIT]. [MIT]: https://github.com/ulfbiallas/npm-mlp/blob/master/LICENSE