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

ptron

v1.2.2

Published

Javascript perceptron

Downloads

16

Readme

ptron.js

Javascript perceptron class and framework

Meta

This is a small, javascript only perceptron. A perceptron is basically a solver for a system of linear equations. The co-efficients of the equations can be determined automatically if we know which inputs map to which outputs through back-propogation training. Small perceptrons can be trained and run locally.

What use is it?

The solutions given are fuzzy but with diligent design and training they can be accurate enough. e.g. you could probably achieve 90% accuracy for a simple classification task

Models can be generated and dissemenated as JSON files. Models can also be trained in the wild as needed.

Multiple small models can be munged to perform more complex tasks e.g. multiple MLPs for each type of data, the results of which feed into another perceptron for a higher-level classification

How to use

import Ptron from 'ptron.js'


const mlp = new Ptron([3, 5, 2])
const inputs = [
  [0.1, 0.2, 0.3],
  [0.4, 0.5, 0.6],
  [0.7, 0.8, 0.9],
]
const targets = [
  [0, 1],
  [1, 0],
  [0, 1],
]

console.time('Training time')

mlp.loadModel('model.json')

mlp.train(inputs, targets, 0.1, 1000000)

const output = [
  mlp.predict(inputs[0]),
  mlp.predict(inputs[1]),
  mlp.predict(inputs[2]),
]

console.log('Expected:', targets)
console.log('Output:', output)

mlp.saveModel('model.json')

console.timeEnd('Training time')