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

proxima-js

v1.0.0

Published

Proxima is a multilayered fully connected neural network micro library.

Downloads

7

Readme

Proxima

Proxima is a fully connected neural network micro library written in javascript for browsers and nodejs.

Support Proxima development by donating or becoming a sponsor.
Donate Donate

Installation

npm install proxima --save

Usage

var Proxima = require('../proxima') // only for nodejs

var xor_training_data = [
    {inputs: [0, 1], targets: [1]},
    {inputs: [1, 0], targets: [1]},
    {inputs: [0, 0], targets: [0]},
    {inputs: [1, 1], targets: [0]}
]

var hyperParameters = {
    neural_network: [2,3,1],
    learning_rate: 0.5,
    max_iterations: 15000,
    cost_threshold: 0.005,
    log_after_x_iterations: 0,
}

var p = new Proxima(hyperParameters)
p.train(xor_training_data)
console.log(p.predict([0,1]))
console.log(p.predict([1,0]))
console.log(p.predict([0,0]))
console.log(p.predict([1,1]))

The above program will print something like this to the console

training: 32.45ms error: 0.004967480795865376 iterations: 1301
training: 37.64ms
[ 0.9003734502498547 ]
[ 0.9000429398063956 ]
[ 0.09926572660491863 ]
[ 0.09967427748286291 ]

Configuration options

var hyperParameters = {
    neural_network: [2,3,1],    // 3 layered neural network with 1 input layer with 2 nodes, 1 hidden layer with 3 nodes and 1 output layer with 1 node
    learning_rate: 0.5,         // η Defaults to 0.5
    max_iterations: 15000,      // Maximum training iterations if the cost_threshold in not reached
    cost_threshold: 0.005,      // Stops training when the result of the cost/loss function is less, defaults to 0.05  
    log_after_x_iterations: 0,
}

What's behind Proxima

Activation functions

  • Sigmoid (default)
  • Tanh (todo)
  • ReLu (todo)
  • Leaky ReLu (todo)
  • Swish (todo)

Cost functions

  • Squared Error (default)
  • Mean Squared Error (todo)
  • Root Mean Square (todo)
  • The Sum of Square Errors (todo)

Gradient descent methods

  • Stochastic gradient descent (default)
  • Mini-batch gradient descent (todo)
  • Batch gradient descent (todo)

Gradient descent optimization algorithms

  • Regular gradient descent (default)
  • Momentum based gradient descent (todo)
  • Implement other gradient descent optimization algorithms (todo)