A flexible neural network library for Node.js and the browser. Check out a live demo of a movie recommendation engine built with Mind.
- Vectorized - uses a matrix implementation to process training data
- Configurable - allows you to customize the network topology
- Pluggable - download/upload minds that have already learned
$ yarn add node-mindconst Mind = require('node-mind');
/**
* Letters.
*
* - Imagine these # and . represent black and white pixels.
*/
const a = character(
'.#####.' +
'#.....#' +
'#.....#' +
'#######' +
'#.....#' +
'#.....#' +
'#.....#'
)
const b = character(
'######.' +
'#.....#' +
'#.....#' +
'######.' +
'#.....#' +
'#.....#' +
'######.'
)
const c = character(
'#######' +
'#......' +
'#......' +
'#......' +
'#......' +
'#......' +
'#######'
)
/**
* Learn the letters A through C.
*/
const mind = new Mind({ activator: 'sigmoid' })
.learn([
{ input: a, output: map('a') },
{ input: b, output: map('b') },
{ input: c, output: map('c') }
])
/**
* Predict the letter C, even with a pixel off.
*/
const result = mind.predict(character(
'#######' +
'#......' +
'#......' +
'#......' +
'#......' +
'##.....' +
'#######'
))
console.log(result) // ~ 0.5
/**
* Turn the # into 1s and . into 0s.
*/
function character(string) {
return string
.trim()
.split('')
.map(integer)
function integer(symbol) {
if ('#' === symbol) return 1
if ('.' === symbol) return 0
}
}
/**
* Map letter to a number.
*/
function map(letter) {
if (letter === 'a') return [ 0.1 ]
if (letter === 'b') return [ 0.3 ]
if (letter === 'c') return [ 0.5 ]
return 0
}Use plugins created by the Mind community to configure pre-trained networks that can go straight to making predictions.
Here's a cool example of the way you could use a hypothetical mind-ocr plugin:
const Mind = require('node-mind')
const ocr = require('mind-ocr')
const mind = Mind()
.upload(ocr)
.predict(
'.#####.' +
'#.....#' +
'#.....#' +
'#######' +
'#.....#' +
'#.....#' +
'#.....#'
)To create a plugin, simply call download on your trained mind:
const Mind = require('node-mind')
const mind = Mind()
.learn([
{ input: [0, 0], output: [ 0 ] },
{ input: [0, 1], output: [ 1 ] },
{ input: [1, 0], output: [ 1 ] },
{ input: [1, 1], output: [ 0 ] }
]);
const xor = mind.download()Here's a list of available plugins:
Create a new instance of Mind that can learn to make predictions.
The available options are:
activator: the activation function to use,sigmoidorhtanlearningRate: the speed at which the network will learnhiddenUnits: the number of units in the hidden layer/siterations: the number of iterations to runhiddenLayers: the number of hidden layers
Learn from training data:
mind.learn([
{ input: [0, 0], output: [ 0 ] },
{ input: [0, 1], output: [ 1 ] },
{ input: [1, 0], output: [ 1 ] },
{ input: [1, 1], output: [ 0 ] }
])Make a prediction:
mind.predict([0, 1])Download a mind:
const xor = mind.download()Upload a mind:
mind.upload(xor)Listen for the 'data' event, which is fired with each iteration:
mind.on('data', (iteration, errors, results) => {
// ...
})CircleCI will handle publishing to npm. To cut a new release, just do:
$ git changelog --tag <version>
$ vim package.json # enter <version>
$ git release <version>
Where <version> follows the semver spec.
If you're interested in learning more, I wrote a blog post on how to build your own neural network:
Also, here are some fantastic libraries you can check out:
stevenmiller888.github.io Β Β·Β GitHub @stevenmiller888 Β Β·Β Twitter @stevenmiller888