A neural network library built in JavaScript

This module can work on the browser, right? Please provide a built script somehere, either on a dist dir in master on a gh-pages branch. Thank you.

Tried to test-drive brain.js but couldn't make it link to the source: https://jsbin.com/yamivi/edit?html,js

can mind take inputs that vary from 0-1? (ex: 0.2, 0.3, 0.5, etc)

like this example from brain.js:

var net = new brain.NeuralNetwork();

net.train([{input: { r: 0.03, g: 0.7, b: 0.5 }, output: { black: 1 }}, {input: { r: 0.16, g: 0.09, b: 0.2 }, output: { white: 1 }}, {input: { r: 0.5, g: 0.5, b: 1.0 }, output: { white: 1 }}]);

var output = net.run({ r: 1, g: 0.4, b: 0 }); // { white: 0.99, black: 0.002 }

...i really like mind.js because of it's simplicity compared with brain.js...but i just couldn't get a proper output..thanks!

Problem: Using the Letters -demo code from Readme.md -- it does not give ~0.5 as expected, but ~1 most of the time.

[(http://codepen.io/mikkokam/pen/730368f3f615bc9930d695cc91b80491?editors=1010)]

Hi @stevenmiller888 !

Thanks a lot for making this public, amazing work and very helpful for beginners. I want to use the Mind in predicting the mood of a user based on keystrokes(moment of pressing, not the content).

As I will have lots of data for training, after training the Mind I would like to download it and use it anytime I need to make a new prediction. I tried to use download() and upload() functions. After downloading the Mind, where can I find it? How do I know what will be the parameter for the upload function?

I am new to nodejs and modules and so on.

Thank you!

Hi,

Is that somehow possible to learn your network several times?

From all the examples, it looks like you need to pass an array of {input, output} there. However, it would be cool to be able to learn your network several times. So it gets "smarter" and "smarter".

Are there any ways to perform that?

Regards,

If the network's weights were optionally namespaced, then a single mind instance could take multiple uploads.

For example:

var mind = Mind()
  .upload(letters, 'Letters')
  .upload(numbers, 'Numbers');

// Predict the letter 'B' from the network's existing knowledge of letters
var letterResult = mind.predict('Letters', character(
  '######.' +
  '#.....#' +
  '#.....#' +
  '######.' +
  '#.....#' +
  '#.....#' +
  '######.'
));

// Predict the number 4 from the network's existing knowledge of numbers
var numberResult = mind.predict('Numbers', character(
  '#.....#' +
  '#.....#' +
  '#.....#' +
  '#######' +
  '......#' +
  '......#' +
  '......#'
));

const Mind = require('node-mind'); const mind = new Mind().learn([ { input: [0, 0, 1], output: [0] }, { input: [0, 1, 1], output: [1] }, { input: [1, 0, 1], output: [1] }, { input: [1, 1, 1], output: [0] }, ]); const result = mind.predict([1, 0]); console.log(result);

Here's the response that I get: [ NaN ]

I guess it's better to have a working example in readme. I digged into one of the closed issue and found the answer.

https://github.com/stevenmiller888/mind/issues/19

Hi Steven,

excellent work, thanks.

I am refering to:

https://github.com/stevenmiller888/mind/blob/master/lib/index.js line 190: var changes = scalar(multiply(delta, results[0].result.transpose()), learningRate);

This is part of Mind.prototype.back = function(examples, results) { and concretely part of... // output > hidden

I did run your framework with two hidden layers and results do not match to what I get from other sources. I did a bit debugging and found that results[0].result.transpose() in line 190 is always referencing hidden layer 0, which I believe makes no sense in the // output > hidden section, when we have more than 1 hidden layer. However, it might be, that I got something wrong here. Would be nice, if you could have a look into that one.

My best guess was, that results[0].result.transpose() in line 190 needs to be replaced by results[hiddenLayers-1].result.transpose().

Best Regards, Jersio

Hello lovely humans,

eslint just published its new version 3.9.1.

This version is not covered by your current version range.

Without accepting this pull request your project will work just like it did before. There might be a bunch of new features, fixes and perf improvements that the maintainers worked on for you though.

I recommend you look into these changes and try to get onto the latest version of eslint. Given that you have a decent test suite, a passing build is a strong indicator that you can take advantage of these changes by merging the proposed change into your project. Otherwise this branch is a great starting point for you to work on the update.

Do you have any ideas how I could improve these pull requests? Did I report anything you think isn’t right? Are you unsure about how things are supposed to work?

There is a collection of frequently asked questions and while I’m just a bot, there is a group of people who are happy to teach me new things. Let them know.

Good luck with your project :sparkles:

You rock!

:palm_tree:

GitHub Release

• 2012258 Fix: incorrect indent check for array property access (fixes #7484) (#7485) (Teddy Katz)
• 8a71d4a Fix: no-useless-return false positive on conditionals (fixes #7477) (#7482) (Teddy Katz)
• 56a662b Fix: allow escaped backreferences in no-useless-escape (fixes #7472) (#7474) (Teddy Katz)
• fffdf13 Build: Fix prefer-reflect rule to not crash site gen build (#7471) (Ilya Volodin)
• 8ba68a3 Docs: Update broken link (#7490) (Devinsuit)
• 65231d8 Docs: add the "fixable" icon for no-useless-return (#7480) (Teddy Katz)

This pull request was created by greenkeeper.io.

_{Tired of seeing this sponsor message? :zap: greenkeeper upgrade}

Hello lovely humans,

png-img just published its new version 2.1.1.

This version is not covered by your current version range.

Without accepting this pull request your project will work just like it did before. There might be a bunch of new features, fixes and perf improvements that the maintainers worked on for you though.

I recommend you look into these changes and try to get onto the latest version of png-img. Given that you have a decent test suite, a passing build is a strong indicator that you can take advantage of these changes by merging the proposed change into your project. Otherwise this branch is a great starting point for you to work on the update.

Do you have any ideas how I could improve these pull requests? Did I report anything you think isn’t right? Are you unsure about how things are supposed to work?

There is a collection of frequently asked questions and while I’m just a bot, there is a group of people who are happy to teach me new things. Let them know.

Good luck with your project :sparkles:

You rock!

:palm_tree:

The new version differs by 37 commits .

• 393e7b7 2.1.1
• f2b7f05 Merge pull request #32 from gemini-testing/fix/crash.on.write
• 86214ca Fix Write method: keep object save from GC until job done
• 58c6aab PngImg: minor fixes
• 78f506a Merge pull request #31 from gemini-testing/legal
• a71cb83 Update legal information
• 67e8230 2.1.0
• 864db14 Forgotten tests for rotate
• 4b75529 Merge pull request #28 from gemini-testing/feature/rotate
• 5462e0a Rotate methods
• e6a852b Merge pull request #27 from gemini-testing/tests.refactoring
• d1ef62b Refactoring:
• 79290a1 2.0.0
• 5adc579 Merge pull request #26 from gemini-testing/feature/insert
• 3f81157 var -> const

There are 37 commits in total. See the full diff.

This pull request was created by greenkeeper.io.

_{Tired of seeing this sponsor message? :zap: greenkeeper upgrade}

Hi Steven, I don't know where else to ask so I'm asking here--

I'm following your useful XOR network tutorial and I'm confused by this step:

Once we get the delta hidden sum, we calculate the change in weights between the input and hidden layer by dividing it with the input data, (1, 1).

What if the input is (1, 0) or (0, 0)? We would be dividing by zero. How should I handle this case?

Later in part 2 you write

Since we’re dealing with matrices, we handle the division by multiplying the delta output sum with the hidden results matrices’ transpose.

But then you're just multiplying the results! No division happens at all. What's going on?

I want to try the dome in README file but found 'character is not defined' in the statement, where is the method character from? const a = character( '.#####.' + '#.....#' + '#.....#' + '#######' + '#.....#' + '#.....#' + '#.....#' )

For example, provided trainings for letters A, B and C, once we are predicting the results providing image A, it would be great if we could have outputs results as an object looking like: { A: 0.99, // this is the correct answer because it has the highest number. B: 0.01, C: 0.00 }

At the moment this is not possible, the predict function only returns one value, so it's very limited with what you can do.

I've tested several times on your provided example:

let train_data = [
    { input: a, output: map('a') },
    { input: b, output: map('b')},
    { input: c, output: map('c')}
]

mind.learn(train_data)
console.log('From mind: ', mind.predict(character(
    '#######' +
    '#......' +
    '#......' +
    '#......' +
    '#......' +
    '##.....' +
    '#######'
  )))

And each time, I got different results ranging from 0.6 ~ 0.9, which were expected to be 0.5. Here are several of them:

1. From mind:  [ 0.8690720414762252 ]
 2. From mind:  [ 0.9931120996113908 ]
 3. From mind:  [ 0.6954245636611965 ]
 4. From mind:  [ 0.9677281776279311 ]
 5. From mind:  [ -0.2278222080355501 ]
 6. From mind:  [ 0.9054097880591 ]

Was there anything wrong?

Hi,

My first steps in deep learning don't go so well. I keep getting NaN. That turned out to be a "lucky" coincidence.

See this full example:

const Mind = require('node-mind');

var asciiToBin = (function () {
    var pad = '00000000';

    return function (str) {
        return str.replace(/./g, function (c) {
            var bin = c.charCodeAt(0).toString(2);
            return pad.substring(bin.length) + bin;
        });
    };
}());

var binToAscii = function (bin) {
    return bin.replace(/[01]{8}/g, function (v) {
        return String.fromCharCode(parseInt(v, 2));
    });
};

function binArray(data) {
  return Array.from(asciiToBin(data)).map(Number);
}

const mind = new Mind()
.learn([
  { input: binArray("the2"), output: [1] },
  { input: binArray("the"), output: [1] }
]);

const result = mind.predict(binArray("the"));

console.log(result);

That returns NaN. Now if i merely swap the learn inputs around to this:

  { input: binArray("the"), output: [1] },
  { input: binArray("the2"), output: [1] }

Then it magically starts working :)

This is not the only ones where it produces NaN. It does so in the following cases as well (only changing the inputs, not the predict):

  { input: binArray("the "), output: [1] },
  { input: binArray("the "), output: [1] }

Here it seems like the predict has to be at least as long as the shortest input.

  { input: binArray("one"), output: [1] },
  { input: binArray("two"), output: [1] },
  { input: binArray("a"), output: [1] },

Also gives NaN. Puttin "a" on top makes it work (in this case).

This might be a bug, and one that seems rather easy to get? Or i'm doing something else extremely wrong, in which case i'd also love to hear that!

p.s. if one knows a more efficient way to convert a string to a binary array. Or if there is a more elegant way of thing this in this library, please do tell :)

Cheers, Mark