junku901 / machine_learning Goto Github PK

Hi JoonKu,

Thank you for creating a great project! But it's sad to see not much update to the project anymore =(. I am a maintainer of https://github.com/machinelearnjs/machinelearnjs, and I propose we should merge these two projects, what do you think? Please let me know.

Cheers,
Jason

not classifier

my data is

x =[[0.4, 0.5, 0.5, 0., 0., 0.],
[0.5, 0.3, 0.5, 0., 0., 0.01],
[0.4, 0.8, 0.5, 0., 0.1, 0.2],
[1.4, 0.5, 0.5, 0., 0., 0.],
[1.5, 0.3, 0.5, 0., 0., 0.],
[0., 0.9, 1.5, 0., 0., 0.],
[0., 0.7, 1.5, 0., 0., 0.],
[0.5, 0.1, 0.9, 0., -1.8, 0.],
[0.8, 0.8, 0.5, 0., 0., 0.],
[0., 0.9, 0.5, 0.3, 0.5, 0.2],
[0., 0., 0.5, 0.4, 0.5, 0.],
[0., 0., 0.5, 0.5, 0.5, 0.],
[0.3, 0.6, 0.7, 1.7, 1.3, -0.7],
[0., 0., 0.5, 0.3, 0.5, 0.2],
[10., 10., 10.5, 10.4, 10.5, 10.1],
[10., 10., 10.5, 10.5, 10.5, 10.01],
[10.2, 10.01, 10.5, 10., 10., 10.9],
[10., 10., 10.5, 10.3, 0.5, -12.3],
[10., 10., 10.5, 10.4, 10.5, 14],
[10., 10., 10.5, 10.5, 10.5, -12],
[50, 40, 10, 22, 20, -10]
];

var y = [1,1,1,1,1,1,1,1,1,1,1,1,1,1,-1,-1,-1,-1,-1,-1,-1];

console.log("Predict : ",svm.predict([0.4, 0.5, 0.5, 0., 0., 0.]));

My data have one output only, when i set the output to one , a error found :

throw new Error('Matrix mismatch.');

Is it the issue of hidden layer? And how to solve it ?

Hi,

How do you save and then re-open a trained network?
It doesn't seem to be explained anywhere in the doc.

Thanks.

I'm still getting the un-updated version when doing npm install machine_learning.
Thanks

I installed via npm: npm install machine_learning

When I try to run Logistic Regression example with nodejs logis.js I'm getting this error:

/home/mertyildiran/Documents/npm/machine_learning/node_modules/machine_learning/lib/machine_learning.js:4
let ml = module.exports;
^^^

SyntaxError: Block-scoped declarations (let, const, function, class) not yet supported outside strict mode
    at exports.runInThisContext (vm.js:53:16)
    at Module._compile (module.js:374:25)
    at Object.Module._extensions..js (module.js:417:10)
    at Module.load (module.js:344:32)
    at Function.Module._load (module.js:301:12)
    at Module.require (module.js:354:17)
    at require (internal/module.js:12:17)
    at Object.<anonymous> (/home/mertyildiran/Documents/npm/machine_learning/logis.js:1:72)
    at Module._compile (module.js:410:26)
    at Object.Module._extensions..js (module.js:417:10)

Considering your machine_learning/examples/DecisionTree.js, whatever the input, teh output is always the same:

> console.log("Classify : ", dt.classify(['(direct)','USA','yes',5]));
Classify :  { None: 6, Basic: 5 }
undefined
> console.log("Classify : ", dt.classify(['slashdot','USA','yes',18]));
Classify :  { None: 6, Basic: 5 }
undefined
> console.log("Classify : ", dt.classify(['kiwitobes','France','yes',23]));
Classify :  { None: 6, Basic: 5 }
undefined
>
> console.log("Classify : ", dt.classify(['(direct)','USA','yes',5]));
Classify :  { None: 6, Basic: 5 }
undefined
> console.log("Classify : ", dt.classify(['(direct)','USA','yes',500]));
Classify :  { None: 6, Basic: 5 }

I see the example use SVM to classify points - two-category classification problem

May I know if the SVM algorithm could also handle classification for multi-category problem? Thanks.

For example,

x = [[0]];
y = [[0, 0]];

In the knn algorithm , the knn.predict method accept weightf argument , but i don't really know it's effect, if the result is string array, the algorithm can't work。
Another question is when characteristic value have different scope, it did't work right. It need a normalization function. But i am not sure that the weightf function can solve this or not.

Used your library under NodeJS and running under strict mode.
Encountered this error:
ReferenceError: mat_T is not defined

Added the var back and runs fine

I've never forgotten you when you write this code as a high school student in Seoul.

You got job offers from California
and some prominent tech companies from Korea when you were even a high schooler.

You had talked about your GitHub even though I did not know about the ABC of machine learning.

He passed away on 16 June 2018.
I miss you Joonku Kang so much.

Best regards,
Minku Kang

Is there a name for the cost function used in the hill-climbing example? I'm talking this:

var costf = function(vec) {
    var cost = 0;
    for(var i =0; i<14;i++) { // This example is using 15-dimensional input vector.
        cost += (0.5*i*vec[i]*Math.exp(-vec[i]+vec[i+1])/vec[i+1])
    }
    cost += (3.*vec[14]/vec[0]);
    return cost; // our goal is finding a vector which makes the cost value minimum.
};

I love the lib and THANK YOU VERY MUCHHHHHHHH!
I like the visualization result in your website, and how can I also do this effect ?