|
@@ -0,0 +1,52 @@
|
|
|
|
|
+<!DOCTYPE html>
|
|
|
|
|
+<html>
|
|
|
|
|
+
|
|
|
|
|
+<head>
|
|
|
|
|
+ <title>Brain JS Test</title>
|
|
|
|
|
+ <meta charset="utf-8" />
|
|
|
|
|
+ <meta http-equiv="Content-Type"
|
|
|
|
|
+ content="text/html; charset=utf-8" />
|
|
|
|
|
+ <style>
|
|
|
|
|
+ .quotes{
|
|
|
|
|
+ background:rgba(128, 128, 128, 0.3);
|
|
|
|
|
+ border-radius: 3px;
|
|
|
|
|
+ padding-left: 0.3em;
|
|
|
|
|
+ padding-right: 0.3em;
|
|
|
|
|
+ padding-top: 0.1em;
|
|
|
|
|
+ padding-bottom: 0.1em;
|
|
|
|
|
+ }
|
|
|
|
|
+ </style>
|
|
|
|
|
+</head>
|
|
|
|
|
+
|
|
|
|
|
+<body>
|
|
|
|
|
+ <h1>Brain JS Test</h1>
|
|
|
|
|
+ <p>
|
|
|
|
|
+ The JavaScript libray <span class="quotes">brain.js</span> is a machine learning program in Javascript.
|
|
|
|
|
+ </p>
|
|
|
|
|
+ <p>With the power of <span class="quotes">brain.js</span>,
|
|
|
|
|
+ we create the following examples to test the models in the browser.</p>
|
|
|
|
|
+
|
|
|
|
|
+ <h2>Neural Network</h2>
|
|
|
|
|
+ <p>
|
|
|
|
|
+ The <span class="quotes">Neural Network</span> is very simple in this libray.
|
|
|
|
|
+ We tested with two examples:
|
|
|
|
|
+ <ul>
|
|
|
|
|
+ <li><a href="brain-js.test-01.html">Basic example</a></li>
|
|
|
|
|
+ <li><a href="brain-js.test-04-classifier.html">Classify data</a></li>
|
|
|
|
|
+ </ul>
|
|
|
|
|
+ </p>
|
|
|
|
|
+
|
|
|
|
|
+ <h2>Recurrent Network</h2>
|
|
|
|
|
+ <p>
|
|
|
|
|
+ The brain.js support <span class="quotes">RNN</span>, <span class="quotes">LSTM</span> and <span class="quotes">GRU</span>. We noticed that the data format of these models are different to Neural netowrk. In recurrent network, the data must be array.
|
|
|
|
|
+
|
|
|
|
|
+ <ul>
|
|
|
|
|
+ <li><a href="brain-js.test-02-RNN.html">RNN</a></li>
|
|
|
|
|
+ <li><a href="brain-js.test-03-LSTM-math.html">LSTM</a></li>
|
|
|
|
|
+ </ul>
|
|
|
|
|
+ </p>
|
|
|
|
|
+</body>
|
|
|
|
|
+<script type="text/javascript">
|
|
|
|
|
+</script>
|
|
|
|
|
+
|
|
|
|
|
+</html>
|
