259 lines
13 KiB
HTML
259 lines
13 KiB
HTML
<!--
|
||
Automatically generated HTML file from DocOnce source
|
||
(https://github.com/hplgit/doconce/)
|
||
-->
|
||
<html>
|
||
<head>
|
||
<meta http-equiv="Content-Type" content="text/html; charset=utf-8" />
|
||
<meta name="generator" content="DocOnce: https://github.com/hplgit/doconce/" />
|
||
<meta name="viewport" content="width=device-width, initial-scale=1.0" />
|
||
<meta name="description" content="Week 42 Convolutional (CNN) and Recurrent (RNN) Neural Networks">
|
||
|
||
<title>Week 42 Convolutional (CNN) and Recurrent (RNN) Neural Networks</title>
|
||
|
||
<!-- Bootstrap style: bootstrap -->
|
||
<link href="https://netdna.bootstrapcdn.com/bootstrap/3.1.1/css/bootstrap.min.css" rel="stylesheet">
|
||
<!-- not necessary
|
||
<link href="https://netdna.bootstrapcdn.com/font-awesome/4.0.3/css/font-awesome.css" rel="stylesheet">
|
||
-->
|
||
|
||
<style type="text/css">
|
||
|
||
/* Add scrollbar to dropdown menus in bootstrap navigation bar */
|
||
.dropdown-menu {
|
||
height: auto;
|
||
max-height: 400px;
|
||
overflow-x: hidden;
|
||
}
|
||
|
||
/* Adds an invisible element before each target to offset for the navigation
|
||
bar */
|
||
.anchor::before {
|
||
content:"";
|
||
display:block;
|
||
height:50px; /* fixed header height for style bootstrap */
|
||
margin:-50px 0 0; /* negative fixed header height */
|
||
}
|
||
</style>
|
||
|
||
|
||
</head>
|
||
|
||
<!-- tocinfo
|
||
{'highest level': 2,
|
||
'sections': [('Plan for week 42', 2, None, '___sec0'),
|
||
('Convolutional Neural Networks (recognizing images)',
|
||
2,
|
||
None,
|
||
'___sec1'),
|
||
('Neural Networks vs CNNs', 2, None, '___sec2'),
|
||
('Why CNNS for images, sound files, medical images from CT scans '
|
||
'etc?',
|
||
2,
|
||
None,
|
||
'___sec3'),
|
||
('Regular NNs don’t scale well to full images',
|
||
2,
|
||
None,
|
||
'___sec4'),
|
||
('3D volumes of neurons', 2, None, '___sec5'),
|
||
('Layers used to build CNNs', 2, None, '___sec6'),
|
||
('Transforming images', 2, None, '___sec7'),
|
||
('CNNs in brief', 2, None, '___sec8'),
|
||
('CNNs in more detail, building convolutional neural networks in '
|
||
'Tensorflow and Keras',
|
||
2,
|
||
None,
|
||
'___sec9'),
|
||
('Setting it up', 2, None, '___sec10'),
|
||
('The MNIST dataset again', 2, None, '___sec11'),
|
||
('Strong correlations', 2, None, '___sec12'),
|
||
('Layers of a CNN', 2, None, '___sec13'),
|
||
('Systematic reduction', 2, None, '___sec14'),
|
||
('Prerequisites: Collect and pre-process data',
|
||
2,
|
||
None,
|
||
'___sec15'),
|
||
('Importing Keras and Tensorflow', 2, None, '___sec16'),
|
||
('Running with Keras', 2, None, '___sec17'),
|
||
('Final part', 2, None, '___sec18'),
|
||
('Final visualization', 2, None, '___sec19'),
|
||
('The CIFAR01 data set', 2, None, '___sec20'),
|
||
('Verifying the data set', 2, None, '___sec21'),
|
||
('Set up the model', 2, None, '___sec22'),
|
||
('Add Dense layers on top', 2, None, '___sec23'),
|
||
('Compile and train the model', 2, None, '___sec24'),
|
||
('Finally, evaluate the model', 2, None, '___sec25'),
|
||
('Recurrent neural networks: Overarching view',
|
||
2,
|
||
None,
|
||
'___sec26'),
|
||
('Set up of an RNN', 2, None, '___sec27'),
|
||
('A simple example', 2, None, '___sec28'),
|
||
('An extrapolation example', 2, None, '___sec29'),
|
||
('Formatting the Data', 2, None, '___sec30'),
|
||
('Predicting New Points With A Trained Recurrent Neural Network',
|
||
2,
|
||
None,
|
||
'___sec31'),
|
||
('Other Things to Try', 2, None, '___sec32'),
|
||
('Other Types of Recurrent Neural Networks',
|
||
2,
|
||
None,
|
||
'___sec33')]}
|
||
end of tocinfo -->
|
||
|
||
<body>
|
||
|
||
|
||
|
||
<script type="text/x-mathjax-config">
|
||
MathJax.Hub.Config({
|
||
TeX: {
|
||
equationNumbers: { autoNumber: "none" },
|
||
extensions: ["AMSmath.js", "AMSsymbols.js", "autobold.js", "color.js"]
|
||
}
|
||
});
|
||
</script>
|
||
<script type="text/javascript" async
|
||
src="https://cdnjs.cloudflare.com/ajax/libs/mathjax/2.7.1/MathJax.js?config=TeX-AMS-MML_HTMLorMML">
|
||
</script>
|
||
|
||
|
||
|
||
|
||
<!-- Bootstrap navigation bar -->
|
||
<div class="navbar navbar-default navbar-fixed-top">
|
||
<div class="navbar-header">
|
||
<button type="button" class="navbar-toggle" data-toggle="collapse" data-target=".navbar-responsive-collapse">
|
||
<span class="icon-bar"></span>
|
||
<span class="icon-bar"></span>
|
||
<span class="icon-bar"></span>
|
||
</button>
|
||
<a class="navbar-brand" href="week42-bs.html">Week 42 Convolutional (CNN) and Recurrent (RNN) Neural Networks</a>
|
||
</div>
|
||
|
||
<div class="navbar-collapse collapse navbar-responsive-collapse">
|
||
<ul class="nav navbar-nav navbar-right">
|
||
<li class="dropdown">
|
||
<a href="#" class="dropdown-toggle" data-toggle="dropdown">Contents <b class="caret"></b></a>
|
||
<ul class="dropdown-menu">
|
||
<!-- navigation toc: --> <li><a href="._week42-bs001.html#___sec0" style="font-size: 80%;">Plan for week 42</a></li>
|
||
<!-- navigation toc: --> <li><a href="._week42-bs002.html#___sec1" style="font-size: 80%;">Convolutional Neural Networks (recognizing images)</a></li>
|
||
<!-- navigation toc: --> <li><a href="._week42-bs003.html#___sec2" style="font-size: 80%;">Neural Networks vs CNNs</a></li>
|
||
<!-- navigation toc: --> <li><a href="._week42-bs004.html#___sec3" style="font-size: 80%;">Why CNNS for images, sound files, medical images from CT scans etc?</a></li>
|
||
<!-- navigation toc: --> <li><a href="._week42-bs005.html#___sec4" style="font-size: 80%;">Regular NNs don’t scale well to full images</a></li>
|
||
<!-- navigation toc: --> <li><a href="._week42-bs006.html#___sec5" style="font-size: 80%;">3D volumes of neurons</a></li>
|
||
<!-- navigation toc: --> <li><a href="#___sec6" style="font-size: 80%;">Layers used to build CNNs</a></li>
|
||
<!-- navigation toc: --> <li><a href="._week42-bs008.html#___sec7" style="font-size: 80%;">Transforming images</a></li>
|
||
<!-- navigation toc: --> <li><a href="._week42-bs009.html#___sec8" style="font-size: 80%;">CNNs in brief</a></li>
|
||
<!-- navigation toc: --> <li><a href="._week42-bs010.html#___sec9" style="font-size: 80%;">CNNs in more detail, building convolutional neural networks in Tensorflow and Keras</a></li>
|
||
<!-- navigation toc: --> <li><a href="._week42-bs011.html#___sec10" style="font-size: 80%;">Setting it up</a></li>
|
||
<!-- navigation toc: --> <li><a href="._week42-bs012.html#___sec11" style="font-size: 80%;">The MNIST dataset again</a></li>
|
||
<!-- navigation toc: --> <li><a href="._week42-bs013.html#___sec12" style="font-size: 80%;">Strong correlations</a></li>
|
||
<!-- navigation toc: --> <li><a href="._week42-bs014.html#___sec13" style="font-size: 80%;">Layers of a CNN</a></li>
|
||
<!-- navigation toc: --> <li><a href="._week42-bs015.html#___sec14" style="font-size: 80%;">Systematic reduction</a></li>
|
||
<!-- navigation toc: --> <li><a href="._week42-bs016.html#___sec15" style="font-size: 80%;">Prerequisites: Collect and pre-process data</a></li>
|
||
<!-- navigation toc: --> <li><a href="._week42-bs017.html#___sec16" style="font-size: 80%;">Importing Keras and Tensorflow</a></li>
|
||
<!-- navigation toc: --> <li><a href="._week42-bs018.html#___sec17" style="font-size: 80%;">Running with Keras</a></li>
|
||
<!-- navigation toc: --> <li><a href="._week42-bs019.html#___sec18" style="font-size: 80%;">Final part</a></li>
|
||
<!-- navigation toc: --> <li><a href="._week42-bs020.html#___sec19" style="font-size: 80%;">Final visualization</a></li>
|
||
<!-- navigation toc: --> <li><a href="._week42-bs021.html#___sec20" style="font-size: 80%;">The CIFAR01 data set</a></li>
|
||
<!-- navigation toc: --> <li><a href="._week42-bs022.html#___sec21" style="font-size: 80%;">Verifying the data set</a></li>
|
||
<!-- navigation toc: --> <li><a href="._week42-bs023.html#___sec22" style="font-size: 80%;">Set up the model</a></li>
|
||
<!-- navigation toc: --> <li><a href="._week42-bs024.html#___sec23" style="font-size: 80%;">Add Dense layers on top</a></li>
|
||
<!-- navigation toc: --> <li><a href="._week42-bs025.html#___sec24" style="font-size: 80%;">Compile and train the model</a></li>
|
||
<!-- navigation toc: --> <li><a href="._week42-bs026.html#___sec25" style="font-size: 80%;">Finally, evaluate the model</a></li>
|
||
<!-- navigation toc: --> <li><a href="._week42-bs027.html#___sec26" style="font-size: 80%;">Recurrent neural networks: Overarching view</a></li>
|
||
<!-- navigation toc: --> <li><a href="._week42-bs028.html#___sec27" style="font-size: 80%;">Set up of an RNN</a></li>
|
||
<!-- navigation toc: --> <li><a href="._week42-bs029.html#___sec28" style="font-size: 80%;">A simple example</a></li>
|
||
<!-- navigation toc: --> <li><a href="._week42-bs030.html#___sec29" style="font-size: 80%;">An extrapolation example</a></li>
|
||
<!-- navigation toc: --> <li><a href="._week42-bs031.html#___sec30" style="font-size: 80%;">Formatting the Data</a></li>
|
||
<!-- navigation toc: --> <li><a href="._week42-bs032.html#___sec31" style="font-size: 80%;">Predicting New Points With A Trained Recurrent Neural Network</a></li>
|
||
<!-- navigation toc: --> <li><a href="._week42-bs033.html#___sec32" style="font-size: 80%;">Other Things to Try</a></li>
|
||
<!-- navigation toc: --> <li><a href="._week42-bs034.html#___sec33" style="font-size: 80%;">Other Types of Recurrent Neural Networks</a></li>
|
||
|
||
</ul>
|
||
</li>
|
||
</ul>
|
||
</div>
|
||
</div>
|
||
</div> <!-- end of navigation bar -->
|
||
|
||
<div class="container">
|
||
|
||
<p> </p><p> </p><p> </p> <!-- add vertical space -->
|
||
|
||
<a name="part0007"></a>
|
||
<!-- !split -->
|
||
|
||
<h2 id="___sec6" class="anchor">Layers used to build CNNs </h2>
|
||
|
||
<p>
|
||
A simple CNN is a sequence of layers, and every layer of a CNN
|
||
transforms one volume of activations to another through a
|
||
differentiable function. We use three main types of layers to build
|
||
CNN architectures: Convolutional Layer, Pooling Layer, and
|
||
Fully-Connected Layer (exactly as seen in regular Neural Networks). We
|
||
will stack these layers to form a full CNN architecture.
|
||
|
||
<p>
|
||
A simple CNN for image classification could have the architecture:
|
||
|
||
<ul>
|
||
<li> <b>INPUT</b> (\( 32\times 32 \times 3 \)) will hold the raw pixel values of the image, in this case an image of width 32, height 32, and with three color channels R,G,B.</li>
|
||
<li> <b>CONV</b> (convolutional )layer will compute the output of neurons that are connected to local regions in the input, each computing a dot product between their weights and a small region they are connected to in the input volume. This may result in volume such as \( [32\times 32\times 12] \) if we decided to use 12 filters.</li>
|
||
<li> <b>RELU</b> layer will apply an elementwise activation function, such as the \( max(0,x) \) thresholding at zero. This leaves the size of the volume unchanged (\( [32\times 32\times 12] \)).</li>
|
||
<li> <b>POOL</b> (pooling) layer will perform a downsampling operation along the spatial dimensions (width, height), resulting in volume such as \( [16\times 16\times 12] \).</li>
|
||
<li> <b>FC</b> (i.e. fully-connected) layer will compute the class scores, resulting in volume of size \( [1\times 1\times 10] \), where each of the 10 numbers correspond to a class score, such as among the 10 categories of the MNIST images we considered above . As with ordinary Neural Networks and as the name implies, each neuron in this layer will be connected to all the numbers in the previous volume.</li>
|
||
</ul>
|
||
|
||
<p>
|
||
<!-- navigation buttons at the bottom of the page -->
|
||
<ul class="pagination">
|
||
<li><a href="._week42-bs006.html">«</a></li>
|
||
<li><a href="._week42-bs000.html">1</a></li>
|
||
<li><a href="._week42-bs001.html">2</a></li>
|
||
<li><a href="._week42-bs002.html">3</a></li>
|
||
<li><a href="._week42-bs003.html">4</a></li>
|
||
<li><a href="._week42-bs004.html">5</a></li>
|
||
<li><a href="._week42-bs005.html">6</a></li>
|
||
<li><a href="._week42-bs006.html">7</a></li>
|
||
<li class="active"><a href="._week42-bs007.html">8</a></li>
|
||
<li><a href="._week42-bs008.html">9</a></li>
|
||
<li><a href="._week42-bs009.html">10</a></li>
|
||
<li><a href="._week42-bs010.html">11</a></li>
|
||
<li><a href="._week42-bs011.html">12</a></li>
|
||
<li><a href="._week42-bs012.html">13</a></li>
|
||
<li><a href="._week42-bs013.html">14</a></li>
|
||
<li><a href="._week42-bs014.html">15</a></li>
|
||
<li><a href="._week42-bs015.html">16</a></li>
|
||
<li><a href="._week42-bs016.html">17</a></li>
|
||
<li><a href="">...</a></li>
|
||
<li><a href="._week42-bs034.html">35</a></li>
|
||
<li><a href="._week42-bs008.html">»</a></li>
|
||
</ul>
|
||
<!-- ------------------- end of main content --------------- -->
|
||
|
||
</div> <!-- end container -->
|
||
<!-- include javascript, jQuery *first* -->
|
||
<script src="https://ajax.googleapis.com/ajax/libs/jquery/1.10.2/jquery.min.js"></script>
|
||
<script src="https://netdna.bootstrapcdn.com/bootstrap/3.0.0/js/bootstrap.min.js"></script>
|
||
|
||
<!-- Bootstrap footer
|
||
<footer>
|
||
<a href="http://..."><img width="250" align=right src="http://..."></a>
|
||
</footer>
|
||
-->
|
||
|
||
|
||
<center style="font-size:80%">
|
||
<!-- copyright only on the titlepage -->
|
||
</center>
|
||
|
||
|
||
</body>
|
||
</html>
|
||
|
||
|