Morten Hjorth-Jensen
552 lines
39 KiB
HTML
552 lines
39 KiB
HTML
<!--
|
||
HTML file automatically generated from DocOnce source
|
||
(https://github.com/doconce/doconce/)
|
||
doconce format html week45.do.txt --html_style=bootstrap --pygments_html_style=default --html_admon=bootstrap_panel --html_output=week45-bs --no_mako
|
||
-->
|
||
<html>
|
||
<head>
|
||
<meta http-equiv="Content-Type" content="text/html; charset=utf-8" />
|
||
<meta name="generator" content="DocOnce: https://github.com/doconce/doconce/" />
|
||
<meta name="viewport" content="width=device-width, initial-scale=1.0" />
|
||
<meta name="description" content="Week 45, Convolutional Neural Networks (CCNs) and Recurrent Neural Networks (RNNs)">
|
||
<title>Week 45, Convolutional Neural Networks (CCNs) and Recurrent Neural Networks (RNNs)</title>
|
||
<!-- Bootstrap style: bootstrap -->
|
||
<!-- doconce format html week45.do.txt --html_style=bootstrap --pygments_html_style=default --html_admon=bootstrap_panel --html_output=week45-bs --no_mako -->
|
||
<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': [('Plans for week 45', 2, None, 'plans-for-week-45'),
|
||
('Material for the lab sessions, additional ways to present '
|
||
'classification results and other practicalities',
|
||
2,
|
||
None,
|
||
'material-for-the-lab-sessions-additional-ways-to-present-classification-results-and-other-practicalities'),
|
||
('Material for Lecture Monday November 4',
|
||
2,
|
||
None,
|
||
'material-for-lecture-monday-november-4'),
|
||
('Convolutional Neural Networks (recognizing images)',
|
||
2,
|
||
None,
|
||
'convolutional-neural-networks-recognizing-images'),
|
||
('What is the Difference', 2, None, 'what-is-the-difference'),
|
||
('Neural Networks vs CNNs', 2, None, 'neural-networks-vs-cnns'),
|
||
('Why CNNS for images, sound files, medical images from CT scans '
|
||
'etc?',
|
||
2,
|
||
None,
|
||
'why-cnns-for-images-sound-files-medical-images-from-ct-scans-etc'),
|
||
('Regular NNs don’t scale well to full images',
|
||
2,
|
||
None,
|
||
'regular-nns-don-t-scale-well-to-full-images'),
|
||
('3D volumes of neurons', 2, None, '3d-volumes-of-neurons'),
|
||
('Layers used to build CNNs',
|
||
2,
|
||
None,
|
||
'layers-used-to-build-cnns'),
|
||
('CNNs in brief', 2, None, 'cnns-in-brief'),
|
||
('A deep CNN model ("From Raschka et '
|
||
'al":"https://github.com/rasbt/machine-learning-book")',
|
||
2,
|
||
None,
|
||
'a-deep-cnn-model-from-raschka-et-al-https-github-com-rasbt-machine-learning-book'),
|
||
('Key Idea', 2, None, 'key-idea'),
|
||
('Building convolutional neural networks in Tensorflow and Keras',
|
||
2,
|
||
None,
|
||
'building-convolutional-neural-networks-in-tensorflow-and-keras'),
|
||
('Setting it up', 2, None, 'setting-it-up'),
|
||
('The MNIST dataset again', 2, None, 'the-mnist-dataset-again'),
|
||
('Strong correlations', 2, None, 'strong-correlations'),
|
||
('Layers of a CNN', 2, None, 'layers-of-a-cnn'),
|
||
('Systematic reduction', 2, None, 'systematic-reduction'),
|
||
('Prerequisites: Collect and pre-process data',
|
||
2,
|
||
None,
|
||
'prerequisites-collect-and-pre-process-data'),
|
||
('Importing Keras and Tensorflow',
|
||
2,
|
||
None,
|
||
'importing-keras-and-tensorflow'),
|
||
('Running with Keras', 2, None, 'running-with-keras'),
|
||
('Final part', 2, None, 'final-part'),
|
||
('Final visualization', 2, None, 'final-visualization'),
|
||
('The CIFAR01 data set', 2, None, 'the-cifar01-data-set'),
|
||
('Verifying the data set', 2, None, 'verifying-the-data-set'),
|
||
('Set up the model', 2, None, 'set-up-the-model'),
|
||
('Add Dense layers on top', 2, None, 'add-dense-layers-on-top'),
|
||
('Compile and train the model',
|
||
2,
|
||
None,
|
||
'compile-and-train-the-model'),
|
||
('Finally, evaluate the model',
|
||
2,
|
||
None,
|
||
'finally-evaluate-the-model'),
|
||
('Building our own CNN code',
|
||
2,
|
||
None,
|
||
'building-our-own-cnn-code'),
|
||
('List of contents:', 3, None, 'list-of-contents'),
|
||
('Schedulers', 3, None, 'schedulers'),
|
||
('Usage of schedulers', 3, None, 'usage-of-schedulers'),
|
||
('Cost functions', 3, None, 'cost-functions'),
|
||
('Usage of cost functions', 3, None, 'usage-of-cost-functions'),
|
||
('Activation functions', 3, None, 'activation-functions'),
|
||
('Usage of activation functions',
|
||
3,
|
||
None,
|
||
'usage-of-activation-functions'),
|
||
('Convolution', 3, None, 'convolution'),
|
||
('Layers', 3, None, 'layers'),
|
||
('Convolution2DLayer: convolution in a hidden layer',
|
||
3,
|
||
None,
|
||
'convolution2dlayer-convolution-in-a-hidden-layer'),
|
||
('Backpropagation in the convolutional layer',
|
||
3,
|
||
None,
|
||
'backpropagation-in-the-convolutional-layer'),
|
||
('Demonstration', 3, None, 'demonstration'),
|
||
('Pooling Layer', 3, None, 'pooling-layer'),
|
||
('Flattening Layer', 3, None, 'flattening-layer'),
|
||
('Fully Connected Layers', 3, None, 'fully-connected-layers'),
|
||
('Optimized Convolution2DLayer',
|
||
3,
|
||
None,
|
||
'optimized-convolution2dlayer'),
|
||
('The Convolutional Neural Network (CNN)',
|
||
3,
|
||
None,
|
||
'the-convolutional-neural-network-cnn'),
|
||
('Usage of CNN code', 3, None, 'usage-of-cnn-code'),
|
||
('Additional Remarks', 3, None, 'additional-remarks'),
|
||
('Remarks on the speed', 3, None, 'remarks-on-the-speed'),
|
||
('Convolution using separable kernels',
|
||
3,
|
||
None,
|
||
'convolution-using-separable-kernels'),
|
||
('Convolution in the Fourier domain',
|
||
3,
|
||
None,
|
||
'convolution-in-the-fourier-domain'),
|
||
('From FFNNs and CNNs to recurrent neural networks (RNNs)',
|
||
2,
|
||
None,
|
||
'from-ffnns-and-cnns-to-recurrent-neural-networks-rnns'),
|
||
('Feedback connections', 2, None, 'feedback-connections'),
|
||
('Vanishing gradients', 2, None, 'vanishing-gradients'),
|
||
('Recurrent neural networks (RNNs): Overarching view',
|
||
2,
|
||
None,
|
||
'recurrent-neural-networks-rnns-overarching-view'),
|
||
('Sequential data only?', 2, None, 'sequential-data-only'),
|
||
('Differential equations', 2, None, 'differential-equations'),
|
||
('A simple example', 2, None, 'a-simple-example'),
|
||
('RNNs', 2, None, 'rnns'),
|
||
('What kinds of behaviour can RNNs exhibit?',
|
||
2,
|
||
None,
|
||
'what-kinds-of-behaviour-can-rnns-exhibit'),
|
||
('Basic layout, "Figures from Sebastian Rashcka et al, Machine '
|
||
'learning with Sickit-Learn and '
|
||
'PyTorch":"https://sebastianraschka.com/blog/2022/ml-pytorch-book.html"',
|
||
2,
|
||
None,
|
||
'basic-layout-figures-from-sebastian-rashcka-et-al-machine-learning-with-sickit-learn-and-pytorch-https-sebastianraschka-com-blog-2022-ml-pytorch-book-html'),
|
||
('Solving differential equations with RNNs',
|
||
2,
|
||
None,
|
||
'solving-differential-equations-with-rnns'),
|
||
('Two first-order differential equations',
|
||
2,
|
||
None,
|
||
'two-first-order-differential-equations'),
|
||
('Velocity only', 2, None, 'velocity-only'),
|
||
('Linking with RNNs', 2, None, 'linking-with-rnns'),
|
||
('Minor rewrite', 2, None, 'minor-rewrite'),
|
||
('RNNs in more detail', 2, None, 'rnns-in-more-detail'),
|
||
('RNNs in more detail, part 2',
|
||
2,
|
||
None,
|
||
'rnns-in-more-detail-part-2'),
|
||
('RNNs in more detail, part 3',
|
||
2,
|
||
None,
|
||
'rnns-in-more-detail-part-3'),
|
||
('RNNs in more detail, part 4',
|
||
2,
|
||
None,
|
||
'rnns-in-more-detail-part-4'),
|
||
('RNNs in more detail, part 5',
|
||
2,
|
||
None,
|
||
'rnns-in-more-detail-part-5'),
|
||
('RNNs in more detail, part 6',
|
||
2,
|
||
None,
|
||
'rnns-in-more-detail-part-6'),
|
||
('RNNs in more detail, part 7',
|
||
2,
|
||
None,
|
||
'rnns-in-more-detail-part-7'),
|
||
('Backpropagation through time',
|
||
2,
|
||
None,
|
||
'backpropagation-through-time'),
|
||
('The backward pass is linear',
|
||
2,
|
||
None,
|
||
'the-backward-pass-is-linear'),
|
||
('The problem of exploding or vanishing gradients',
|
||
2,
|
||
None,
|
||
'the-problem-of-exploding-or-vanishing-gradients'),
|
||
('Mathematical setup', 2, None, 'mathematical-setup'),
|
||
('Back propagation in time through figures, part 1',
|
||
2,
|
||
None,
|
||
'back-propagation-in-time-through-figures-part-1'),
|
||
('Back propagation in time, part 2',
|
||
2,
|
||
None,
|
||
'back-propagation-in-time-part-2'),
|
||
('Back propagation in time, part 3',
|
||
2,
|
||
None,
|
||
'back-propagation-in-time-part-3'),
|
||
('Back propagation in time, part 4',
|
||
2,
|
||
None,
|
||
'back-propagation-in-time-part-4'),
|
||
('Back propagation in time in equations',
|
||
2,
|
||
None,
|
||
'back-propagation-in-time-in-equations'),
|
||
('Chain rule again', 2, None, 'chain-rule-again'),
|
||
('Gradients of loss functions',
|
||
2,
|
||
None,
|
||
'gradients-of-loss-functions'),
|
||
('Summary of RNNs', 2, None, 'summary-of-rnns'),
|
||
('Summary of a typical RNN',
|
||
2,
|
||
None,
|
||
'summary-of-a-typical-rnn'),
|
||
('Four effective ways to learn an RNN and preparing for next '
|
||
'week',
|
||
2,
|
||
None,
|
||
'four-effective-ways-to-learn-an-rnn-and-preparing-for-next-week'),
|
||
('Gating mechanism: Long Short Term Memory (LSTM)',
|
||
2,
|
||
None,
|
||
'gating-mechanism-long-short-term-memory-lstm'),
|
||
('Implementing a memory cell in a neural network',
|
||
2,
|
||
None,
|
||
'implementing-a-memory-cell-in-a-neural-network'),
|
||
('LSTM details', 2, None, 'lstm-details'),
|
||
('Basic layout', 2, None, 'basic-layout'),
|
||
('More LSTM details', 2, None, 'more-lstm-details'),
|
||
('The forget gate', 2, None, 'the-forget-gate'),
|
||
('Input gate', 2, None, 'input-gate'),
|
||
('Forget and input', 2, None, 'forget-and-input'),
|
||
('Output gate', 2, None, 'output-gate')]}
|
||
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="week45-bs.html">Week 45, Convolutional Neural Networks (CCNs) and Recurrent Neural Networks (RNNs)</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="._week45-bs001.html#plans-for-week-45" style="font-size: 80%;"><b>Plans for week 45</b></a></li>
|
||
<!-- navigation toc: --> <li><a href="._week45-bs002.html#material-for-the-lab-sessions-additional-ways-to-present-classification-results-and-other-practicalities" style="font-size: 80%;"><b>Material for the lab sessions, additional ways to present classification results and other practicalities</b></a></li>
|
||
<!-- navigation toc: --> <li><a href="._week45-bs003.html#material-for-lecture-monday-november-4" style="font-size: 80%;"><b>Material for Lecture Monday November 4</b></a></li>
|
||
<!-- navigation toc: --> <li><a href="._week45-bs004.html#convolutional-neural-networks-recognizing-images" style="font-size: 80%;"><b>Convolutional Neural Networks (recognizing images)</b></a></li>
|
||
<!-- navigation toc: --> <li><a href="._week45-bs005.html#what-is-the-difference" style="font-size: 80%;"><b>What is the Difference</b></a></li>
|
||
<!-- navigation toc: --> <li><a href="._week45-bs006.html#neural-networks-vs-cnns" style="font-size: 80%;"><b>Neural Networks vs CNNs</b></a></li>
|
||
<!-- navigation toc: --> <li><a href="._week45-bs007.html#why-cnns-for-images-sound-files-medical-images-from-ct-scans-etc" style="font-size: 80%;"><b>Why CNNS for images, sound files, medical images from CT scans etc?</b></a></li>
|
||
<!-- navigation toc: --> <li><a href="._week45-bs008.html#regular-nns-don-t-scale-well-to-full-images" style="font-size: 80%;"><b>Regular NNs don’t scale well to full images</b></a></li>
|
||
<!-- navigation toc: --> <li><a href="._week45-bs009.html#3d-volumes-of-neurons" style="font-size: 80%;"><b>3D volumes of neurons</b></a></li>
|
||
<!-- navigation toc: --> <li><a href="._week45-bs010.html#layers-used-to-build-cnns" style="font-size: 80%;"><b>Layers used to build CNNs</b></a></li>
|
||
<!-- navigation toc: --> <li><a href="._week45-bs011.html#cnns-in-brief" style="font-size: 80%;"><b>CNNs in brief</b></a></li>
|
||
<!-- navigation toc: --> <li><a href="._week45-bs012.html#a-deep-cnn-model-from-raschka-et-al-https-github-com-rasbt-machine-learning-book" style="font-size: 80%;"><b>A deep CNN model ("From Raschka et al":"https://github.com/rasbt/machine-learning-book")</b></a></li>
|
||
<!-- navigation toc: --> <li><a href="._week45-bs013.html#key-idea" style="font-size: 80%;"><b>Key Idea</b></a></li>
|
||
<!-- navigation toc: --> <li><a href="._week45-bs014.html#building-convolutional-neural-networks-in-tensorflow-and-keras" style="font-size: 80%;"><b>Building convolutional neural networks in Tensorflow and Keras</b></a></li>
|
||
<!-- navigation toc: --> <li><a href="._week45-bs015.html#setting-it-up" style="font-size: 80%;"><b>Setting it up</b></a></li>
|
||
<!-- navigation toc: --> <li><a href="._week45-bs016.html#the-mnist-dataset-again" style="font-size: 80%;"><b>The MNIST dataset again</b></a></li>
|
||
<!-- navigation toc: --> <li><a href="._week45-bs017.html#strong-correlations" style="font-size: 80%;"><b>Strong correlations</b></a></li>
|
||
<!-- navigation toc: --> <li><a href="._week45-bs018.html#layers-of-a-cnn" style="font-size: 80%;"><b>Layers of a CNN</b></a></li>
|
||
<!-- navigation toc: --> <li><a href="._week45-bs019.html#systematic-reduction" style="font-size: 80%;"><b>Systematic reduction</b></a></li>
|
||
<!-- navigation toc: --> <li><a href="._week45-bs020.html#prerequisites-collect-and-pre-process-data" style="font-size: 80%;"><b>Prerequisites: Collect and pre-process data</b></a></li>
|
||
<!-- navigation toc: --> <li><a href="._week45-bs021.html#importing-keras-and-tensorflow" style="font-size: 80%;"><b>Importing Keras and Tensorflow</b></a></li>
|
||
<!-- navigation toc: --> <li><a href="._week45-bs022.html#running-with-keras" style="font-size: 80%;"><b>Running with Keras</b></a></li>
|
||
<!-- navigation toc: --> <li><a href="._week45-bs023.html#final-part" style="font-size: 80%;"><b>Final part</b></a></li>
|
||
<!-- navigation toc: --> <li><a href="._week45-bs024.html#final-visualization" style="font-size: 80%;"><b>Final visualization</b></a></li>
|
||
<!-- navigation toc: --> <li><a href="._week45-bs025.html#the-cifar01-data-set" style="font-size: 80%;"><b>The CIFAR01 data set</b></a></li>
|
||
<!-- navigation toc: --> <li><a href="._week45-bs026.html#verifying-the-data-set" style="font-size: 80%;"><b>Verifying the data set</b></a></li>
|
||
<!-- navigation toc: --> <li><a href="._week45-bs027.html#set-up-the-model" style="font-size: 80%;"><b>Set up the model</b></a></li>
|
||
<!-- navigation toc: --> <li><a href="._week45-bs028.html#add-dense-layers-on-top" style="font-size: 80%;"><b>Add Dense layers on top</b></a></li>
|
||
<!-- navigation toc: --> <li><a href="._week45-bs029.html#compile-and-train-the-model" style="font-size: 80%;"><b>Compile and train the model</b></a></li>
|
||
<!-- navigation toc: --> <li><a href="._week45-bs030.html#finally-evaluate-the-model" style="font-size: 80%;"><b>Finally, evaluate the model</b></a></li>
|
||
<!-- navigation toc: --> <li><a href="._week45-bs031.html#building-our-own-cnn-code" style="font-size: 80%;"><b>Building our own CNN code</b></a></li>
|
||
<!-- navigation toc: --> <li><a href="._week45-bs031.html#list-of-contents" style="font-size: 80%;"> List of contents:</a></li>
|
||
<!-- navigation toc: --> <li><a href="._week45-bs031.html#schedulers" style="font-size: 80%;"> Schedulers</a></li>
|
||
<!-- navigation toc: --> <li><a href="._week45-bs031.html#usage-of-schedulers" style="font-size: 80%;"> Usage of schedulers</a></li>
|
||
<!-- navigation toc: --> <li><a href="._week45-bs031.html#cost-functions" style="font-size: 80%;"> Cost functions</a></li>
|
||
<!-- navigation toc: --> <li><a href="._week45-bs031.html#usage-of-cost-functions" style="font-size: 80%;"> Usage of cost functions</a></li>
|
||
<!-- navigation toc: --> <li><a href="._week45-bs031.html#activation-functions" style="font-size: 80%;"> Activation functions</a></li>
|
||
<!-- navigation toc: --> <li><a href="._week45-bs031.html#usage-of-activation-functions" style="font-size: 80%;"> Usage of activation functions</a></li>
|
||
<!-- navigation toc: --> <li><a href="._week45-bs031.html#convolution" style="font-size: 80%;"> Convolution</a></li>
|
||
<!-- navigation toc: --> <li><a href="._week45-bs031.html#layers" style="font-size: 80%;"> Layers</a></li>
|
||
<!-- navigation toc: --> <li><a href="._week45-bs031.html#convolution2dlayer-convolution-in-a-hidden-layer" style="font-size: 80%;"> Convolution2DLayer: convolution in a hidden layer</a></li>
|
||
<!-- navigation toc: --> <li><a href="._week45-bs031.html#backpropagation-in-the-convolutional-layer" style="font-size: 80%;"> Backpropagation in the convolutional layer</a></li>
|
||
<!-- navigation toc: --> <li><a href="._week45-bs031.html#demonstration" style="font-size: 80%;"> Demonstration</a></li>
|
||
<!-- navigation toc: --> <li><a href="._week45-bs031.html#pooling-layer" style="font-size: 80%;"> Pooling Layer</a></li>
|
||
<!-- navigation toc: --> <li><a href="._week45-bs031.html#flattening-layer" style="font-size: 80%;"> Flattening Layer</a></li>
|
||
<!-- navigation toc: --> <li><a href="._week45-bs031.html#fully-connected-layers" style="font-size: 80%;"> Fully Connected Layers</a></li>
|
||
<!-- navigation toc: --> <li><a href="._week45-bs031.html#optimized-convolution2dlayer" style="font-size: 80%;"> Optimized Convolution2DLayer</a></li>
|
||
<!-- navigation toc: --> <li><a href="._week45-bs031.html#the-convolutional-neural-network-cnn" style="font-size: 80%;"> The Convolutional Neural Network (CNN)</a></li>
|
||
<!-- navigation toc: --> <li><a href="._week45-bs031.html#usage-of-cnn-code" style="font-size: 80%;"> Usage of CNN code</a></li>
|
||
<!-- navigation toc: --> <li><a href="._week45-bs031.html#additional-remarks" style="font-size: 80%;"> Additional Remarks</a></li>
|
||
<!-- navigation toc: --> <li><a href="._week45-bs031.html#remarks-on-the-speed" style="font-size: 80%;"> Remarks on the speed</a></li>
|
||
<!-- navigation toc: --> <li><a href="._week45-bs031.html#convolution-using-separable-kernels" style="font-size: 80%;"> Convolution using separable kernels</a></li>
|
||
<!-- navigation toc: --> <li><a href="._week45-bs031.html#convolution-in-the-fourier-domain" style="font-size: 80%;"> Convolution in the Fourier domain</a></li>
|
||
<!-- navigation toc: --> <li><a href="._week45-bs032.html#from-ffnns-and-cnns-to-recurrent-neural-networks-rnns" style="font-size: 80%;"><b>From FFNNs and CNNs to recurrent neural networks (RNNs)</b></a></li>
|
||
<!-- navigation toc: --> <li><a href="._week45-bs033.html#feedback-connections" style="font-size: 80%;"><b>Feedback connections</b></a></li>
|
||
<!-- navigation toc: --> <li><a href="._week45-bs034.html#vanishing-gradients" style="font-size: 80%;"><b>Vanishing gradients</b></a></li>
|
||
<!-- navigation toc: --> <li><a href="._week45-bs035.html#recurrent-neural-networks-rnns-overarching-view" style="font-size: 80%;"><b>Recurrent neural networks (RNNs): Overarching view</b></a></li>
|
||
<!-- navigation toc: --> <li><a href="._week45-bs036.html#sequential-data-only" style="font-size: 80%;"><b>Sequential data only?</b></a></li>
|
||
<!-- navigation toc: --> <li><a href="._week45-bs037.html#differential-equations" style="font-size: 80%;"><b>Differential equations</b></a></li>
|
||
<!-- navigation toc: --> <li><a href="#a-simple-example" style="font-size: 80%;"><b>A simple example</b></a></li>
|
||
<!-- navigation toc: --> <li><a href="._week45-bs039.html#rnns" style="font-size: 80%;"><b>RNNs</b></a></li>
|
||
<!-- navigation toc: --> <li><a href="._week45-bs040.html#what-kinds-of-behaviour-can-rnns-exhibit" style="font-size: 80%;"><b>What kinds of behaviour can RNNs exhibit?</b></a></li>
|
||
<!-- navigation toc: --> <li><a href="._week45-bs041.html#basic-layout-figures-from-sebastian-rashcka-et-al-machine-learning-with-sickit-learn-and-pytorch-https-sebastianraschka-com-blog-2022-ml-pytorch-book-html" style="font-size: 80%;"><b>Basic layout, "Figures from Sebastian Rashcka et al, Machine learning with Sickit-Learn and PyTorch":"https://sebastianraschka.com/blog/2022/ml-pytorch-book.html"</b></a></li>
|
||
<!-- navigation toc: --> <li><a href="._week45-bs042.html#solving-differential-equations-with-rnns" style="font-size: 80%;"><b>Solving differential equations with RNNs</b></a></li>
|
||
<!-- navigation toc: --> <li><a href="._week45-bs043.html#two-first-order-differential-equations" style="font-size: 80%;"><b>Two first-order differential equations</b></a></li>
|
||
<!-- navigation toc: --> <li><a href="._week45-bs044.html#velocity-only" style="font-size: 80%;"><b>Velocity only</b></a></li>
|
||
<!-- navigation toc: --> <li><a href="._week45-bs045.html#linking-with-rnns" style="font-size: 80%;"><b>Linking with RNNs</b></a></li>
|
||
<!-- navigation toc: --> <li><a href="._week45-bs046.html#minor-rewrite" style="font-size: 80%;"><b>Minor rewrite</b></a></li>
|
||
<!-- navigation toc: --> <li><a href="._week45-bs047.html#rnns-in-more-detail" style="font-size: 80%;"><b>RNNs in more detail</b></a></li>
|
||
<!-- navigation toc: --> <li><a href="._week45-bs048.html#rnns-in-more-detail-part-2" style="font-size: 80%;"><b>RNNs in more detail, part 2</b></a></li>
|
||
<!-- navigation toc: --> <li><a href="._week45-bs049.html#rnns-in-more-detail-part-3" style="font-size: 80%;"><b>RNNs in more detail, part 3</b></a></li>
|
||
<!-- navigation toc: --> <li><a href="._week45-bs050.html#rnns-in-more-detail-part-4" style="font-size: 80%;"><b>RNNs in more detail, part 4</b></a></li>
|
||
<!-- navigation toc: --> <li><a href="._week45-bs051.html#rnns-in-more-detail-part-5" style="font-size: 80%;"><b>RNNs in more detail, part 5</b></a></li>
|
||
<!-- navigation toc: --> <li><a href="._week45-bs052.html#rnns-in-more-detail-part-6" style="font-size: 80%;"><b>RNNs in more detail, part 6</b></a></li>
|
||
<!-- navigation toc: --> <li><a href="._week45-bs053.html#rnns-in-more-detail-part-7" style="font-size: 80%;"><b>RNNs in more detail, part 7</b></a></li>
|
||
<!-- navigation toc: --> <li><a href="._week45-bs054.html#backpropagation-through-time" style="font-size: 80%;"><b>Backpropagation through time</b></a></li>
|
||
<!-- navigation toc: --> <li><a href="._week45-bs055.html#the-backward-pass-is-linear" style="font-size: 80%;"><b>The backward pass is linear</b></a></li>
|
||
<!-- navigation toc: --> <li><a href="._week45-bs056.html#the-problem-of-exploding-or-vanishing-gradients" style="font-size: 80%;"><b>The problem of exploding or vanishing gradients</b></a></li>
|
||
<!-- navigation toc: --> <li><a href="._week45-bs057.html#mathematical-setup" style="font-size: 80%;"><b>Mathematical setup</b></a></li>
|
||
<!-- navigation toc: --> <li><a href="._week45-bs058.html#back-propagation-in-time-through-figures-part-1" style="font-size: 80%;"><b>Back propagation in time through figures, part 1</b></a></li>
|
||
<!-- navigation toc: --> <li><a href="._week45-bs059.html#back-propagation-in-time-part-2" style="font-size: 80%;"><b>Back propagation in time, part 2</b></a></li>
|
||
<!-- navigation toc: --> <li><a href="._week45-bs060.html#back-propagation-in-time-part-3" style="font-size: 80%;"><b>Back propagation in time, part 3</b></a></li>
|
||
<!-- navigation toc: --> <li><a href="._week45-bs061.html#back-propagation-in-time-part-4" style="font-size: 80%;"><b>Back propagation in time, part 4</b></a></li>
|
||
<!-- navigation toc: --> <li><a href="._week45-bs062.html#back-propagation-in-time-in-equations" style="font-size: 80%;"><b>Back propagation in time in equations</b></a></li>
|
||
<!-- navigation toc: --> <li><a href="._week45-bs063.html#chain-rule-again" style="font-size: 80%;"><b>Chain rule again</b></a></li>
|
||
<!-- navigation toc: --> <li><a href="._week45-bs064.html#gradients-of-loss-functions" style="font-size: 80%;"><b>Gradients of loss functions</b></a></li>
|
||
<!-- navigation toc: --> <li><a href="._week45-bs065.html#summary-of-rnns" style="font-size: 80%;"><b>Summary of RNNs</b></a></li>
|
||
<!-- navigation toc: --> <li><a href="._week45-bs066.html#summary-of-a-typical-rnn" style="font-size: 80%;"><b>Summary of a typical RNN</b></a></li>
|
||
<!-- navigation toc: --> <li><a href="._week45-bs067.html#four-effective-ways-to-learn-an-rnn-and-preparing-for-next-week" style="font-size: 80%;"><b>Four effective ways to learn an RNN and preparing for next week</b></a></li>
|
||
<!-- navigation toc: --> <li><a href="._week45-bs068.html#gating-mechanism-long-short-term-memory-lstm" style="font-size: 80%;"><b>Gating mechanism: Long Short Term Memory (LSTM)</b></a></li>
|
||
<!-- navigation toc: --> <li><a href="._week45-bs069.html#implementing-a-memory-cell-in-a-neural-network" style="font-size: 80%;"><b>Implementing a memory cell in a neural network</b></a></li>
|
||
<!-- navigation toc: --> <li><a href="._week45-bs070.html#lstm-details" style="font-size: 80%;"><b>LSTM details</b></a></li>
|
||
<!-- navigation toc: --> <li><a href="._week45-bs071.html#basic-layout" style="font-size: 80%;"><b>Basic layout</b></a></li>
|
||
<!-- navigation toc: --> <li><a href="._week45-bs072.html#more-lstm-details" style="font-size: 80%;"><b>More LSTM details</b></a></li>
|
||
<!-- navigation toc: --> <li><a href="._week45-bs073.html#the-forget-gate" style="font-size: 80%;"><b>The forget gate</b></a></li>
|
||
<!-- navigation toc: --> <li><a href="._week45-bs074.html#input-gate" style="font-size: 80%;"><b>Input gate</b></a></li>
|
||
<!-- navigation toc: --> <li><a href="._week45-bs075.html#forget-and-input" style="font-size: 80%;"><b>Forget and input</b></a></li>
|
||
<!-- navigation toc: --> <li><a href="._week45-bs076.html#output-gate" style="font-size: 80%;"><b>Output gate</b></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="part0038"></a>
|
||
<!-- !split -->
|
||
<h2 id="a-simple-example" class="anchor">A simple example </h2>
|
||
|
||
|
||
<!-- code=python (!bc pycod) typeset with pygments style "default" -->
|
||
<div class="cell border-box-sizing code_cell rendered">
|
||
<div class="input">
|
||
<div class="inner_cell">
|
||
<div class="input_area">
|
||
<div class="highlight" style="background: #f8f8f8">
|
||
<pre style="line-height: 125%;"><span style="color: #408080; font-style: italic"># Start importing packages</span>
|
||
<span style="color: #008000; font-weight: bold">import</span> <span style="color: #0000FF; font-weight: bold">pandas</span> <span style="color: #008000; font-weight: bold">as</span> <span style="color: #0000FF; font-weight: bold">pd</span>
|
||
<span style="color: #008000; font-weight: bold">import</span> <span style="color: #0000FF; font-weight: bold">numpy</span> <span style="color: #008000; font-weight: bold">as</span> <span style="color: #0000FF; font-weight: bold">np</span>
|
||
<span style="color: #008000; font-weight: bold">import</span> <span style="color: #0000FF; font-weight: bold">matplotlib.pyplot</span> <span style="color: #008000; font-weight: bold">as</span> <span style="color: #0000FF; font-weight: bold">plt</span>
|
||
<span style="color: #008000; font-weight: bold">import</span> <span style="color: #0000FF; font-weight: bold">tensorflow</span> <span style="color: #008000; font-weight: bold">as</span> <span style="color: #0000FF; font-weight: bold">tf</span>
|
||
<span style="color: #008000; font-weight: bold">from</span> <span style="color: #0000FF; font-weight: bold">tensorflow.keras</span> <span style="color: #008000; font-weight: bold">import</span> datasets, layers, models
|
||
<span style="color: #008000; font-weight: bold">from</span> <span style="color: #0000FF; font-weight: bold">tensorflow.keras.layers</span> <span style="color: #008000; font-weight: bold">import</span> Input
|
||
<span style="color: #008000; font-weight: bold">from</span> <span style="color: #0000FF; font-weight: bold">tensorflow.keras.models</span> <span style="color: #008000; font-weight: bold">import</span> Model, Sequential
|
||
<span style="color: #008000; font-weight: bold">from</span> <span style="color: #0000FF; font-weight: bold">tensorflow.keras.layers</span> <span style="color: #008000; font-weight: bold">import</span> Dense, SimpleRNN, LSTM, GRU
|
||
<span style="color: #008000; font-weight: bold">from</span> <span style="color: #0000FF; font-weight: bold">tensorflow.keras</span> <span style="color: #008000; font-weight: bold">import</span> optimizers
|
||
<span style="color: #008000; font-weight: bold">from</span> <span style="color: #0000FF; font-weight: bold">tensorflow.keras</span> <span style="color: #008000; font-weight: bold">import</span> regularizers
|
||
<span style="color: #008000; font-weight: bold">from</span> <span style="color: #0000FF; font-weight: bold">tensorflow.keras.utils</span> <span style="color: #008000; font-weight: bold">import</span> to_categorical
|
||
|
||
|
||
|
||
<span style="color: #408080; font-style: italic"># convert into dataset matrix</span>
|
||
<span style="color: #008000; font-weight: bold">def</span> <span style="color: #0000FF">convertToMatrix</span>(data, step):
|
||
X, Y <span style="color: #666666">=</span>[], []
|
||
<span style="color: #008000; font-weight: bold">for</span> i <span style="color: #AA22FF; font-weight: bold">in</span> <span style="color: #008000">range</span>(<span style="color: #008000">len</span>(data)<span style="color: #666666">-</span>step):
|
||
d<span style="color: #666666">=</span>i<span style="color: #666666">+</span>step
|
||
X<span style="color: #666666">.</span>append(data[i:d,])
|
||
Y<span style="color: #666666">.</span>append(data[d,])
|
||
<span style="color: #008000; font-weight: bold">return</span> np<span style="color: #666666">.</span>array(X), np<span style="color: #666666">.</span>array(Y)
|
||
|
||
step <span style="color: #666666">=</span> <span style="color: #666666">4</span>
|
||
N <span style="color: #666666">=</span> <span style="color: #666666">1000</span>
|
||
Tp <span style="color: #666666">=</span> <span style="color: #666666">800</span>
|
||
|
||
t<span style="color: #666666">=</span>np<span style="color: #666666">.</span>arange(<span style="color: #666666">0</span>,N)
|
||
x<span style="color: #666666">=</span>np<span style="color: #666666">.</span>sin(<span style="color: #666666">0.02*</span>t)<span style="color: #666666">+2*</span>np<span style="color: #666666">.</span>random<span style="color: #666666">.</span>rand(N)
|
||
df <span style="color: #666666">=</span> pd<span style="color: #666666">.</span>DataFrame(x)
|
||
df<span style="color: #666666">.</span>head()
|
||
|
||
values<span style="color: #666666">=</span>df<span style="color: #666666">.</span>values
|
||
train,test <span style="color: #666666">=</span> values[<span style="color: #666666">0</span>:Tp,:], values[Tp:N,:]
|
||
|
||
<span style="color: #408080; font-style: italic"># add step elements into train and test</span>
|
||
test <span style="color: #666666">=</span> np<span style="color: #666666">.</span>append(test,np<span style="color: #666666">.</span>repeat(test[<span style="color: #666666">-1</span>,],step))
|
||
train <span style="color: #666666">=</span> np<span style="color: #666666">.</span>append(train,np<span style="color: #666666">.</span>repeat(train[<span style="color: #666666">-1</span>,],step))
|
||
|
||
trainX,trainY <span style="color: #666666">=</span>convertToMatrix(train,step)
|
||
testX,testY <span style="color: #666666">=</span>convertToMatrix(test,step)
|
||
trainX <span style="color: #666666">=</span> np<span style="color: #666666">.</span>reshape(trainX, (trainX<span style="color: #666666">.</span>shape[<span style="color: #666666">0</span>], <span style="color: #666666">1</span>, trainX<span style="color: #666666">.</span>shape[<span style="color: #666666">1</span>]))
|
||
testX <span style="color: #666666">=</span> np<span style="color: #666666">.</span>reshape(testX, (testX<span style="color: #666666">.</span>shape[<span style="color: #666666">0</span>], <span style="color: #666666">1</span>, testX<span style="color: #666666">.</span>shape[<span style="color: #666666">1</span>]))
|
||
|
||
model <span style="color: #666666">=</span> Sequential()
|
||
model<span style="color: #666666">.</span>add(SimpleRNN(units<span style="color: #666666">=32</span>, input_shape<span style="color: #666666">=</span>(<span style="color: #666666">1</span>,step), activation<span style="color: #666666">=</span><span style="color: #BA2121">"relu"</span>))
|
||
model<span style="color: #666666">.</span>add(Dense(<span style="color: #666666">8</span>, activation<span style="color: #666666">=</span><span style="color: #BA2121">"relu"</span>))
|
||
model<span style="color: #666666">.</span>add(Dense(<span style="color: #666666">1</span>))
|
||
model<span style="color: #666666">.</span>compile(loss<span style="color: #666666">=</span><span style="color: #BA2121">'mean_squared_error'</span>, optimizer<span style="color: #666666">=</span><span style="color: #BA2121">'rmsprop'</span>)
|
||
model<span style="color: #666666">.</span>summary()
|
||
|
||
model<span style="color: #666666">.</span>fit(trainX,trainY, epochs<span style="color: #666666">=100</span>, batch_size<span style="color: #666666">=16</span>, verbose<span style="color: #666666">=2</span>)
|
||
trainPredict <span style="color: #666666">=</span> model<span style="color: #666666">.</span>predict(trainX)
|
||
testPredict<span style="color: #666666">=</span> model<span style="color: #666666">.</span>predict(testX)
|
||
predicted<span style="color: #666666">=</span>np<span style="color: #666666">.</span>concatenate((trainPredict,testPredict),axis<span style="color: #666666">=0</span>)
|
||
|
||
trainScore <span style="color: #666666">=</span> model<span style="color: #666666">.</span>evaluate(trainX, trainY, verbose<span style="color: #666666">=0</span>)
|
||
<span style="color: #008000">print</span>(trainScore)
|
||
plt<span style="color: #666666">.</span>plot(df)
|
||
plt<span style="color: #666666">.</span>plot(predicted)
|
||
plt<span style="color: #666666">.</span>show()
|
||
</pre>
|
||
</div>
|
||
</div>
|
||
</div>
|
||
</div>
|
||
<div class="output_wrapper">
|
||
<div class="output">
|
||
<div class="output_area">
|
||
<div class="output_subarea output_stream output_stdout output_text">
|
||
</div>
|
||
</div>
|
||
</div>
|
||
</div>
|
||
</div>
|
||
|
||
|
||
<p>
|
||
<!-- navigation buttons at the bottom of the page -->
|
||
<ul class="pagination">
|
||
<li><a href="._week45-bs037.html">«</a></li>
|
||
<li><a href="._week45-bs000.html">1</a></li>
|
||
<li><a href="">...</a></li>
|
||
<li><a href="._week45-bs030.html">31</a></li>
|
||
<li><a href="._week45-bs031.html">32</a></li>
|
||
<li><a href="._week45-bs032.html">33</a></li>
|
||
<li><a href="._week45-bs033.html">34</a></li>
|
||
<li><a href="._week45-bs034.html">35</a></li>
|
||
<li><a href="._week45-bs035.html">36</a></li>
|
||
<li><a href="._week45-bs036.html">37</a></li>
|
||
<li><a href="._week45-bs037.html">38</a></li>
|
||
<li class="active"><a href="._week45-bs038.html">39</a></li>
|
||
<li><a href="._week45-bs039.html">40</a></li>
|
||
<li><a href="._week45-bs040.html">41</a></li>
|
||
<li><a href="._week45-bs041.html">42</a></li>
|
||
<li><a href="._week45-bs042.html">43</a></li>
|
||
<li><a href="._week45-bs043.html">44</a></li>
|
||
<li><a href="._week45-bs044.html">45</a></li>
|
||
<li><a href="._week45-bs045.html">46</a></li>
|
||
<li><a href="._week45-bs046.html">47</a></li>
|
||
<li><a href="._week45-bs047.html">48</a></li>
|
||
<li><a href="">...</a></li>
|
||
<li><a href="._week45-bs076.html">77</a></li>
|
||
<li><a href="._week45-bs039.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="https://..."><img width="250" align=right src="https://..."></a>
|
||
</footer>
|
||
-->
|
||
<center style="font-size:80%">
|
||
<!-- copyright only on the titlepage -->
|
||
</center>
|
||
</body>
|
||
</html>
|
||
|