283 lines
16 KiB
HTML
283 lines
16 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, Recurrent Neural Networks">
|
|
<title>Week 45, Recurrent Neural Networks</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': [('Plan for week 45', 2, None, 'plan-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'),
|
|
('Searching for Optimal Regularization Parameters $\\lambda$',
|
|
2,
|
|
None,
|
|
'searching-for-optimal-regularization-parameters-lambda'),
|
|
('Grid Search', 2, None, 'grid-search'),
|
|
('Randomized Grid Search', 2, None, 'randomized-grid-search'),
|
|
('Wisconsin Cancer Data', 2, None, 'wisconsin-cancer-data'),
|
|
('Using the correlation matrix',
|
|
2,
|
|
None,
|
|
'using-the-correlation-matrix'),
|
|
('Discussing the correlation data',
|
|
2,
|
|
None,
|
|
'discussing-the-correlation-data'),
|
|
('Other ways of presenting a classification problem',
|
|
2,
|
|
None,
|
|
'other-ways-of-presenting-a-classification-problem'),
|
|
('Combinations of classification results',
|
|
2,
|
|
None,
|
|
'combinations-of-classification-results'),
|
|
('Positive and negative prediction values',
|
|
2,
|
|
None,
|
|
'positive-and-negative-prediction-values'),
|
|
('Other quantities', 2, None, 'other-quantities'),
|
|
('$F_1$ score', 2, None, 'f-1-score'),
|
|
('ROC curve', 2, None, 'roc-curve'),
|
|
('Cumulative gain curve', 2, None, 'cumulative-gain-curve'),
|
|
('Other measures in classification studies: Cancer Data again',
|
|
2,
|
|
None,
|
|
'other-measures-in-classification-studies-cancer-data-again'),
|
|
('Material for Lecture Thursday November 9',
|
|
2,
|
|
None,
|
|
'material-for-lecture-thursday-november-9'),
|
|
('Recurrent neural networks (RNNs): Overarching view',
|
|
2,
|
|
None,
|
|
'recurrent-neural-networks-rnns-overarching-view'),
|
|
('A simple example', 2, None, 'a-simple-example'),
|
|
('RNNs', 3, None, 'rnns'),
|
|
('Basic layout', 2, None, 'basic-layout'),
|
|
('We need to specify the initial activity state of all the '
|
|
'hidden and output units',
|
|
3,
|
|
None,
|
|
'we-need-to-specify-the-initial-activity-state-of-all-the-hidden-and-output-units'),
|
|
('We can specify inputs in several ways',
|
|
3,
|
|
None,
|
|
'we-can-specify-inputs-in-several-ways'),
|
|
('We can specify targets in several ways',
|
|
3,
|
|
None,
|
|
'we-can-specify-targets-in-several-ways'),
|
|
('Backpropagation through time',
|
|
3,
|
|
None,
|
|
'backpropagation-through-time'),
|
|
('The backward pass is linear',
|
|
3,
|
|
None,
|
|
'the-backward-pass-is-linear'),
|
|
('The problem of exploding or vanishing gradients',
|
|
2,
|
|
None,
|
|
'the-problem-of-exploding-or-vanishing-gradients'),
|
|
('Four effective ways to learn an RNN',
|
|
2,
|
|
None,
|
|
'four-effective-ways-to-learn-an-rnn'),
|
|
('Long Short Term Memory (LSTM)',
|
|
3,
|
|
None,
|
|
'long-short-term-memory-lstm'),
|
|
('Implementing a memory cell in a neural network',
|
|
3,
|
|
None,
|
|
'implementing-a-memory-cell-in-a-neural-network'),
|
|
('An extrapolation example', 2, None, 'an-extrapolation-example'),
|
|
('Formatting the Data', 2, None, 'formatting-the-data'),
|
|
('Predicting New Points With A Trained Recurrent Neural Network',
|
|
2,
|
|
None,
|
|
'predicting-new-points-with-a-trained-recurrent-neural-network'),
|
|
('Other Things to Try', 2, None, 'other-things-to-try'),
|
|
('Other Types of Recurrent Neural Networks',
|
|
2,
|
|
None,
|
|
'other-types-of-recurrent-neural-networks')]}
|
|
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, Recurrent 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="._week45-bs001.html#plan-for-week-45" style="font-size: 80%;"><b>Plan 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#searching-for-optimal-regularization-parameters-lambda" style="font-size: 80%;"><b>Searching for Optimal Regularization Parameters \( \lambda \)</b></a></li>
|
|
<!-- navigation toc: --> <li><a href="._week45-bs004.html#grid-search" style="font-size: 80%;"><b>Grid Search</b></a></li>
|
|
<!-- navigation toc: --> <li><a href="._week45-bs005.html#randomized-grid-search" style="font-size: 80%;"><b>Randomized Grid Search</b></a></li>
|
|
<!-- navigation toc: --> <li><a href="._week45-bs006.html#wisconsin-cancer-data" style="font-size: 80%;"><b>Wisconsin Cancer Data</b></a></li>
|
|
<!-- navigation toc: --> <li><a href="._week45-bs007.html#using-the-correlation-matrix" style="font-size: 80%;"><b>Using the correlation matrix</b></a></li>
|
|
<!-- navigation toc: --> <li><a href="._week45-bs008.html#discussing-the-correlation-data" style="font-size: 80%;"><b>Discussing the correlation data</b></a></li>
|
|
<!-- navigation toc: --> <li><a href="._week45-bs009.html#other-ways-of-presenting-a-classification-problem" style="font-size: 80%;"><b>Other ways of presenting a classification problem</b></a></li>
|
|
<!-- navigation toc: --> <li><a href="._week45-bs010.html#combinations-of-classification-results" style="font-size: 80%;"><b>Combinations of classification results</b></a></li>
|
|
<!-- navigation toc: --> <li><a href="._week45-bs011.html#positive-and-negative-prediction-values" style="font-size: 80%;"><b>Positive and negative prediction values</b></a></li>
|
|
<!-- navigation toc: --> <li><a href="._week45-bs012.html#other-quantities" style="font-size: 80%;"><b>Other quantities</b></a></li>
|
|
<!-- navigation toc: --> <li><a href="._week45-bs013.html#f-1-score" style="font-size: 80%;"><b>\( F_1 \) score</b></a></li>
|
|
<!-- navigation toc: --> <li><a href="._week45-bs014.html#roc-curve" style="font-size: 80%;"><b>ROC curve</b></a></li>
|
|
<!-- navigation toc: --> <li><a href="._week45-bs015.html#cumulative-gain-curve" style="font-size: 80%;"><b>Cumulative gain curve</b></a></li>
|
|
<!-- navigation toc: --> <li><a href="._week45-bs016.html#other-measures-in-classification-studies-cancer-data-again" style="font-size: 80%;"><b>Other measures in classification studies: Cancer Data again</b></a></li>
|
|
<!-- navigation toc: --> <li><a href="._week45-bs017.html#material-for-lecture-thursday-november-9" style="font-size: 80%;"><b>Material for Lecture Thursday November 9</b></a></li>
|
|
<!-- navigation toc: --> <li><a href="#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-bs019.html#a-simple-example" style="font-size: 80%;"><b>A simple example</b></a></li>
|
|
<!-- navigation toc: --> <li><a href="._week45-bs019.html#rnns" style="font-size: 80%;"> RNNs</a></li>
|
|
<!-- navigation toc: --> <li><a href="._week45-bs020.html#basic-layout" style="font-size: 80%;"><b>Basic layout</b></a></li>
|
|
<!-- navigation toc: --> <li><a href="._week45-bs020.html#we-need-to-specify-the-initial-activity-state-of-all-the-hidden-and-output-units" style="font-size: 80%;"> We need to specify the initial activity state of all the hidden and output units</a></li>
|
|
<!-- navigation toc: --> <li><a href="._week45-bs020.html#we-can-specify-inputs-in-several-ways" style="font-size: 80%;"> We can specify inputs in several ways</a></li>
|
|
<!-- navigation toc: --> <li><a href="._week45-bs020.html#we-can-specify-targets-in-several-ways" style="font-size: 80%;"> We can specify targets in several ways</a></li>
|
|
<!-- navigation toc: --> <li><a href="._week45-bs020.html#backpropagation-through-time" style="font-size: 80%;"> Backpropagation through time</a></li>
|
|
<!-- navigation toc: --> <li><a href="._week45-bs020.html#the-backward-pass-is-linear" style="font-size: 80%;"> The backward pass is linear</a></li>
|
|
<!-- navigation toc: --> <li><a href="._week45-bs021.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-bs022.html#four-effective-ways-to-learn-an-rnn" style="font-size: 80%;"><b>Four effective ways to learn an RNN</b></a></li>
|
|
<!-- navigation toc: --> <li><a href="._week45-bs022.html#long-short-term-memory-lstm" style="font-size: 80%;"> Long Short Term Memory (LSTM)</a></li>
|
|
<!-- navigation toc: --> <li><a href="._week45-bs022.html#implementing-a-memory-cell-in-a-neural-network" style="font-size: 80%;"> Implementing a memory cell in a neural network</a></li>
|
|
<!-- navigation toc: --> <li><a href="._week45-bs023.html#an-extrapolation-example" style="font-size: 80%;"><b>An extrapolation example</b></a></li>
|
|
<!-- navigation toc: --> <li><a href="._week45-bs024.html#formatting-the-data" style="font-size: 80%;"><b>Formatting the Data</b></a></li>
|
|
<!-- navigation toc: --> <li><a href="._week45-bs025.html#predicting-new-points-with-a-trained-recurrent-neural-network" style="font-size: 80%;"><b>Predicting New Points With A Trained Recurrent Neural Network</b></a></li>
|
|
<!-- navigation toc: --> <li><a href="._week45-bs026.html#other-things-to-try" style="font-size: 80%;"><b>Other Things to Try</b></a></li>
|
|
<!-- navigation toc: --> <li><a href="._week45-bs027.html#other-types-of-recurrent-neural-networks" style="font-size: 80%;"><b>Other Types of Recurrent Neural Networks</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="part0018"></a>
|
|
<!-- !split -->
|
|
<h2 id="recurrent-neural-networks-rnns-overarching-view" class="anchor">Recurrent neural networks (RNNs): Overarching view </h2>
|
|
|
|
<p>Till now our focus has been, including convolutional neural networks
|
|
as well, on feedforward neural networks. The output or the activations
|
|
flow only in one direction, from the input layer to the output layer.
|
|
</p>
|
|
|
|
<p>A recurrent neural network (RNN) looks very much like a feedforward
|
|
neural network, except that it also has connections pointing
|
|
backward.
|
|
</p>
|
|
|
|
<p>RNNs are used to analyze time series data such as stock prices, and
|
|
tell you when to buy or sell. In autonomous driving systems, they can
|
|
anticipate car trajectories and help avoid accidents. More generally,
|
|
they can work on sequences of arbitrary lengths, rather than on
|
|
fixed-sized inputs like all the nets we have discussed so far. For
|
|
example, they can take sentences, documents, or audio samples as
|
|
input, making them extremely useful for natural language processing
|
|
systems such as automatic translation and speech-to-text.
|
|
</p>
|
|
|
|
<p>
|
|
<!-- navigation buttons at the bottom of the page -->
|
|
<ul class="pagination">
|
|
<li><a href="._week45-bs017.html">«</a></li>
|
|
<li><a href="._week45-bs000.html">1</a></li>
|
|
<li><a href="">...</a></li>
|
|
<li><a href="._week45-bs010.html">11</a></li>
|
|
<li><a href="._week45-bs011.html">12</a></li>
|
|
<li><a href="._week45-bs012.html">13</a></li>
|
|
<li><a href="._week45-bs013.html">14</a></li>
|
|
<li><a href="._week45-bs014.html">15</a></li>
|
|
<li><a href="._week45-bs015.html">16</a></li>
|
|
<li><a href="._week45-bs016.html">17</a></li>
|
|
<li><a href="._week45-bs017.html">18</a></li>
|
|
<li class="active"><a href="._week45-bs018.html">19</a></li>
|
|
<li><a href="._week45-bs019.html">20</a></li>
|
|
<li><a href="._week45-bs020.html">21</a></li>
|
|
<li><a href="._week45-bs021.html">22</a></li>
|
|
<li><a href="._week45-bs022.html">23</a></li>
|
|
<li><a href="._week45-bs023.html">24</a></li>
|
|
<li><a href="._week45-bs024.html">25</a></li>
|
|
<li><a href="._week45-bs025.html">26</a></li>
|
|
<li><a href="._week45-bs026.html">27</a></li>
|
|
<li><a href="._week45-bs027.html">28</a></li>
|
|
<li><a href="._week45-bs019.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>
|
|
|