lars/FYS-STK4155
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Editing auto encoders

Browse Source
This commit is contained in:
mhjensen
2019-01-01 10:17:06 +01:00
parent 1b60558520
commit ced370c97a
10 changed files with 57 additions and 24 deletions
Download Patch File Download Diff File Expand all files Collapse all files
doc/pub/Autoencoders/html/._Autoencoders-bs000.html
+6 -3
View File
@@ -41,7 +41,8 @@ Automatically generated HTML file from DocOnce source
<!-- tocinfo
{'highest level': 2,
'sections': [('Autoencoders: Overarching view', 2, None, '___sec0')]}
'sections': [('Autoencoders: Overarching view', 2, None, '___sec0'),
('Simple examples of Autoencoders', 2, None, '___sec1')]}
end of tocinfo -->
<body>
@@ -64,6 +65,7 @@ end of tocinfo -->
<a href="#" class="dropdown-toggle" data-toggle="dropdown">Contents <b class="caret"></b></a>
<ul class="dropdown-menu">
<!-- navigation toc: --> <li><a href="._Autoencoders-bs001.html#___sec0" style="font-size: 80%;">Autoencoders: Overarching view</a></li>
<!-- navigation toc: --> <li><a href="._Autoencoders-bs002.html#___sec1" style="font-size: 80%;">Simple examples of Autoencoders</a></li>
</ul>
</li>
@@ -98,7 +100,7 @@ end of tocinfo -->
<center>[2] <b>Department of Physics and Astronomy and National Superconducting Cyclotron Laboratory, Michigan State University</b></center>
<br>
<p>
<center><h4>Dec 30, 2018</h4></center> <!-- date -->
<center><h4>Jan 1, 2019</h4></center> <!-- date -->
<br>
<p>
@@ -113,6 +115,7 @@ end of tocinfo -->
<ul class="pagination">
<li class="active"><a href="._Autoencoders-bs000.html">1</a></li>
<li><a href="._Autoencoders-bs001.html">2</a></li>
<li><a href="._Autoencoders-bs002.html">3</a></li>
<li><a href="._Autoencoders-bs001.html">&raquo;</a></li>
</ul>
<!-- ------------------- end of main content --------------- -->
@@ -130,7 +133,7 @@ end of tocinfo -->
<center style="font-size:80%">
<!-- copyright --> &copy; 1999-2018, Morten Hjorth-Jensen. Released under CC Attribution-NonCommercial 4.0 license
<!-- copyright --> &copy; 1999-2019, Morten Hjorth-Jensen. Released under CC Attribution-NonCommercial 4.0 license
</center>
doc/pub/Autoencoders/html/._Autoencoders-bs001.html
+7 -2
View File
@@ -41,7 +41,8 @@ Automatically generated HTML file from DocOnce source
<!-- tocinfo
{'highest level': 2,
'sections': [('Autoencoders: Overarching view', 2, None, '___sec0')]}
'sections': [('Autoencoders: Overarching view', 2, None, '___sec0'),
('Simple examples of Autoencoders', 2, None, '___sec1')]}
end of tocinfo -->
<body>
@@ -64,6 +65,7 @@ end of tocinfo -->
<a href="#" class="dropdown-toggle" data-toggle="dropdown">Contents <b class="caret"></b></a>
<ul class="dropdown-menu">
<!-- navigation toc: --> <li><a href="#___sec0" style="font-size: 80%;">Autoencoders: Overarching view</a></li>
<!-- navigation toc: --> <li><a href="._Autoencoders-bs002.html#___sec1" style="font-size: 80%;">Simple examples of Autoencoders</a></li>
</ul>
</li>
@@ -83,7 +85,7 @@ end of tocinfo -->
<p>
Autoencoders are artificial neural networks capable of learning
efficient representations of the input data, called codings, without
efficient representations of the input data (these representations are called codings) without
any supervision (i.e., the training set is unlabeled). These codings
typically have a much lower dimensionality than the input data, making
autoencoders useful for dimensionality reduction.
@@ -108,12 +110,15 @@ which forces it to learn efficient ways of representing the data. In
short, the codings are byproducts of the autoencoder&#8217;s attempt to
learn the identity function under some constraints.
<p>
<p>
<!-- navigation buttons at the bottom of the page -->
<ul class="pagination">
<li><a href="._Autoencoders-bs000.html">&laquo;</a></li>
<li><a href="._Autoencoders-bs000.html">1</a></li>
<li class="active"><a href="._Autoencoders-bs001.html">2</a></li>
<li><a href="._Autoencoders-bs002.html">3</a></li>
<li><a href="._Autoencoders-bs002.html">&raquo;</a></li>
</ul>
<!-- ------------------- end of main content --------------- -->
doc/pub/Autoencoders/html/Autoencoders-bs.html
+6 -3
View File
@@ -41,7 +41,8 @@ Automatically generated HTML file from DocOnce source
<!-- tocinfo
{'highest level': 2,
'sections': [('Autoencoders: Overarching view', 2, None, '___sec0')]}
'sections': [('Autoencoders: Overarching view', 2, None, '___sec0'),
('Simple examples of Autoencoders', 2, None, '___sec1')]}
end of tocinfo -->
<body>
@@ -64,6 +65,7 @@ end of tocinfo -->
<a href="#" class="dropdown-toggle" data-toggle="dropdown">Contents <b class="caret"></b></a>
<ul class="dropdown-menu">
<!-- navigation toc: --> <li><a href="._Autoencoders-bs001.html#___sec0" style="font-size: 80%;">Autoencoders: Overarching view</a></li>
<!-- navigation toc: --> <li><a href="._Autoencoders-bs002.html#___sec1" style="font-size: 80%;">Simple examples of Autoencoders</a></li>
</ul>
</li>
@@ -98,7 +100,7 @@ end of tocinfo -->
<center>[2] <b>Department of Physics and Astronomy and National Superconducting Cyclotron Laboratory, Michigan State University</b></center>
<br>
<p>
<center><h4>Dec 30, 2018</h4></center> <!-- date -->
<center><h4>Jan 1, 2019</h4></center> <!-- date -->
<br>
<p>
@@ -113,6 +115,7 @@ end of tocinfo -->
<ul class="pagination">
<li class="active"><a href="._Autoencoders-bs000.html">1</a></li>
<li><a href="._Autoencoders-bs001.html">2</a></li>
<li><a href="._Autoencoders-bs002.html">3</a></li>
<li><a href="._Autoencoders-bs001.html">&raquo;</a></li>
</ul>
<!-- ------------------- end of main content --------------- -->
@@ -130,7 +133,7 @@ end of tocinfo -->
<center style="font-size:80%">
<!-- copyright --> &copy; 1999-2018, Morten Hjorth-Jensen. Released under CC Attribution-NonCommercial 4.0 license
<!-- copyright --> &copy; 1999-2019, Morten Hjorth-Jensen. Released under CC Attribution-NonCommercial 4.0 license
</center>
doc/pub/Autoencoders/html/Autoencoders-reveal.html
+8 -3
View File
@@ -132,12 +132,12 @@ td.padding {
<center>[2] <b>Department of Physics and Astronomy and National Superconducting Cyclotron Laboratory, Michigan State University</b></center>
<br>
<p>&nbsp;<br>
<center><h4>Dec 30, 2018</h4></center> <!-- date -->
<center><h4>Jan 1, 2019</h4></center> <!-- date -->
<br>
<p>
<center style="font-size:80%">
<!-- copyright --> &copy; 1999-2018, Morten Hjorth-Jensen. Released under CC Attribution-NonCommercial 4.0 license
<!-- copyright --> &copy; 1999-2019, Morten Hjorth-Jensen. Released under CC Attribution-NonCommercial 4.0 license
</center>
</section>
@@ -147,7 +147,7 @@ td.padding {
<p>
Autoencoders are artificial neural networks capable of learning
efficient representations of the input data, called codings, without
efficient representations of the input data (these representations are called codings) without
any supervision (i.e., the training set is unlabeled). These codings
typically have a much lower dimensionality than the input data, making
autoencoders useful for dimensionality reduction.
@@ -174,6 +174,11 @@ learn the identity function under some constraints.
</section>
<section>
<h2 id="___sec1">Simple examples of Autoencoders </h2>
</section>
</div> <!-- class="slides" -->
</div> <!-- class="reveal" -->
doc/pub/Autoencoders/html/Autoencoders-solarized.html
+10 -4
View File
@@ -35,7 +35,8 @@ div { text-align: justify; text-justify: inter-word; }
<!-- tocinfo
{'highest level': 2,
'sections': [('Autoencoders: Overarching view', 2, None, '___sec0')]}
'sections': [('Autoencoders: Overarching view', 2, None, '___sec0'),
('Simple examples of Autoencoders', 2, None, '___sec1')]}
end of tocinfo -->
<body>
@@ -61,7 +62,7 @@ end of tocinfo -->
<center>[2] <b>Department of Physics and Astronomy and National Superconducting Cyclotron Laboratory, Michigan State University</b></center>
<br>
<p>
<center><h4>Dec 30, 2018</h4></center> <!-- date -->
<center><h4>Jan 1, 2019</h4></center> <!-- date -->
<br>
<p>
<!-- !split --><br><br><br><br><br><br><br><br><br><br>
@@ -70,7 +71,7 @@ end of tocinfo -->
<p>
Autoencoders are artificial neural networks capable of learning
efficient representations of the input data, called codings, without
efficient representations of the input data (these representations are called codings) without
any supervision (i.e., the training set is unlabeled). These codings
typically have a much lower dimensionality than the input data, making
autoencoders useful for dimensionality reduction.
@@ -95,11 +96,16 @@ which forces it to learn efficient ways of representing the data. In
short, the codings are byproducts of the autoencoder&#8217;s attempt to
learn the identity function under some constraints.
<p>
<!-- !split --><br><br><br><br><br><br><br><br><br><br>
<h2 id="___sec1">Simple examples of Autoencoders </h2>
<!-- ------------------- end of main content --------------- -->
<center style="font-size:80%">
<!-- copyright --> &copy; 1999-2018, Morten Hjorth-Jensen. Released under CC Attribution-NonCommercial 4.0 license
<!-- copyright --> &copy; 1999-2019, Morten Hjorth-Jensen. Released under CC Attribution-NonCommercial 4.0 license
</center>
doc/pub/Autoencoders/html/Autoencoders.html
+10 -4
View File
@@ -40,7 +40,8 @@ div { text-align: justify; text-justify: inter-word; }
<!-- tocinfo
{'highest level': 2,
'sections': [('Autoencoders: Overarching view', 2, None, '___sec0')]}
'sections': [('Autoencoders: Overarching view', 2, None, '___sec0'),
('Simple examples of Autoencoders', 2, None, '___sec1')]}
end of tocinfo -->
<body>
@@ -66,7 +67,7 @@ end of tocinfo -->
<center>[2] <b>Department of Physics and Astronomy and National Superconducting Cyclotron Laboratory, Michigan State University</b></center>
<br>
<p>
<center><h4>Dec 30, 2018</h4></center> <!-- date -->
<center><h4>Jan 1, 2019</h4></center> <!-- date -->
<br>
<p>
<!-- !split --><br><br><br><br><br><br><br><br><br><br>
@@ -75,7 +76,7 @@ end of tocinfo -->
<p>
Autoencoders are artificial neural networks capable of learning
efficient representations of the input data, called codings, without
efficient representations of the input data (these representations are called codings) without
any supervision (i.e., the training set is unlabeled). These codings
typically have a much lower dimensionality than the input data, making
autoencoders useful for dimensionality reduction.
@@ -100,11 +101,16 @@ which forces it to learn efficient ways of representing the data. In
short, the codings are byproducts of the autoencoder&#8217;s attempt to
learn the identity function under some constraints.
<p>
<!-- !split --><br><br><br><br><br><br><br><br><br><br>
<h2 id="___sec1">Simple examples of Autoencoders </h2>
<!-- ------------------- end of main content --------------- -->
<center style="font-size:80%">
<!-- copyright --> &copy; 1999-2018, Morten Hjorth-Jensen. Released under CC Attribution-NonCommercial 4.0 license
<!-- copyright --> &copy; 1999-2019, Morten Hjorth-Jensen. Released under CC Attribution-NonCommercial 4.0 license
</center>
doc/pub/Autoencoders/ipynb/Autoencoders.ipynb
+6 -4
View File
@@ -10,9 +10,9 @@
"<!-- Author: --> \n",
"**Morten Hjorth-Jensen**, Department of Physics, University of Oslo and Department of Physics and Astronomy and National Superconducting Cyclotron Laboratory, Michigan State University\n",
"\n",
"Date: **Dec 30, 2018**\n",
"Date: **Jan 1, 2019**\n",
"\n",
"Copyright 1999-2018, Morten Hjorth-Jensen. Released under CC Attribution-NonCommercial 4.0 license\n",
"Copyright 1999-2019, Morten Hjorth-Jensen. Released under CC Attribution-NonCommercial 4.0 license\n",
"\n",
"\n",
"\n",
@@ -20,7 +20,7 @@
"## Autoencoders: Overarching view\n",
"\n",
"Autoencoders are artificial neural networks capable of learning\n",
"efficient representations of the input data, called codings, without\n",
"efficient representations of the input data (these representations are called codings) without\n",
"any supervision (i.e., the training set is unlabeled). These codings\n",
"typically have a much lower dimensionality than the input data, making\n",
"autoencoders useful for dimensionality reduction. \n",
@@ -41,7 +41,9 @@
"autoencoder from trivially copying the inputs directly to the outputs,\n",
"which forces it to learn efficient ways of representing the data. In\n",
"short, the codings are byproducts of the autoencoder’s attempt to\n",
"learn the identity function under some constraints."
"learn the identity function under some constraints.\n",
"\n",
"## Simple examples of Autoencoders"
]
}
],
doc/pub/Autoencoders/ipynb/ipynb-Autoencoders-src.tar.gz
BIN
View File
Binary file not shown.
doc/pub/Autoencoders/pdf/Autoencoders-minted.pdf
BIN
View File
Binary file not shown.
doc/src/Autoencoders/Autoencoders.do.txt
+4 -1
View File
@@ -7,7 +7,7 @@ DATE: today
===== Autoencoders: Overarching view =====
Autoencoders are artificial neural networks capable of learning
efficient representations of the input data, called codings, without
efficient representations of the input data (these representations are called codings) without
any supervision (i.e., the training set is unlabeled). These codings
typically have a much lower dimensionality than the input data, making
autoencoders useful for dimensionality reduction.
@@ -29,3 +29,6 @@ autoencoder from trivially copying the inputs directly to the outputs,
which forces it to learn efficient ways of representing the data. In
short, the codings are byproducts of the autoencoder’s attempt to
learn the identity function under some constraints.
!split
===== Simple examples of Autoencoders =====