diff --git a/doc/pub/Autoencoders/html/._Autoencoders-bs000.html b/doc/pub/Autoencoders/html/._Autoencoders-bs000.html
index 8d89a8e9f..ada978097 100644
--- a/doc/pub/Autoencoders/html/._Autoencoders-bs000.html
+++ b/doc/pub/Autoencoders/html/._Autoencoders-bs000.html
@@ -41,7 +41,8 @@ Automatically generated HTML file from DocOnce source
@@ -64,6 +65,7 @@ end of tocinfo -->
Contents
@@ -98,7 +100,7 @@ end of tocinfo -->
[2] Department of Physics and Astronomy and National Superconducting Cyclotron Laboratory, Michigan State University
-
Dec 30, 2018
+Jan 1, 2019
@@ -113,6 +115,7 @@ end of tocinfo -->
@@ -130,7 +133,7 @@ end of tocinfo -->
- © 1999-2018, Morten Hjorth-Jensen. Released under CC Attribution-NonCommercial 4.0 license
+ © 1999-2019, Morten Hjorth-Jensen. Released under CC Attribution-NonCommercial 4.0 license
diff --git a/doc/pub/Autoencoders/html/._Autoencoders-bs001.html b/doc/pub/Autoencoders/html/._Autoencoders-bs001.html
index e481e674d..d749df1cd 100644
--- a/doc/pub/Autoencoders/html/._Autoencoders-bs001.html
+++ b/doc/pub/Autoencoders/html/._Autoencoders-bs001.html
@@ -41,7 +41,8 @@ Automatically generated HTML file from DocOnce source
@@ -64,6 +65,7 @@ end of tocinfo -->
Contents
@@ -83,7 +85,7 @@ end of tocinfo -->
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’s attempt to
learn the identity function under some constraints.
+
diff --git a/doc/pub/Autoencoders/html/Autoencoders-bs.html b/doc/pub/Autoencoders/html/Autoencoders-bs.html
index 8d89a8e9f..ada978097 100644
--- a/doc/pub/Autoencoders/html/Autoencoders-bs.html
+++ b/doc/pub/Autoencoders/html/Autoencoders-bs.html
@@ -41,7 +41,8 @@ Automatically generated HTML file from DocOnce source
@@ -64,6 +65,7 @@ end of tocinfo -->
Contents
@@ -98,7 +100,7 @@ end of tocinfo -->
[2] Department of Physics and Astronomy and National Superconducting Cyclotron Laboratory, Michigan State University
-
Dec 30, 2018
+Jan 1, 2019
@@ -113,6 +115,7 @@ end of tocinfo -->
@@ -130,7 +133,7 @@ end of tocinfo -->
- © 1999-2018, Morten Hjorth-Jensen. Released under CC Attribution-NonCommercial 4.0 license
+ © 1999-2019, Morten Hjorth-Jensen. Released under CC Attribution-NonCommercial 4.0 license
diff --git a/doc/pub/Autoencoders/html/Autoencoders-reveal.html b/doc/pub/Autoencoders/html/Autoencoders-reveal.html
index 01db054bd..7202bc563 100644
--- a/doc/pub/Autoencoders/html/Autoencoders-reveal.html
+++ b/doc/pub/Autoencoders/html/Autoencoders-reveal.html
@@ -132,12 +132,12 @@ td.padding {
[2] Department of Physics and Astronomy and National Superconducting Cyclotron Laboratory, Michigan State University
-
Dec 30, 2018
+Jan 1, 2019
- © 1999-2018, Morten Hjorth-Jensen. Released under CC Attribution-NonCommercial 4.0 license
+ © 1999-2019, Morten Hjorth-Jensen. Released under CC Attribution-NonCommercial 4.0 license
@@ -147,7 +147,7 @@ td.padding {
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.
+
+Simple examples of Autoencoders
+
+
+
diff --git a/doc/pub/Autoencoders/html/Autoencoders-solarized.html b/doc/pub/Autoencoders/html/Autoencoders-solarized.html
index c84e93a05..551f88771 100644
--- a/doc/pub/Autoencoders/html/Autoencoders-solarized.html
+++ b/doc/pub/Autoencoders/html/Autoencoders-solarized.html
@@ -35,7 +35,8 @@ div { text-align: justify; text-justify: inter-word; }
@@ -61,7 +62,7 @@ end of tocinfo -->
[2] Department of Physics and Astronomy and National Superconducting Cyclotron Laboratory, Michigan State University
-
Dec 30, 2018
+Jan 1, 2019
@@ -70,7 +71,7 @@ end of tocinfo -->
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’s attempt to
learn the identity function under some constraints.
+
+
+
+
Simple examples of Autoencoders
+
- © 1999-2018, Morten Hjorth-Jensen. Released under CC Attribution-NonCommercial 4.0 license
+ © 1999-2019, Morten Hjorth-Jensen. Released under CC Attribution-NonCommercial 4.0 license
diff --git a/doc/pub/Autoencoders/html/Autoencoders.html b/doc/pub/Autoencoders/html/Autoencoders.html
index b3c6e6443..85096d3ea 100644
--- a/doc/pub/Autoencoders/html/Autoencoders.html
+++ b/doc/pub/Autoencoders/html/Autoencoders.html
@@ -40,7 +40,8 @@ div { text-align: justify; text-justify: inter-word; }
@@ -66,7 +67,7 @@ end of tocinfo -->
[2] Department of Physics and Astronomy and National Superconducting Cyclotron Laboratory, Michigan State University
-
Dec 30, 2018
+Jan 1, 2019
@@ -75,7 +76,7 @@ end of tocinfo -->
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’s attempt to
learn the identity function under some constraints.
+
+
+
+
Simple examples of Autoencoders
+
- © 1999-2018, Morten Hjorth-Jensen. Released under CC Attribution-NonCommercial 4.0 license
+ © 1999-2019, Morten Hjorth-Jensen. Released under CC Attribution-NonCommercial 4.0 license
diff --git a/doc/pub/Autoencoders/ipynb/Autoencoders.ipynb b/doc/pub/Autoencoders/ipynb/Autoencoders.ipynb
index 42c657b91..4dadc277b 100644
--- a/doc/pub/Autoencoders/ipynb/Autoencoders.ipynb
+++ b/doc/pub/Autoencoders/ipynb/Autoencoders.ipynb
@@ -10,9 +10,9 @@
" \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"
]
}
],
diff --git a/doc/pub/Autoencoders/ipynb/ipynb-Autoencoders-src.tar.gz b/doc/pub/Autoencoders/ipynb/ipynb-Autoencoders-src.tar.gz
index 80a269725..aafb26640 100644
Binary files a/doc/pub/Autoencoders/ipynb/ipynb-Autoencoders-src.tar.gz and b/doc/pub/Autoencoders/ipynb/ipynb-Autoencoders-src.tar.gz differ
diff --git a/doc/pub/Autoencoders/pdf/Autoencoders-minted.pdf b/doc/pub/Autoencoders/pdf/Autoencoders-minted.pdf
index 044d5b264..1eefa4baa 100644
Binary files a/doc/pub/Autoencoders/pdf/Autoencoders-minted.pdf and b/doc/pub/Autoencoders/pdf/Autoencoders-minted.pdf differ
diff --git a/doc/src/Autoencoders/Autoencoders.do.txt b/doc/src/Autoencoders/Autoencoders.do.txt
index 969c0d5d1..c781fa987 100644
--- a/doc/src/Autoencoders/Autoencoders.do.txt
+++ b/doc/src/Autoencoders/Autoencoders.do.txt
@@ -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 =====