update on Boltzmann machines
This commit is contained in:
mhjensen
+22
-19
@@ -40,8 +40,8 @@ Automatically generated HTML file from DocOnce source
|
||||
|
||||
<!-- tocinfo
|
||||
{'highest level': 2,
|
||||
'sections': [('Unsupervised learning, ovrarching aims', 2, None, '___sec0'),
|
||||
('Types of Machine Learning', 2, None, '___sec1'),
|
||||
'sections': [('Types of Machine Learning, a repetition', 2, None, '___sec0'),
|
||||
('Why Boltzmann machines?', 2, None, '___sec1'),
|
||||
('Boltzmann Machines', 2, None, '___sec2'),
|
||||
('Some similarities and differences from DNNs',
|
||||
2,
|
||||
@@ -115,8 +115,8 @@ MathJax.Hub.Config({
|
||||
<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="#___sec0" style="font-size: 80%;">Unsupervised learning, ovrarching aims</a></li>
|
||||
<!-- navigation toc: --> <li><a href="#___sec1" style="font-size: 80%;">Types of Machine Learning</a></li>
|
||||
<!-- navigation toc: --> <li><a href="#___sec0" style="font-size: 80%;">Types of Machine Learning, a repetition</a></li>
|
||||
<!-- navigation toc: --> <li><a href="#___sec1" style="font-size: 80%;">Why Boltzmann machines?</a></li>
|
||||
<!-- navigation toc: --> <li><a href="#___sec2" style="font-size: 80%;">Boltzmann Machines</a></li>
|
||||
<!-- navigation toc: --> <li><a href="#___sec3" style="font-size: 80%;">Some similarities and differences from DNNs</a></li>
|
||||
<!-- navigation toc: --> <li><a href="#___sec4" style="font-size: 80%;">The structure of the RBM network</a></li>
|
||||
@@ -173,7 +173,7 @@ MathJax.Hub.Config({
|
||||
<center><b>Department of Physics and Astronomy and National Superconducting Cyclotron Laboratory, Michigan State University and Department of Physics, University of Oslo, Norway</b></center>
|
||||
<br>
|
||||
<p>
|
||||
<center><h4>Nov 19, 2018 </h4></center> <!-- date -->
|
||||
<center><h4>Nov 20, 2018 </h4></center> <!-- date -->
|
||||
<br>
|
||||
<p>
|
||||
<!-- potential-jumbotron-button -->
|
||||
@@ -181,20 +181,7 @@ MathJax.Hub.Config({
|
||||
|
||||
<!-- !split -->
|
||||
|
||||
<h2 id="___sec0" class="anchor">Unsupervised learning, ovrarching aims </h2>
|
||||
<div class="panel panel-default">
|
||||
<div class="panel-body">
|
||||
<p> <!-- subsequent paragraphs come in larger fonts, so start with a paragraph -->
|
||||
|
||||
<p>
|
||||
</div>
|
||||
</div>
|
||||
|
||||
|
||||
<p>
|
||||
<!-- !split -->
|
||||
|
||||
<h2 id="___sec1" class="anchor">Types of Machine Learning </h2>
|
||||
<h2 id="___sec0" class="anchor">Types of Machine Learning, a repetition </h2>
|
||||
|
||||
<p>
|
||||
<div class="panel panel-default">
|
||||
@@ -216,11 +203,27 @@ Some of the most common tasks are:
|
||||
<li> Classification: Outputs are divided into two or more classes. The goal is to produce a model that assigns inputs into one of these classes. An example is to identify digits based on pictures of hand-written ones. Classification is typically supervised learning.</li>
|
||||
<li> Regression: Finding a functional relationship between an input data set and a reference data set. The goal is to construct a function that maps input data to continuous output values.</li>
|
||||
<li> Clustering: Data are divided into groups with certain common traits, without knowing the different groups beforehand. It is thus a form of unsupervised learning.</li>
|
||||
<li> Other unsupervised learning algortihms, here Boltzmann machines</li>
|
||||
</ul>
|
||||
</div>
|
||||
</div>
|
||||
|
||||
|
||||
<p>
|
||||
<!-- !split -->
|
||||
|
||||
<h2 id="___sec1" class="anchor">Why Boltzmann machines? </h2>
|
||||
|
||||
<p>
|
||||
What is known as restricted Boltzmann Machines (RMB) have received a lot of attention lately.
|
||||
One of the major reasons is that they can be stacked layer-wise to build deep neural networks that capture complicated statistics.
|
||||
|
||||
<p>
|
||||
The original RBMs had just one visible layer and a hidden layer, but recently so-called Gaussian-binary RBMs have gained quite some popularity in imaging since they are capable of modeling continuous data that are common to natural images.
|
||||
|
||||
<p>
|
||||
Furthermore, they have been used to solve complicated quantum mechanical many-particle problems or classical statistical physics problems like the Ising and Potts classes of models.
|
||||
|
||||
<p>
|
||||
<!-- !split -->
|
||||
|
||||
|
||||
@@ -147,7 +147,7 @@ MathJax.Hub.Config({
|
||||
<center><b>Department of Physics and Astronomy and National Superconducting Cyclotron Laboratory, Michigan State University and Department of Physics, University of Oslo, Norway</b></center>
|
||||
<br>
|
||||
<p> <br>
|
||||
<center><h4>Nov 19, 2018 </h4></center> <!-- date -->
|
||||
<center><h4>Nov 20, 2018 </h4></center> <!-- date -->
|
||||
<br>
|
||||
<p>
|
||||
|
||||
@@ -158,16 +158,7 @@ MathJax.Hub.Config({
|
||||
|
||||
|
||||
<section>
|
||||
<h2 id="___sec0">Unsupervised learning, ovrarching aims </h2>
|
||||
<div class="alert alert-block alert-block alert-text-normal">
|
||||
<b></b>
|
||||
<p>
|
||||
</div>
|
||||
</section>
|
||||
|
||||
|
||||
<section>
|
||||
<h2 id="___sec1">Types of Machine Learning </h2>
|
||||
<h2 id="___sec0">Types of Machine Learning, a repetition </h2>
|
||||
|
||||
<p>
|
||||
<div class="alert alert-block alert-block alert-text-normal">
|
||||
@@ -192,11 +183,28 @@ Some of the most common tasks are:
|
||||
<p><li> Regression: Finding a functional relationship between an input data set and a reference data set. The goal is to construct a function that maps input data to continuous output values.</li>
|
||||
|
||||
<p><li> Clustering: Data are divided into groups with certain common traits, without knowing the different groups beforehand. It is thus a form of unsupervised learning.</li>
|
||||
|
||||
<p><li> Other unsupervised learning algortihms, here Boltzmann machines</li>
|
||||
</ul>
|
||||
</div>
|
||||
</section>
|
||||
|
||||
|
||||
<section>
|
||||
<h2 id="___sec1">Why Boltzmann machines? </h2>
|
||||
|
||||
<p>
|
||||
What is known as restricted Boltzmann Machines (RMB) have received a lot of attention lately.
|
||||
One of the major reasons is that they can be stacked layer-wise to build deep neural networks that capture complicated statistics.
|
||||
|
||||
<p>
|
||||
The original RBMs had just one visible layer and a hidden layer, but recently so-called Gaussian-binary RBMs have gained quite some popularity in imaging since they are capable of modeling continuous data that are common to natural images.
|
||||
|
||||
<p>
|
||||
Furthermore, they have been used to solve complicated quantum mechanical many-particle problems or classical statistical physics problems like the Ising and Potts classes of models.
|
||||
</section>
|
||||
|
||||
|
||||
<section>
|
||||
<h2 id="___sec2">Boltzmann Machines </h2>
|
||||
|
||||
|
||||
@@ -60,8 +60,8 @@ div { text-align: justify; text-justify: inter-word; }
|
||||
|
||||
<!-- tocinfo
|
||||
{'highest level': 2,
|
||||
'sections': [('Unsupervised learning, ovrarching aims', 2, None, '___sec0'),
|
||||
('Types of Machine Learning', 2, None, '___sec1'),
|
||||
'sections': [('Types of Machine Learning, a repetition', 2, None, '___sec0'),
|
||||
('Why Boltzmann machines?', 2, None, '___sec1'),
|
||||
('Boltzmann Machines', 2, None, '___sec2'),
|
||||
('Some similarities and differences from DNNs',
|
||||
2,
|
||||
@@ -138,24 +138,12 @@ MathJax.Hub.Config({
|
||||
<center><b>Department of Physics and Astronomy and National Superconducting Cyclotron Laboratory, Michigan State University and Department of Physics, University of Oslo, Norway</b></center>
|
||||
<br>
|
||||
<p>
|
||||
<center><h4>Nov 19, 2018 </h4></center> <!-- date -->
|
||||
<center><h4>Nov 20, 2018 </h4></center> <!-- date -->
|
||||
<br>
|
||||
<p>
|
||||
<!-- !split --><br><br><br><br><br><br><br><br><br><br>
|
||||
|
||||
<h2 id="___sec0">Unsupervised learning, ovrarching aims </h2>
|
||||
<div class="alert alert-block alert-block alert-text-normal">
|
||||
<b></b>
|
||||
<p>
|
||||
|
||||
|
||||
</div>
|
||||
|
||||
|
||||
<p>
|
||||
<!-- !split --><br><br><br><br><br><br><br><br><br><br>
|
||||
|
||||
<h2 id="___sec1">Types of Machine Learning </h2>
|
||||
<h2 id="___sec0">Types of Machine Learning, a repetition </h2>
|
||||
|
||||
<p>
|
||||
<div class="alert alert-block alert-block alert-text-normal">
|
||||
@@ -177,10 +165,26 @@ Some of the most common tasks are:
|
||||
<li> Classification: Outputs are divided into two or more classes. The goal is to produce a model that assigns inputs into one of these classes. An example is to identify digits based on pictures of hand-written ones. Classification is typically supervised learning.</li>
|
||||
<li> Regression: Finding a functional relationship between an input data set and a reference data set. The goal is to construct a function that maps input data to continuous output values.</li>
|
||||
<li> Clustering: Data are divided into groups with certain common traits, without knowing the different groups beforehand. It is thus a form of unsupervised learning.</li>
|
||||
<li> Other unsupervised learning algortihms, here Boltzmann machines</li>
|
||||
</ul>
|
||||
</div>
|
||||
|
||||
|
||||
<p>
|
||||
<!-- !split --><br><br><br><br><br><br><br><br><br><br>
|
||||
|
||||
<h2 id="___sec1">Why Boltzmann machines? </h2>
|
||||
|
||||
<p>
|
||||
What is known as restricted Boltzmann Machines (RMB) have received a lot of attention lately.
|
||||
One of the major reasons is that they can be stacked layer-wise to build deep neural networks that capture complicated statistics.
|
||||
|
||||
<p>
|
||||
The original RBMs had just one visible layer and a hidden layer, but recently so-called Gaussian-binary RBMs have gained quite some popularity in imaging since they are capable of modeling continuous data that are common to natural images.
|
||||
|
||||
<p>
|
||||
Furthermore, they have been used to solve complicated quantum mechanical many-particle problems or classical statistical physics problems like the Ising and Potts classes of models.
|
||||
|
||||
<p>
|
||||
<!-- !split --><br><br><br><br><br><br><br><br><br><br>
|
||||
|
||||
|
||||
+20
-16
@@ -65,8 +65,8 @@ div { text-align: justify; text-justify: inter-word; }
|
||||
|
||||
<!-- tocinfo
|
||||
{'highest level': 2,
|
||||
'sections': [('Unsupervised learning, ovrarching aims', 2, None, '___sec0'),
|
||||
('Types of Machine Learning', 2, None, '___sec1'),
|
||||
'sections': [('Types of Machine Learning, a repetition', 2, None, '___sec0'),
|
||||
('Why Boltzmann machines?', 2, None, '___sec1'),
|
||||
('Boltzmann Machines', 2, None, '___sec2'),
|
||||
('Some similarities and differences from DNNs',
|
||||
2,
|
||||
@@ -143,24 +143,12 @@ MathJax.Hub.Config({
|
||||
<center><b>Department of Physics and Astronomy and National Superconducting Cyclotron Laboratory, Michigan State University and Department of Physics, University of Oslo, Norway</b></center>
|
||||
<br>
|
||||
<p>
|
||||
<center><h4>Nov 19, 2018 </h4></center> <!-- date -->
|
||||
<center><h4>Nov 20, 2018 </h4></center> <!-- date -->
|
||||
<br>
|
||||
<p>
|
||||
<!-- !split --><br><br><br><br><br><br><br><br><br><br>
|
||||
|
||||
<h2 id="___sec0">Unsupervised learning, ovrarching aims </h2>
|
||||
<div class="alert alert-block alert-block alert-text-normal">
|
||||
<b></b>
|
||||
<p>
|
||||
|
||||
|
||||
</div>
|
||||
|
||||
|
||||
<p>
|
||||
<!-- !split --><br><br><br><br><br><br><br><br><br><br>
|
||||
|
||||
<h2 id="___sec1">Types of Machine Learning </h2>
|
||||
<h2 id="___sec0">Types of Machine Learning, a repetition </h2>
|
||||
|
||||
<p>
|
||||
<div class="alert alert-block alert-block alert-text-normal">
|
||||
@@ -182,10 +170,26 @@ Some of the most common tasks are:
|
||||
<li> Classification: Outputs are divided into two or more classes. The goal is to produce a model that assigns inputs into one of these classes. An example is to identify digits based on pictures of hand-written ones. Classification is typically supervised learning.</li>
|
||||
<li> Regression: Finding a functional relationship between an input data set and a reference data set. The goal is to construct a function that maps input data to continuous output values.</li>
|
||||
<li> Clustering: Data are divided into groups with certain common traits, without knowing the different groups beforehand. It is thus a form of unsupervised learning.</li>
|
||||
<li> Other unsupervised learning algortihms, here Boltzmann machines</li>
|
||||
</ul>
|
||||
</div>
|
||||
|
||||
|
||||
<p>
|
||||
<!-- !split --><br><br><br><br><br><br><br><br><br><br>
|
||||
|
||||
<h2 id="___sec1">Why Boltzmann machines? </h2>
|
||||
|
||||
<p>
|
||||
What is known as restricted Boltzmann Machines (RMB) have received a lot of attention lately.
|
||||
One of the major reasons is that they can be stacked layer-wise to build deep neural networks that capture complicated statistics.
|
||||
|
||||
<p>
|
||||
The original RBMs had just one visible layer and a hidden layer, but recently so-called Gaussian-binary RBMs have gained quite some popularity in imaging since they are capable of modeling continuous data that are common to natural images.
|
||||
|
||||
<p>
|
||||
Furthermore, they have been used to solve complicated quantum mechanical many-particle problems or classical statistical physics problems like the Ising and Potts classes of models.
|
||||
|
||||
<p>
|
||||
<!-- !split --><br><br><br><br><br><br><br><br><br><br>
|
||||
|
||||
|
||||
@@ -10,22 +10,15 @@
|
||||
"<!-- Author: --> \n",
|
||||
"**Morten Hjorth-Jensen**, Department of Physics and Astronomy and National Superconducting Cyclotron Laboratory, Michigan State University and Department of Physics, University of Oslo, Norway\n",
|
||||
"\n",
|
||||
"Date: **Nov 19, 2018**\n",
|
||||
"Date: **Nov 20, 2018**\n",
|
||||
"\n",
|
||||
"Copyright 1999-2018, Morten Hjorth-Jensen. Released under CC Attribution-NonCommercial 4.0 license\n",
|
||||
"\n",
|
||||
" \n",
|
||||
"\n",
|
||||
"\n",
|
||||
"## Unsupervised learning, ovrarching aims\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"## Types of Machine Learning\n",
|
||||
"## Types of Machine Learning, a repetition\n",
|
||||
"\n",
|
||||
"The approaches to machine learning are many, but are often split into two main categories. \n",
|
||||
"In *supervised learning* we know the answer to a problem,\n",
|
||||
@@ -44,10 +37,21 @@
|
||||
"\n",
|
||||
" * Clustering: Data are divided into groups with certain common traits, without knowing the different groups beforehand. It is thus a form of unsupervised learning.\n",
|
||||
"\n",
|
||||
" * Other unsupervised learning algortihms, here Boltzmann machines\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"## Why Boltzmann machines?\n",
|
||||
"\n",
|
||||
"What is known as restricted Boltzmann Machines (RMB) have received a lot of attention lately. \n",
|
||||
"One of the major reasons is that they can be stacked layer-wise to build deep neural networks that capture complicated statistics.\n",
|
||||
"\n",
|
||||
"The original RBMs had just one visible layer and a hidden layer, but recently so-called Gaussian-binary RBMs have gained quite some popularity in imaging since they are capable of modeling continuous data that are common to natural images. \n",
|
||||
"\n",
|
||||
"Furthermore, they have been used to solve complicated quantum mechanical many-particle problems or classical statistical physics problems like the Ising and Potts classes of models. \n",
|
||||
"\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"## Boltzmann Machines\n",
|
||||
|
||||
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
@@ -3,17 +3,9 @@ AUTHOR: Morten Hjorth-Jensen {copyright, 1999-present|CC BY-NC} at Department of
|
||||
DATE: today
|
||||
|
||||
|
||||
!split
|
||||
===== Unsupervised learning, ovrarching aims =====
|
||||
!bblock
|
||||
|
||||
|
||||
!eblock
|
||||
|
||||
|
||||
|
||||
!split
|
||||
===== Types of Machine Learning =====
|
||||
===== Types of Machine Learning, a repetition =====
|
||||
|
||||
!bblock
|
||||
The approaches to machine learning are many, but are often split into two main categories.
|
||||
@@ -32,10 +24,22 @@ Some of the most common tasks are:
|
||||
* Regression: Finding a functional relationship between an input data set and a reference data set. The goal is to construct a function that maps input data to continuous output values.
|
||||
|
||||
* Clustering: Data are divided into groups with certain common traits, without knowing the different groups beforehand. It is thus a form of unsupervised learning.
|
||||
|
||||
* Other unsupervised learning algortihms, here Boltzmann machines
|
||||
!eblock
|
||||
|
||||
|
||||
!split
|
||||
===== Why Boltzmann machines? =====
|
||||
|
||||
What is known as restricted Boltzmann Machines (RMB) have received a lot of attention lately.
|
||||
One of the major reasons is that they can be stacked layer-wise to build deep neural networks that capture complicated statistics.
|
||||
|
||||
The original RBMs had just one visible layer and a hidden layer, but recently so-called Gaussian-binary RBMs have gained quite some popularity in imaging since they are capable of modeling continuous data that are common to natural images.
|
||||
|
||||
Furthermore, they have been used to solve complicated quantum mechanical many-particle problems or classical statistical physics problems like the Ising and Potts classes of models.
|
||||
|
||||
|
||||
|
||||
|
||||
!split
|
||||
|
||||
Reference in New Issue
Block a user