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

added thesis

Browse Source
This commit is contained in:
Morten Hjorth-Jensen
2022-10-21 07:08:34 +02:00
parent 55d8ebdf15
commit 48dd6045bb
12 changed files with 338 additions and 288 deletions
Download Patch File Download Diff File Expand all files Collapse all files
doc/pub/week42/html/._week42-bs000.html
+1 -1
View File
@@ -422,7 +422,7 @@ MathJax.Hub.Config({
</center>
<br>
<center>
<h4>Oct 20, 2022</h4>
<h4>Oct 21, 2022</h4>
</center> <!-- date -->
<br>
doc/pub/week42/html/._week42-bs001.html
+1
View File
@@ -435,6 +435,7 @@ MathJax.Hub.Config({
</div>
</div>
<p>m</p>
<div class="panel panel-default">
<div class="panel-body">
doc/pub/week42/html/._week42-bs002.html
+3 -2
View File
@@ -405,9 +405,10 @@ MathJax.Hub.Config({
<a name="part0002"></a>
<!-- !split -->
<h2 id="using-automatic-differentiation" class="anchor">Using Automatic differentiation </h2>
<p>In our discussions of ordinary differential equations
<p>a
In our discussions of ordinary differential equations
we will also study the usage of <a href="https://www.youtube.com/watch?v=fRf4l5qaX1M&ab_channel=AlexSmola" target="_self">Autograd</a> in computing gradients for deep learning. For the documentation of Autograd and examples see the lectures slides from <a href="https://compphysics.github.io/MachineLearning/doc/pub/week39/html/week39.html" target="_self">week 39</a> and the <a href="https://github.com/HIPS/autograd" target="_self">Autograd documentation</a>.
t
</p>
<p>
doc/pub/week42/html/._week42-bs004.html
+8
View File
@@ -425,6 +425,14 @@ and output layer to any given precision.
</div>
<div class="panel panel-default">
<div class="panel-body">
<!-- subsequent paragraphs come in larger fonts, so start with a paragraph -->
<p><a href="https://www.duo.uio.no/handle/10852/79212" target="_self">Using Deep Reinforcement Learning for Active Flow Control</a>, by Marius Holm</p>
</div>
</div>
<div class="panel panel-default">
<div class="panel-body">
<!-- subsequent paragraphs come in larger fonts, so start with a paragraph -->
doc/pub/week42/html/._week42-bs062.html
+1 -1
View File
@@ -408,7 +408,7 @@ MathJax.Hub.Config({
<p>The mathematics of CNNs is based on the mathematical operation of
<b>convolution</b>. In mathematics (in particular in functional analysis),
convolution is represented by matheematical operation (integration,
convolution is represented by mathematical operation (integration,
summation etc) on two function in order to produce a third function
that expresses how the shape of one gets modified by the other.
Convolution has a plethora of applications in a variety of disciplines, spanning from statistics to signal processing, computer vision, solutions of differential equations,linear algebra, engineering, and yes, machine learning.
doc/pub/week42/html/week42-bs.html
+1 -1
View File
@@ -422,7 +422,7 @@ MathJax.Hub.Config({
</center>
<br>
<center>
<h4>Oct 20, 2022</h4>
<h4>Oct 21, 2022</h4>
</center> <!-- date -->
<br>
doc/pub/week42/html/week42-reveal.html
+13 -4
View File
@@ -184,7 +184,7 @@ MathJax.Hub.Config({
</center>
<br>
<center>
<h4>Oct 20, 2022</h4>
<h4>Oct 21, 2022</h4>
</center> <!-- date -->
<br>
@@ -225,6 +225,7 @@ MathJax.Hub.Config({
</ul>
</div>
<p>m</p>
<div class="alert alert-block alert-block alert-text-normal">
<b>And Lecture material on CNNs</b>
@@ -239,9 +240,10 @@ MathJax.Hub.Config({
<section>
<h2 id="using-automatic-differentiation">Using Automatic differentiation </h2>
<p>In our discussions of ordinary differential equations
<p>a
In our discussions of ordinary differential equations
we will also study the usage of <a href="https://www.youtube.com/watch?v=fRf4l5qaX1M&ab_channel=AlexSmola" target="_blank">Autograd</a> in computing gradients for deep learning. For the documentation of Autograd and examples see the lectures slides from <a href="https://compphysics.github.io/MachineLearning/doc/pub/week39/html/week39.html" target="_blank">week 39</a> and the <a href="https://github.com/HIPS/autograd" target="_blank">Autograd documentation</a>.
t
</p>
</section>
@@ -276,6 +278,13 @@ and output layer to any given precision.
</div>
<div class="alert alert-block alert-block alert-text-normal">
<b>Master thesis on applying deep learning to problems in mechanics</b>
<p>
<p><a href="https://www.duo.uio.no/handle/10852/79212" target="_blank">Using Deep Reinforcement Learning for Active Flow Control</a>, by Marius Holm</p>
</div>
<div class="alert alert-block alert-block alert-text-normal">
<b>Thanks to Kristine Baluka Hein</b>
<p>
@@ -3291,7 +3300,7 @@ only neighboring neurons in the input instead of connecting all with the first h
<p>The mathematics of CNNs is based on the mathematical operation of
<b>convolution</b>. In mathematics (in particular in functional analysis),
convolution is represented by matheematical operation (integration,
convolution is represented by mathematical operation (integration,
summation etc) on two function in order to produce a third function
that expresses how the shape of one gets modified by the other.
Convolution has a plethora of applications in a variety of disciplines, spanning from statistics to signal processing, computer vision, solutions of differential equations,linear algebra, engineering, and yes, machine learning.
doc/pub/week42/html/week42-solarized.html
+13 -4
View File
@@ -330,7 +330,7 @@ MathJax.Hub.Config({
</center>
<br>
<center>
<h4>Oct 20, 2022</h4>
<h4>Oct 21, 2022</h4>
</center> <!-- date -->
<br>
@@ -364,6 +364,7 @@ MathJax.Hub.Config({
</ul>
</div>
<p>m</p>
<div class="alert alert-block alert-block alert-text-normal">
<b>And Lecture material on CNNs</b>
@@ -378,9 +379,10 @@ MathJax.Hub.Config({
<!-- !split --><br><br><br><br><br><br><br><br><br><br>
<h2 id="using-automatic-differentiation">Using Automatic differentiation </h2>
<p>In our discussions of ordinary differential equations
<p>a
In our discussions of ordinary differential equations
we will also study the usage of <a href="https://www.youtube.com/watch?v=fRf4l5qaX1M&ab_channel=AlexSmola" target="_blank">Autograd</a> in computing gradients for deep learning. For the documentation of Autograd and examples see the lectures slides from <a href="https://compphysics.github.io/MachineLearning/doc/pub/week39/html/week39.html" target="_blank">week 39</a> and the <a href="https://github.com/HIPS/autograd" target="_blank">Autograd documentation</a>.
t
</p>
<!-- !split --><br><br><br><br><br><br><br><br><br><br>
@@ -412,6 +414,13 @@ and output layer to any given precision.
</div>
<div class="alert alert-block alert-block alert-text-normal">
<b>Master thesis on applying deep learning to problems in mechanics</b>
<p>
<p><a href="https://www.duo.uio.no/handle/10852/79212" target="_blank">Using Deep Reinforcement Learning for Active Flow Control</a>, by Marius Holm</p>
</div>
<div class="alert alert-block alert-block alert-text-normal">
<b>Thanks to Kristine Baluka Hein</b>
<p>
@@ -3256,7 +3265,7 @@ only neighboring neurons in the input instead of connecting all with the first h
<p>The mathematics of CNNs is based on the mathematical operation of
<b>convolution</b>. In mathematics (in particular in functional analysis),
convolution is represented by matheematical operation (integration,
convolution is represented by mathematical operation (integration,
summation etc) on two function in order to produce a third function
that expresses how the shape of one gets modified by the other.
Convolution has a plethora of applications in a variety of disciplines, spanning from statistics to signal processing, computer vision, solutions of differential equations,linear algebra, engineering, and yes, machine learning.
doc/pub/week42/html/week42.html
+13 -4
View File
@@ -407,7 +407,7 @@ MathJax.Hub.Config({
</center>
<br>
<center>
<h4>Oct 20, 2022</h4>
<h4>Oct 21, 2022</h4>
</center> <!-- date -->
<br>
@@ -441,6 +441,7 @@ MathJax.Hub.Config({
</ul>
</div>
<p>m</p>
<div class="alert alert-block alert-block alert-text-normal">
<b>And Lecture material on CNNs</b>
@@ -455,9 +456,10 @@ MathJax.Hub.Config({
<!-- !split --><br><br><br><br><br><br><br><br><br><br>
<h2 id="using-automatic-differentiation">Using Automatic differentiation </h2>
<p>In our discussions of ordinary differential equations
<p>a
In our discussions of ordinary differential equations
we will also study the usage of <a href="https://www.youtube.com/watch?v=fRf4l5qaX1M&ab_channel=AlexSmola" target="_blank">Autograd</a> in computing gradients for deep learning. For the documentation of Autograd and examples see the lectures slides from <a href="https://compphysics.github.io/MachineLearning/doc/pub/week39/html/week39.html" target="_blank">week 39</a> and the <a href="https://github.com/HIPS/autograd" target="_blank">Autograd documentation</a>.
t
</p>
<!-- !split --><br><br><br><br><br><br><br><br><br><br>
@@ -489,6 +491,13 @@ and output layer to any given precision.
</div>
<div class="alert alert-block alert-block alert-text-normal">
<b>Master thesis on applying deep learning to problems in mechanics</b>
<p>
<p><a href="https://www.duo.uio.no/handle/10852/79212" target="_blank">Using Deep Reinforcement Learning for Active Flow Control</a>, by Marius Holm</p>
</div>
<div class="alert alert-block alert-block alert-text-normal">
<b>Thanks to Kristine Baluka Hein</b>
<p>
@@ -3333,7 +3342,7 @@ only neighboring neurons in the input instead of connecting all with the first h
<p>The mathematics of CNNs is based on the mathematical operation of
<b>convolution</b>. In mathematics (in particular in functional analysis),
convolution is represented by matheematical operation (integration,
convolution is represented by mathematical operation (integration,
summation etc) on two function in order to produce a third function
that expresses how the shape of one gets modified by the other.
Convolution has a plethora of applications in a variety of disciplines, spanning from statistics to signal processing, computer vision, solutions of differential equations,linear algebra, engineering, and yes, machine learning.
doc/pub/week42/ipynb/ipynb-week42-src.tar.gz
BIN
View File
Binary file not shown.
doc/pub/week42/ipynb/week42.ipynb
+274 -267
View File
File diff suppressed because it is too large Load Diff
doc/src/week42/week42.do.txt
+10 -4
View File
@@ -23,7 +23,7 @@ DATE: today
* "Video on Convolutional Neural Networks from MIT":"https://www.youtube.com/watch?v=iaSUYvmCekI&ab_channel=AlexanderAmini"
* "Video on CNNs from Stanford":"https://www.youtube.com/watch?v=bNb2fEVKeEo&list=PLC1qU-LWwrF64f4QKQT-Vg5Wr4qEE1Zxk&index=6&ab_channel=StanfordUniversitySchoolofEngineering"
!eblock
m
!bblock And Lecture material on CNNs
* "Lectures from IN5400 spring 2019":"https://www.uio.no/studier/emner/matnat/ifi/IN5400/v19/material/week5/in5400_2019_week5_convolutional_nerual_networks.pdf"
@@ -35,10 +35,10 @@ DATE: today
!split
===== Using Automatic differentiation =====
a
In our discussions of ordinary differential equations
we will also study the usage of "Autograd":"https://www.youtube.com/watch?v=fRf4l5qaX1M&ab_channel=AlexSmola" in computing gradients for deep learning. For the documentation of Autograd and examples see the lectures slides from "week 39":"https://compphysics.github.io/MachineLearning/doc/pub/week39/html/week39.html" and the "Autograd documentation":"https://github.com/HIPS/autograd".
t
!split
===== Back propagation and automatic differentiation =====
@@ -62,6 +62,12 @@ and output layer to any given precision.
"An Introduction to Neural Network Methods for Differential Equations":"https://www.springer.com/gp/book/9789401798150", by Yadav and Kumar.
!eblock
!bblock Master thesis on applying deep learning to problems in mechanics
"Using Deep Reinforcement Learning for Active Flow Control":"https://www.duo.uio.no/handle/10852/79212", by Marius Holm
!eblock
!bblock Thanks to Kristine Baluka Hein
The lectures on differential equations were developed by Kristine Baluka Hein, now PhD student at IFI.
A great thanks to Kristine.
@@ -2640,7 +2646,7 @@ We say we perform a filtering (convolution is the mathematical operation).
The mathematics of CNNs is based on the mathematical operation of
_convolution_. In mathematics (in particular in functional analysis),
convolution is represented by matheematical operation (integration,
convolution is represented by mathematical operation (integration,
summation etc) on two function in order to produce a third function
that expresses how the shape of one gets modified by the other.
Convolution has a plethora of applications in a variety of disciplines, spanning from statistics to signal processing, computer vision, solutions of differential equations,linear algebra, engineering, and yes, machine learning.