Skip to content

Commit 067f2cf

Browse files
committed
cnn part
1 parent 47e9247 commit 067f2cf

File tree

10 files changed

+1192
-308
lines changed

10 files changed

+1192
-308
lines changed
Lines changed: 181 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,181 @@
1+
<!--
2+
HTML file automatically generated from DocOnce source
3+
(https://github.com/doconce/doconce/)
4+
doconce format html CNNandmore.do.txt --html_style=bootstrap --pygments_html_style=default --html_admon=bootstrap_panel --html_output=CNNandmore-bs
5+
-->
6+
<html>
7+
<head>
8+
<meta http-equiv="Content-Type" content="text/html; charset=utf-8" />
9+
<meta name="generator" content="DocOnce: https://github.com/doconce/doconce/" />
10+
<meta name="viewport" content="width=device-width, initial-scale=1.0" />
11+
<meta name="description" content="Project 1 CNNs, RNNs, Autoencoders and more">
12+
<title>Project 1 CNNs, RNNs, Autoencoders and more</title>
13+
<!-- Bootstrap style: bootstrap -->
14+
<!-- doconce format html CNNandmore.do.txt --html_style=bootstrap --pygments_html_style=default --html_admon=bootstrap_panel --html_output=CNNandmore-bs -->
15+
<link href="https://netdna.bootstrapcdn.com/bootstrap/3.1.1/css/bootstrap.min.css" rel="stylesheet">
16+
<!-- not necessary
17+
<link href="https://netdna.bootstrapcdn.com/font-awesome/4.0.3/css/font-awesome.css" rel="stylesheet">
18+
-->
19+
<style type="text/css">
20+
/* Add scrollbar to dropdown menus in bootstrap navigation bar */
21+
.dropdown-menu {
22+
height: auto;
23+
max-height: 400px;
24+
overflow-x: hidden;
25+
}
26+
/* Adds an invisible element before each target to offset for the navigation
27+
bar */
28+
.anchor::before {
29+
content:"";
30+
display:block;
31+
height:50px; /* fixed header height for style bootstrap */
32+
margin:-50px 0 0; /* negative fixed header height */
33+
}
34+
</style>
35+
</head>
36+
37+
<!-- tocinfo
38+
{'highest level': 2,
39+
'sections': [('Discriminative methods', 2, None, 'discriminative-methods'),
40+
('Images and more', 3, None, 'images-and-more'),
41+
('Time series', 3, None, 'time-series'),
42+
('Introduction to numerical projects',
43+
2,
44+
None,
45+
'introduction-to-numerical-projects'),
46+
('Format for electronic delivery of report and programs',
47+
2,
48+
None,
49+
'format-for-electronic-delivery-of-report-and-programs')]}
50+
end of tocinfo -->
51+
52+
<body>
53+
<!-- Bootstrap navigation bar -->
54+
<div class="navbar navbar-default navbar-fixed-top">
55+
<div class="navbar-header">
56+
<button type="button" class="navbar-toggle" data-toggle="collapse" data-target=".navbar-responsive-collapse">
57+
<span class="icon-bar"></span>
58+
<span class="icon-bar"></span>
59+
<span class="icon-bar"></span>
60+
</button>
61+
<a class="navbar-brand" href="CNNandmore-bs.html">Project 1 CNNs, RNNs, Autoencoders and more</a>
62+
</div>
63+
<div class="navbar-collapse collapse navbar-responsive-collapse">
64+
<ul class="nav navbar-nav navbar-right">
65+
<li class="dropdown">
66+
<a href="#" class="dropdown-toggle" data-toggle="dropdown">Contents <b class="caret"></b></a>
67+
<ul class="dropdown-menu">
68+
<!-- navigation toc: --> <li><a href="#discriminative-methods" style="font-size: 80%;"><b>Discriminative methods</b></a></li>
69+
<!-- navigation toc: --> <li><a href="#images-and-more" style="font-size: 80%;">&nbsp;&nbsp;&nbsp;Images and more</a></li>
70+
<!-- navigation toc: --> <li><a href="#time-series" style="font-size: 80%;">&nbsp;&nbsp;&nbsp;Time series</a></li>
71+
<!-- navigation toc: --> <li><a href="#introduction-to-numerical-projects" style="font-size: 80%;"><b>Introduction to numerical projects</b></a></li>
72+
<!-- navigation toc: --> <li><a href="#format-for-electronic-delivery-of-report-and-programs" style="font-size: 80%;"><b>Format for electronic delivery of report and programs</b></a></li>
73+
74+
</ul>
75+
</li>
76+
</ul>
77+
</div>
78+
</div>
79+
</div> <!-- end of navigation bar -->
80+
<div class="container">
81+
<p>&nbsp;</p><p>&nbsp;</p><p>&nbsp;</p> <!-- add vertical space -->
82+
<a name="part0000"></a>
83+
<!-- ------------------- main content ---------------------- -->
84+
<div class="jumbotron">
85+
<center>
86+
<h1>Project 1 CNNs, RNNs, Autoencoders and more</h1>
87+
</center> <!-- document title -->
88+
89+
<!-- author(s): <a href="https://www.uio.no/studier/emner/matnat/fys/FYS5429/index-eng.html" target="_self">FYS5429/9429</a>, Advanced machine learning and data analysis for the physical sciences, University of Oslo, Norway -->
90+
<center>
91+
<b><a href="https://www.uio.no/studier/emner/matnat/fys/FYS5429/index-eng.html" target="_self">FYS5429/9429</a>, Advanced machine learning and data analysis for the physical sciences, University of Oslo, Norway</b>
92+
</center>
93+
<!-- institution(s) -->
94+
<br>
95+
<center>
96+
<h4>Spring semester 2025, deadline March 21</h4>
97+
</center> <!-- date -->
98+
<br>
99+
100+
101+
</div> <!-- end jumbotron -->
102+
<h2 id="discriminative-methods" class="anchor">Discriminative methods </h2>
103+
104+
<p>This project explores different discriminative methods, starting with
105+
standard neural networks, then moving to Comvolutional NNs (CNNs) or
106+
Recurrent NNs (RNNs), Autoencoders and/or Graphical NNs (GNNs). It
107+
allows also for a smooth transition to generative methods like
108+
Boltzmann machines, VAEs, GANs and Diffusion models. These methods are
109+
the topic of the second project.
110+
</p>
111+
<h3 id="images-and-more" class="anchor">Images and more </h3>
112+
113+
<p>A data set which many of you are familiar with is the MNIST set of
114+
handwritten numbers, see
115+
<a href="https://en.wikipedia.org/wiki/MNIST_database" target="_self"><tt>https://en.wikipedia.org/wiki/MNIST_database</tt></a>. Here you can
116+
study this data set with NNs, CNNs and eventually autoencoders or
117+
GNNs. For project 2 you could continue with the same data set and
118+
explore generative methods. You can obviously replace this data set
119+
with other images, such as images from modeling of phase transitions
120+
in physical systems, see <a href="https://www.arxiv.org/abs/2501.05547" target="_self"><tt>https://www.arxiv.org/abs/2501.05547</tt></a> or
121+
other data sets of your choice.
122+
</p>
123+
<h3 id="time-series" class="anchor">Time series </h3>
124+
125+
<p>Another frequently occuring type of data are so-called time
126+
series. Here again you can start with NNs, move over to RNNs and
127+
autoencoders. Similarly, for project 2, you can include VAEs,
128+
Diffusion models or other generative methods. At the end you will have
129+
studied a broad set of deep learning methods, allowing you thereby to
130+
assess their pros and cons.
131+
</p>
132+
133+
<p>Feel free to develop own codes or use libraries like TensorFlow and/or PyTorch.</p>
134+
<h2 id="introduction-to-numerical-projects" class="anchor">Introduction to numerical projects </h2>
135+
136+
<p>Here follows a brief recipe and recommendation on how to write a report for each
137+
project.
138+
</p>
139+
140+
<ul>
141+
<li> Give a short description of the nature of the problem and the eventual numerical methods you have used.</li>
142+
<li> Describe the algorithm you have used and/or developed. Here you may find it convenient to use pseudocoding. In many cases you can describe the algorithm in the program itself.</li>
143+
<li> Include the source code of your program. Comment your program properly.</li>
144+
<li> If possible, try to find analytic solutions, or known limits in order to test your program when developing the code.</li>
145+
<li> Include your results either in figure form or in a table. Remember to label your results. All tables and figures should have relevant captions and labels on the axes.</li>
146+
<li> Try to evaluate the reliabilty and numerical stability/precision of your results. If possible, include a qualitative and/or quantitative discussion of the numerical stability, eventual loss of precision etc.</li>
147+
<li> Try to give an interpretation of you results in your answers to the problems.</li>
148+
<li> Critique: if possible include your comments and reflections about the exercise, whether you felt you learnt something, ideas for improvements and other thoughts you've made when solving the exercise. We wish to keep this course at the interactive level and your comments can help us improve it.</li>
149+
<li> Try to establish a practice where you log your work at the computerlab. You may find such a logbook very handy at later stages in your work, especially when you don't properly remember what a previous test version of your program did. Here you could also record the time spent on solving the exercise, various algorithms you may have tested or other topics which you feel worthy of mentioning.</li>
150+
</ul>
151+
<h2 id="format-for-electronic-delivery-of-report-and-programs" class="anchor">Format for electronic delivery of report and programs </h2>
152+
153+
<p>The preferred format for the report is a PDF file. You can also use DOC or postscript formats or as an ipython notebook file. As programming language we prefer that you choose between C/C++, Fortran2008 or Python. The following prescription should be followed when preparing the report:</p>
154+
155+
<ul>
156+
<li> Send us an email in order to hand in your projects with a link to your GitHub/Gitlab repository.</li>
157+
<li> In your GitHub/GitLab or similar repository, please include a folder which contains selected results. These can be in the form of output from your code for a selected set of runs and input parameters.</li>
158+
</ul>
159+
<p>Finally,
160+
we encourage you to collaborate. Optimal working groups consist of
161+
2-3 students. You can then hand in a common report.
162+
</p>
163+
164+
<p>
165+
<!-- navigation buttons at the bottom of the page -->
166+
<ul class="pagination">
167+
<li class="active"><a href="._CNNandmore-bs000.html">1</a></li>
168+
</ul>
169+
<!-- ------------------- end of main content --------------- -->
170+
</div> <!-- end container -->
171+
<!-- include javascript, jQuery *first* -->
172+
<script src="https://ajax.googleapis.com/ajax/libs/jquery/1.10.2/jquery.min.js"></script>
173+
<script src="https://netdna.bootstrapcdn.com/bootstrap/3.0.0/js/bootstrap.min.js"></script>
174+
<!-- Bootstrap footer
175+
<footer>
176+
<a href="https://..."><img width="250" align=right src="https://..."></a>
177+
</footer>
178+
-->
179+
</body>
180+
</html>
181+
Lines changed: 181 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,181 @@
1+
<!--
2+
HTML file automatically generated from DocOnce source
3+
(https://github.com/doconce/doconce/)
4+
doconce format html CNNandmore.do.txt --html_style=bootstrap --pygments_html_style=default --html_admon=bootstrap_panel --html_output=CNNandmore-bs
5+
-->
6+
<html>
7+
<head>
8+
<meta http-equiv="Content-Type" content="text/html; charset=utf-8" />
9+
<meta name="generator" content="DocOnce: https://github.com/doconce/doconce/" />
10+
<meta name="viewport" content="width=device-width, initial-scale=1.0" />
11+
<meta name="description" content="Project 1 CNNs, RNNs, Autoencoders and more">
12+
<title>Project 1 CNNs, RNNs, Autoencoders and more</title>
13+
<!-- Bootstrap style: bootstrap -->
14+
<!-- doconce format html CNNandmore.do.txt --html_style=bootstrap --pygments_html_style=default --html_admon=bootstrap_panel --html_output=CNNandmore-bs -->
15+
<link href="https://netdna.bootstrapcdn.com/bootstrap/3.1.1/css/bootstrap.min.css" rel="stylesheet">
16+
<!-- not necessary
17+
<link href="https://netdna.bootstrapcdn.com/font-awesome/4.0.3/css/font-awesome.css" rel="stylesheet">
18+
-->
19+
<style type="text/css">
20+
/* Add scrollbar to dropdown menus in bootstrap navigation bar */
21+
.dropdown-menu {
22+
height: auto;
23+
max-height: 400px;
24+
overflow-x: hidden;
25+
}
26+
/* Adds an invisible element before each target to offset for the navigation
27+
bar */
28+
.anchor::before {
29+
content:"";
30+
display:block;
31+
height:50px; /* fixed header height for style bootstrap */
32+
margin:-50px 0 0; /* negative fixed header height */
33+
}
34+
</style>
35+
</head>
36+
37+
<!-- tocinfo
38+
{'highest level': 2,
39+
'sections': [('Discriminative methods', 2, None, 'discriminative-methods'),
40+
('Images and more', 3, None, 'images-and-more'),
41+
('Time series', 3, None, 'time-series'),
42+
('Introduction to numerical projects',
43+
2,
44+
None,
45+
'introduction-to-numerical-projects'),
46+
('Format for electronic delivery of report and programs',
47+
2,
48+
None,
49+
'format-for-electronic-delivery-of-report-and-programs')]}
50+
end of tocinfo -->
51+
52+
<body>
53+
<!-- Bootstrap navigation bar -->
54+
<div class="navbar navbar-default navbar-fixed-top">
55+
<div class="navbar-header">
56+
<button type="button" class="navbar-toggle" data-toggle="collapse" data-target=".navbar-responsive-collapse">
57+
<span class="icon-bar"></span>
58+
<span class="icon-bar"></span>
59+
<span class="icon-bar"></span>
60+
</button>
61+
<a class="navbar-brand" href="CNNandmore-bs.html">Project 1 CNNs, RNNs, Autoencoders and more</a>
62+
</div>
63+
<div class="navbar-collapse collapse navbar-responsive-collapse">
64+
<ul class="nav navbar-nav navbar-right">
65+
<li class="dropdown">
66+
<a href="#" class="dropdown-toggle" data-toggle="dropdown">Contents <b class="caret"></b></a>
67+
<ul class="dropdown-menu">
68+
<!-- navigation toc: --> <li><a href="#discriminative-methods" style="font-size: 80%;"><b>Discriminative methods</b></a></li>
69+
<!-- navigation toc: --> <li><a href="#images-and-more" style="font-size: 80%;">&nbsp;&nbsp;&nbsp;Images and more</a></li>
70+
<!-- navigation toc: --> <li><a href="#time-series" style="font-size: 80%;">&nbsp;&nbsp;&nbsp;Time series</a></li>
71+
<!-- navigation toc: --> <li><a href="#introduction-to-numerical-projects" style="font-size: 80%;"><b>Introduction to numerical projects</b></a></li>
72+
<!-- navigation toc: --> <li><a href="#format-for-electronic-delivery-of-report-and-programs" style="font-size: 80%;"><b>Format for electronic delivery of report and programs</b></a></li>
73+
74+
</ul>
75+
</li>
76+
</ul>
77+
</div>
78+
</div>
79+
</div> <!-- end of navigation bar -->
80+
<div class="container">
81+
<p>&nbsp;</p><p>&nbsp;</p><p>&nbsp;</p> <!-- add vertical space -->
82+
<a name="part0000"></a>
83+
<!-- ------------------- main content ---------------------- -->
84+
<div class="jumbotron">
85+
<center>
86+
<h1>Project 1 CNNs, RNNs, Autoencoders and more</h1>
87+
</center> <!-- document title -->
88+
89+
<!-- author(s): <a href="https://www.uio.no/studier/emner/matnat/fys/FYS5429/index-eng.html" target="_self">FYS5429/9429</a>, Advanced machine learning and data analysis for the physical sciences, University of Oslo, Norway -->
90+
<center>
91+
<b><a href="https://www.uio.no/studier/emner/matnat/fys/FYS5429/index-eng.html" target="_self">FYS5429/9429</a>, Advanced machine learning and data analysis for the physical sciences, University of Oslo, Norway</b>
92+
</center>
93+
<!-- institution(s) -->
94+
<br>
95+
<center>
96+
<h4>Spring semester 2025, deadline March 21</h4>
97+
</center> <!-- date -->
98+
<br>
99+
100+
101+
</div> <!-- end jumbotron -->
102+
<h2 id="discriminative-methods" class="anchor">Discriminative methods </h2>
103+
104+
<p>This project explores different discriminative methods, starting with
105+
standard neural networks, then moving to Comvolutional NNs (CNNs) or
106+
Recurrent NNs (RNNs), Autoencoders and/or Graphical NNs (GNNs). It
107+
allows also for a smooth transition to generative methods like
108+
Boltzmann machines, VAEs, GANs and Diffusion models. These methods are
109+
the topic of the second project.
110+
</p>
111+
<h3 id="images-and-more" class="anchor">Images and more </h3>
112+
113+
<p>A data set which many of you are familiar with is the MNIST set of
114+
handwritten numbers, see
115+
<a href="https://en.wikipedia.org/wiki/MNIST_database" target="_self"><tt>https://en.wikipedia.org/wiki/MNIST_database</tt></a>. Here you can
116+
study this data set with NNs, CNNs and eventually autoencoders or
117+
GNNs. For project 2 you could continue with the same data set and
118+
explore generative methods. You can obviously replace this data set
119+
with other images, such as images from modeling of phase transitions
120+
in physical systems, see <a href="https://www.arxiv.org/abs/2501.05547" target="_self"><tt>https://www.arxiv.org/abs/2501.05547</tt></a> or
121+
other data sets of your choice.
122+
</p>
123+
<h3 id="time-series" class="anchor">Time series </h3>
124+
125+
<p>Another frequently occuring type of data are so-called time
126+
series. Here again you can start with NNs, move over to RNNs and
127+
autoencoders. Similarly, for project 2, you can include VAEs,
128+
Diffusion models or other generative methods. At the end you will have
129+
studied a broad set of deep learning methods, allowing you thereby to
130+
assess their pros and cons.
131+
</p>
132+
133+
<p>Feel free to develop own codes or use libraries like TensorFlow and/or PyTorch.</p>
134+
<h2 id="introduction-to-numerical-projects" class="anchor">Introduction to numerical projects </h2>
135+
136+
<p>Here follows a brief recipe and recommendation on how to write a report for each
137+
project.
138+
</p>
139+
140+
<ul>
141+
<li> Give a short description of the nature of the problem and the eventual numerical methods you have used.</li>
142+
<li> Describe the algorithm you have used and/or developed. Here you may find it convenient to use pseudocoding. In many cases you can describe the algorithm in the program itself.</li>
143+
<li> Include the source code of your program. Comment your program properly.</li>
144+
<li> If possible, try to find analytic solutions, or known limits in order to test your program when developing the code.</li>
145+
<li> Include your results either in figure form or in a table. Remember to label your results. All tables and figures should have relevant captions and labels on the axes.</li>
146+
<li> Try to evaluate the reliabilty and numerical stability/precision of your results. If possible, include a qualitative and/or quantitative discussion of the numerical stability, eventual loss of precision etc.</li>
147+
<li> Try to give an interpretation of you results in your answers to the problems.</li>
148+
<li> Critique: if possible include your comments and reflections about the exercise, whether you felt you learnt something, ideas for improvements and other thoughts you've made when solving the exercise. We wish to keep this course at the interactive level and your comments can help us improve it.</li>
149+
<li> Try to establish a practice where you log your work at the computerlab. You may find such a logbook very handy at later stages in your work, especially when you don't properly remember what a previous test version of your program did. Here you could also record the time spent on solving the exercise, various algorithms you may have tested or other topics which you feel worthy of mentioning.</li>
150+
</ul>
151+
<h2 id="format-for-electronic-delivery-of-report-and-programs" class="anchor">Format for electronic delivery of report and programs </h2>
152+
153+
<p>The preferred format for the report is a PDF file. You can also use DOC or postscript formats or as an ipython notebook file. As programming language we prefer that you choose between C/C++, Fortran2008 or Python. The following prescription should be followed when preparing the report:</p>
154+
155+
<ul>
156+
<li> Send us an email in order to hand in your projects with a link to your GitHub/Gitlab repository.</li>
157+
<li> In your GitHub/GitLab or similar repository, please include a folder which contains selected results. These can be in the form of output from your code for a selected set of runs and input parameters.</li>
158+
</ul>
159+
<p>Finally,
160+
we encourage you to collaborate. Optimal working groups consist of
161+
2-3 students. You can then hand in a common report.
162+
</p>
163+
164+
<p>
165+
<!-- navigation buttons at the bottom of the page -->
166+
<ul class="pagination">
167+
<li class="active"><a href="._CNNandmore-bs000.html">1</a></li>
168+
</ul>
169+
<!-- ------------------- end of main content --------------- -->
170+
</div> <!-- end container -->
171+
<!-- include javascript, jQuery *first* -->
172+
<script src="https://ajax.googleapis.com/ajax/libs/jquery/1.10.2/jquery.min.js"></script>
173+
<script src="https://netdna.bootstrapcdn.com/bootstrap/3.0.0/js/bootstrap.min.js"></script>
174+
<!-- Bootstrap footer
175+
<footer>
176+
<a href="https://..."><img width="250" align=right src="https://..."></a>
177+
</footer>
178+
-->
179+
</body>
180+
</html>
181+

0 commit comments

Comments
 (0)