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

update week 39

Browse Source
This commit is contained in:
Morten Hjorth-Jensen
2024-09-17 22:17:26 +02:00
parent 8afe465b5f
commit b83d90df2b
9 changed files with 1336 additions and 690 deletions
Download Patch File Download Diff File Expand all files Collapse all files
doc/LectureNotes/exercisesweek39.ipynb
+59
View File
@@ -0,0 +1,59 @@
{
"cells": [
{
"cell_type": "markdown",
"id": "263a45c0",
"metadata": {
"editable": true
},
"source": [
"<!-- HTML file automatically generated from DocOnce source (https://github.com/doconce/doconce/)\n",
"doconce format html exercisesweek39.do.txt -->\n",
"<!-- dom:TITLE: Exercises week 39 -->"
]
},
{
"cell_type": "markdown",
"id": "155995fb",
"metadata": {
"editable": true
},
"source": [
"# Exercises week 39\n",
"**September 23-27, 2024**\n",
"\n",
"Date: **Deadline is Friday September 27 at midnight**"
]
},
{
"cell_type": "markdown",
"id": "402606f9",
"metadata": {
"editable": true
},
"source": [
"## Overarching aims of the exercises this week\n",
"\n",
"The aim of the exercises this week is to aid you in getting started\n",
"with writing the report. This will be discussed during the lab\n",
"sessions as well. \n",
"\n",
"A general guideline can be found at <https://github.com/CompPhysics/MachineLearning/blob/master/doc/Projects/EvaluationGrading/EvaluationForm.md>.\n",
"\n",
"Similarly, an example of an earlier project can be found at <https://github.com/CompPhysics/MachineLearning/blob/master/doc/Projects/ReportExample/ReportSample.pdf>\n",
"\n",
"Your task this week is to\n",
"1. Write an abstract for your project\n",
"\n",
"2. Write an introduction\n",
"\n",
"3. Include references\n",
"\n",
"A short feedback to the this exercise will be available before the project deadline. And you can reuse these elements in your final report."
]
}
],
"metadata": {},
"nbformat": 4,
"nbformat_minor": 5
}
doc/pub/week39/html/week39-bs.html
+5 -5
View File
@@ -37,11 +37,11 @@ doconce format html week39.do.txt --html_style=bootstrap --pygments_html_style=d
<!-- tocinfo
{'highest level': 2,
'sections': [('Plan for week 39', 2, None, 'plan-for-week-39'),
('Optimization, the central part of any Machine Learning '
'algortithm',
('Lecture Monday September 23, Optimization, the central part of '
'any Machine Learning algortithm',
2,
None,
'optimization-the-central-part-of-any-machine-learning-algortithm'),
'lecture-monday-september-23-optimization-the-central-part-of-any-machine-learning-algortithm'),
('Revisiting our Logistic Regression case',
2,
None,
@@ -306,7 +306,7 @@ MathJax.Hub.Config({
<a href="#" class="dropdown-toggle" data-toggle="dropdown">Contents <b class="caret"></b></a>
<ul class="dropdown-menu">
<!-- navigation toc: --> <li><a href="._week39-bs001.html#plan-for-week-39" style="font-size: 80%;">Plan for week 39</a></li>
<!-- navigation toc: --> <li><a href="._week39-bs002.html#optimization-the-central-part-of-any-machine-learning-algortithm" style="font-size: 80%;">Optimization, the central part of any Machine Learning algortithm</a></li>
<!-- navigation toc: --> <li><a href="._week39-bs002.html#lecture-monday-september-23-optimization-the-central-part-of-any-machine-learning-algortithm" style="font-size: 80%;">Lecture Monday September 23, Optimization, the central part of any Machine Learning algortithm</a></li>
<!-- navigation toc: --> <li><a href="._week39-bs003.html#revisiting-our-logistic-regression-case" style="font-size: 80%;">Revisiting our Logistic Regression case</a></li>
<!-- navigation toc: --> <li><a href="._week39-bs004.html#the-equations-to-solve" style="font-size: 80%;">The equations to solve</a></li>
<!-- navigation toc: --> <li><a href="._week39-bs005.html#solving-using-newton-raphson-s-method" style="font-size: 80%;">Solving using Newton-Raphson's method</a></li>
@@ -460,7 +460,7 @@ MathJax.Hub.Config({
</footer>
-->
<center style="font-size:80%">
<!-- copyright --> &copy; 1999-2023, Morten Hjorth-Jensen. Released under CC Attribution-NonCommercial 4.0 license
<!-- copyright --> &copy; 1999-2024, Morten Hjorth-Jensen. Released under CC Attribution-NonCommercial 4.0 license
</center>
</body>
</html>
doc/pub/week39/html/week39-reveal.html
+25 -25
View File
@@ -190,7 +190,7 @@ MathJax.Hub.Config({
<center style="font-size:80%">
<!-- copyright --> &copy; 1999-2023, Morten Hjorth-Jensen. Released under CC Attribution-NonCommercial 4.0 license
<!-- copyright --> &copy; 1999-2024, Morten Hjorth-Jensen. Released under CC Attribution-NonCommercial 4.0 license
</center>
</section>
@@ -198,29 +198,7 @@ MathJax.Hub.Config({
<h2 id="plan-for-week-39">Plan for week 39 </h2>
<div class="alert alert-block alert-block alert-text-normal">
<b>Material for the active learning sessions on Tuesday and Wednesday</b>
<p>
<ul>
<p><li> Discussions on how to structure your report for the first project</li>
<p><li> Exercise for week 39 on how to write the abstract and the introduction of the report and how to include references.</li>
<p><li> Work on project 1, in particular resampling methods like cross-validation and bootstrap. <b>For more discussions of project 1, chapter 5 of Goodfellow et al is a good read, in particular sections 5.1-5.5 and 5.7-5.11</b>.</li>
<p><li> <a href="https://youtu.be/tVW1ZDmZnwM" target="_blank">Video on how to write scientific reports recorded during one of the lab sessions</a></li>
</ul>
<p>
<p>These sections summarize neatly what we have done till now and point to what is coming with respect to deep learning. </p>
<ul>
<p><li> A general guideline can be found at <a href="https://github.com/CompPhysics/MachineLearning/blob/master/doc/Projects/EvaluationGrading/EvaluationForm.md" target="_blank"><tt>https://github.com/CompPhysics/MachineLearning/blob/master/doc/Projects/EvaluationGrading/EvaluationForm.md</tt></a>.</li>
</ul>
</div>
<div class="alert alert-block alert-block alert-text-normal">
<b>Material for the lecture on Thursday September 28</b>
<b>Material for the lecture on Monday September 23</b>
<p>
<ul>
@@ -248,11 +226,33 @@ MathJax.Hub.Config({
</div>
<div class="alert alert-block alert-block alert-text-normal">
<b>Material for the active learning sessions on Tuesday and Wednesday</b>
<p>
<ul>
<p><li> Discussions on how to structure your report for the first project</li>
<p><li> Exercise for week 39 on how to write the abstract and the introduction of the report and how to include references.</li>
<p><li> Work on project 1, in particular resampling methods like cross-validation and bootstrap. <b>For more discussions of project 1, chapter 5 of Goodfellow et al is a good read, in particular sections 5.1-5.5 and 5.7-5.11</b>.</li>
<p><li> <a href="https://youtu.be/tVW1ZDmZnwM" target="_blank">Video on how to write scientific reports recorded during one of the lab sessions</a></li>
</ul>
<p>
<p>These sections summarize neatly what we have done till now and point to what is coming with respect to deep learning. </p>
<ul>
<p><li> A general guideline can be found at <a href="https://github.com/CompPhysics/MachineLearning/blob/master/doc/Projects/EvaluationGrading/EvaluationForm.md" target="_blank"><tt>https://github.com/CompPhysics/MachineLearning/blob/master/doc/Projects/EvaluationGrading/EvaluationForm.md</tt></a>.</li>
</ul>
</div>
<!-- rett opp tyrleif -->
</section>
<section>
<h2 id="optimization-the-central-part-of-any-machine-learning-algortithm">Optimization, the central part of any Machine Learning algortithm </h2>
<h2 id="lecture-monday-september-23-optimization-the-central-part-of-any-machine-learning-algortithm">Lecture Monday September 23, Optimization, the central part of any Machine Learning algortithm </h2>
<p>The first few slides here are a repetition from last week. </p>
doc/pub/week39/html/week39-solarized.html
+22 -22
View File
@@ -64,11 +64,11 @@ div.toc p,a {
<!-- tocinfo
{'highest level': 2,
'sections': [('Plan for week 39', 2, None, 'plan-for-week-39'),
('Optimization, the central part of any Machine Learning '
'algortithm',
('Lecture Monday September 23, Optimization, the central part of '
'any Machine Learning algortithm',
2,
None,
'optimization-the-central-part-of-any-machine-learning-algortithm'),
'lecture-monday-september-23-optimization-the-central-part-of-any-machine-learning-algortithm'),
('Revisiting our Logistic Regression case',
2,
None,
@@ -343,23 +343,7 @@ MathJax.Hub.Config({
<h2 id="plan-for-week-39">Plan for week 39 </h2>
<div class="alert alert-block alert-block alert-text-normal">
<b>Material for the active learning sessions on Tuesday and Wednesday</b>
<p>
<ul>
<li> Discussions on how to structure your report for the first project</li>
<li> Exercise for week 39 on how to write the abstract and the introduction of the report and how to include references.</li>
<li> Work on project 1, in particular resampling methods like cross-validation and bootstrap. <b>For more discussions of project 1, chapter 5 of Goodfellow et al is a good read, in particular sections 5.1-5.5 and 5.7-5.11</b>.</li>
<li> <a href="https://youtu.be/tVW1ZDmZnwM" target="_blank">Video on how to write scientific reports recorded during one of the lab sessions</a></li>
</ul>
<p>These sections summarize neatly what we have done till now and point to what is coming with respect to deep learning. </p>
<ul>
<li> A general guideline can be found at <a href="https://github.com/CompPhysics/MachineLearning/blob/master/doc/Projects/EvaluationGrading/EvaluationForm.md" target="_blank"><tt>https://github.com/CompPhysics/MachineLearning/blob/master/doc/Projects/EvaluationGrading/EvaluationForm.md</tt></a>.</li>
</ul>
</div>
<div class="alert alert-block alert-block alert-text-normal">
<b>Material for the lecture on Thursday September 28</b>
<b>Material for the lecture on Monday September 23</b>
<p>
<ul>
<li> Repetition of Logistic regression equations and classification problems and discussion of Gradient methods. Examples on how to implement Logistic Regression and discussion of stochastic gradient descent</li>
@@ -377,10 +361,26 @@ MathJax.Hub.Config({
</div>
<div class="alert alert-block alert-block alert-text-normal">
<b>Material for the active learning sessions on Tuesday and Wednesday</b>
<p>
<ul>
<li> Discussions on how to structure your report for the first project</li>
<li> Exercise for week 39 on how to write the abstract and the introduction of the report and how to include references.</li>
<li> Work on project 1, in particular resampling methods like cross-validation and bootstrap. <b>For more discussions of project 1, chapter 5 of Goodfellow et al is a good read, in particular sections 5.1-5.5 and 5.7-5.11</b>.</li>
<li> <a href="https://youtu.be/tVW1ZDmZnwM" target="_blank">Video on how to write scientific reports recorded during one of the lab sessions</a></li>
</ul>
<p>These sections summarize neatly what we have done till now and point to what is coming with respect to deep learning. </p>
<ul>
<li> A general guideline can be found at <a href="https://github.com/CompPhysics/MachineLearning/blob/master/doc/Projects/EvaluationGrading/EvaluationForm.md" target="_blank"><tt>https://github.com/CompPhysics/MachineLearning/blob/master/doc/Projects/EvaluationGrading/EvaluationForm.md</tt></a>.</li>
</ul>
</div>
<!-- rett opp tyrleif -->
<!-- !split --><br><br><br><br><br><br><br><br><br><br>
<h2 id="optimization-the-central-part-of-any-machine-learning-algortithm">Optimization, the central part of any Machine Learning algortithm </h2>
<h2 id="lecture-monday-september-23-optimization-the-central-part-of-any-machine-learning-algortithm">Lecture Monday September 23, Optimization, the central part of any Machine Learning algortithm </h2>
<p>The first few slides here are a repetition from last week. </p>
@@ -3815,7 +3815,7 @@ derivative_fn = grad(sum_logistic)
<!-- ------------------- end of main content --------------- -->
<center style="font-size:80%">
<!-- copyright --> &copy; 1999-2023, Morten Hjorth-Jensen. Released under CC Attribution-NonCommercial 4.0 license
<!-- copyright --> &copy; 1999-2024, Morten Hjorth-Jensen. Released under CC Attribution-NonCommercial 4.0 license
</center>
</body>
</html>
doc/pub/week39/html/week39.html
+22 -22
View File
@@ -141,11 +141,11 @@ div.toc p,a {
<!-- tocinfo
{'highest level': 2,
'sections': [('Plan for week 39', 2, None, 'plan-for-week-39'),
('Optimization, the central part of any Machine Learning '
'algortithm',
('Lecture Monday September 23, Optimization, the central part of '
'any Machine Learning algortithm',
2,
None,
'optimization-the-central-part-of-any-machine-learning-algortithm'),
'lecture-monday-september-23-optimization-the-central-part-of-any-machine-learning-algortithm'),
('Revisiting our Logistic Regression case',
2,
None,
@@ -420,23 +420,7 @@ MathJax.Hub.Config({
<h2 id="plan-for-week-39">Plan for week 39 </h2>
<div class="alert alert-block alert-block alert-text-normal">
<b>Material for the active learning sessions on Tuesday and Wednesday</b>
<p>
<ul>
<li> Discussions on how to structure your report for the first project</li>
<li> Exercise for week 39 on how to write the abstract and the introduction of the report and how to include references.</li>
<li> Work on project 1, in particular resampling methods like cross-validation and bootstrap. <b>For more discussions of project 1, chapter 5 of Goodfellow et al is a good read, in particular sections 5.1-5.5 and 5.7-5.11</b>.</li>
<li> <a href="https://youtu.be/tVW1ZDmZnwM" target="_blank">Video on how to write scientific reports recorded during one of the lab sessions</a></li>
</ul>
<p>These sections summarize neatly what we have done till now and point to what is coming with respect to deep learning. </p>
<ul>
<li> A general guideline can be found at <a href="https://github.com/CompPhysics/MachineLearning/blob/master/doc/Projects/EvaluationGrading/EvaluationForm.md" target="_blank"><tt>https://github.com/CompPhysics/MachineLearning/blob/master/doc/Projects/EvaluationGrading/EvaluationForm.md</tt></a>.</li>
</ul>
</div>
<div class="alert alert-block alert-block alert-text-normal">
<b>Material for the lecture on Thursday September 28</b>
<b>Material for the lecture on Monday September 23</b>
<p>
<ul>
<li> Repetition of Logistic regression equations and classification problems and discussion of Gradient methods. Examples on how to implement Logistic Regression and discussion of stochastic gradient descent</li>
@@ -454,10 +438,26 @@ MathJax.Hub.Config({
</div>
<div class="alert alert-block alert-block alert-text-normal">
<b>Material for the active learning sessions on Tuesday and Wednesday</b>
<p>
<ul>
<li> Discussions on how to structure your report for the first project</li>
<li> Exercise for week 39 on how to write the abstract and the introduction of the report and how to include references.</li>
<li> Work on project 1, in particular resampling methods like cross-validation and bootstrap. <b>For more discussions of project 1, chapter 5 of Goodfellow et al is a good read, in particular sections 5.1-5.5 and 5.7-5.11</b>.</li>
<li> <a href="https://youtu.be/tVW1ZDmZnwM" target="_blank">Video on how to write scientific reports recorded during one of the lab sessions</a></li>
</ul>
<p>These sections summarize neatly what we have done till now and point to what is coming with respect to deep learning. </p>
<ul>
<li> A general guideline can be found at <a href="https://github.com/CompPhysics/MachineLearning/blob/master/doc/Projects/EvaluationGrading/EvaluationForm.md" target="_blank"><tt>https://github.com/CompPhysics/MachineLearning/blob/master/doc/Projects/EvaluationGrading/EvaluationForm.md</tt></a>.</li>
</ul>
</div>
<!-- rett opp tyrleif -->
<!-- !split --><br><br><br><br><br><br><br><br><br><br>
<h2 id="optimization-the-central-part-of-any-machine-learning-algortithm">Optimization, the central part of any Machine Learning algortithm </h2>
<h2 id="lecture-monday-september-23-optimization-the-central-part-of-any-machine-learning-algortithm">Lecture Monday September 23, Optimization, the central part of any Machine Learning algortithm </h2>
<p>The first few slides here are a repetition from last week. </p>
@@ -3892,7 +3892,7 @@ derivative_fn <span style="color: #666666">=</span> grad(sum_logistic)
<!-- ------------------- end of main content --------------- -->
<center style="font-size:80%">
<!-- copyright --> &copy; 1999-2023, Morten Hjorth-Jensen. Released under CC Attribution-NonCommercial 4.0 license
<!-- copyright --> &copy; 1999-2024, Morten Hjorth-Jensen. Released under CC Attribution-NonCommercial 4.0 license
</center>
</body>
</html>
doc/pub/week39/ipynb/ipynb-week39-src.tar.gz
BIN
View File
Binary file not shown.
doc/pub/week39/ipynb/week39.ipynb
+1187 -602
View File
File diff suppressed because it is too large Load Diff
doc/src/week39/exercisesweek39.do.txt
+4 -4
View File
@@ -1,13 +1,13 @@
TITLE: Exercises week 39
AUTHOR: September 25-29, 2023
DATE: Deadline is Sunday October 1 at midnight
AUTHOR: September 23-27, 2024
DATE: Deadline is Friday September 27 at midnight
===== Overarching aims of the exercises this week =====
The aim of the exercises this week is to aid you in getting started
with writing the report. This will be discussed during the lab
sessions as well. One of the lab sessions will be recorded.
sessions as well.
A general guideline can be found at URL:"https://github.com/CompPhysics/MachineLearning/blob/master/doc/Projects/EvaluationGrading/EvaluationForm.md".
@@ -19,6 +19,6 @@ o Write an abstract for your project
o Write an introduction
o Include references
Ashort feedback to the this exercise will be available after the deadline. And you can reuse these elements in your final report.
A short feedback to the this exercise will be available before the project deadline. And you can reuse these elements in your final report.
doc/src/week39/week39.do.txt
+12 -10
View File
@@ -6,17 +6,9 @@ DATE: Week 39
===== Plan for week 39 =====
!bblock Material for the active learning sessions on Tuesday and Wednesday
* Discussions on how to structure your report for the first project
* Exercise for week 39 on how to write the abstract and the introduction of the report and how to include references.
* Work on project 1, in particular resampling methods like cross-validation and bootstrap. _For more discussions of project 1, chapter 5 of Goodfellow et al is a good read, in particular sections 5.1-5.5 and 5.7-5.11_.
* "Video on how to write scientific reports recorded during one of the lab sessions":"https://youtu.be/tVW1ZDmZnwM"
These sections summarize neatly what we have done till now and point to what is coming with respect to deep learning.
* A general guideline can be found at URL:"https://github.com/CompPhysics/MachineLearning/blob/master/doc/Projects/EvaluationGrading/EvaluationForm.md".
!eblock
!bblock Material for the lecture on Thursday September 28
!bblock Material for the lecture on Monday September 23
* Repetition of Logistic regression equations and classification problems and discussion of Gradient methods. Examples on how to implement Logistic Regression and discussion of stochastic gradient descent
* Stochastic Gradient descent with examples and automatic differentiation
* "Video of lecture":"https://youtu.be/bFRVuIJroHs"
@@ -29,12 +21,22 @@ These sections summarize neatly what we have done till now and point to what is
!eblock
!bblock Material for the active learning sessions on Tuesday and Wednesday
* Discussions on how to structure your report for the first project
* Exercise for week 39 on how to write the abstract and the introduction of the report and how to include references.
* Work on project 1, in particular resampling methods like cross-validation and bootstrap. _For more discussions of project 1, chapter 5 of Goodfellow et al is a good read, in particular sections 5.1-5.5 and 5.7-5.11_.
* "Video on how to write scientific reports recorded during one of the lab sessions":"https://youtu.be/tVW1ZDmZnwM"
These sections summarize neatly what we have done till now and point to what is coming with respect to deep learning.
* A general guideline can be found at URL:"https://github.com/CompPhysics/MachineLearning/blob/master/doc/Projects/EvaluationGrading/EvaluationForm.md".
!eblock
# rett opp tyrleif
!split
===== Optimization, the central part of any Machine Learning algortithm =====
===== Lecture Monday September 23, Optimization, the central part of any Machine Learning algortithm =====
The first few slides here are a repetition from last week.