Morten Hjorth-Jensen
630 lines
27 KiB
HTML
630 lines
27 KiB
HTML
|
|
<!DOCTYPE html>
|
|
|
|
|
|
<html lang="en" data-content_root="./" >
|
|
|
|
<head>
|
|
<meta charset="utf-8" />
|
|
<meta name="viewport" content="width=device-width, initial-scale=1.0" /><meta name="viewport" content="width=device-width, initial-scale=1" />
|
|
|
|
<title>Exercises week 38 — Applied Data Analysis and Machine Learning</title>
|
|
|
|
|
|
|
|
<script data-cfasync="false">
|
|
document.documentElement.dataset.mode = localStorage.getItem("mode") || "";
|
|
document.documentElement.dataset.theme = localStorage.getItem("theme") || "";
|
|
</script>
|
|
<!--
|
|
this give us a css class that will be invisible only if js is disabled
|
|
-->
|
|
<noscript>
|
|
<style>
|
|
.pst-js-only { display: none !important; }
|
|
|
|
</style>
|
|
</noscript>
|
|
|
|
<!-- Loaded before other Sphinx assets -->
|
|
<link href="_static/styles/theme.css?digest=26a4bc78f4c0ddb94549" rel="stylesheet" />
|
|
<link href="_static/styles/pydata-sphinx-theme.css?digest=26a4bc78f4c0ddb94549" rel="stylesheet" />
|
|
|
|
<link rel="stylesheet" type="text/css" href="_static/pygments.css?v=fa44fd50" />
|
|
<link rel="stylesheet" type="text/css" href="_static/styles/sphinx-book-theme.css?v=a3416100" />
|
|
<link rel="stylesheet" type="text/css" href="_static/togglebutton.css?v=13237357" />
|
|
<link rel="stylesheet" type="text/css" href="_static/copybutton.css?v=76b2166b" />
|
|
<link rel="stylesheet" type="text/css" href="_static/mystnb.4510f1fc1dee50b3e5859aac5469c37c29e427902b24a333a5f9fcb2f0b3ac41.css?v=be8a1c11" />
|
|
<link rel="stylesheet" type="text/css" href="_static/sphinx-thebe.css?v=4fa983c6" />
|
|
<link rel="stylesheet" type="text/css" href="_static/sphinx-design.min.css?v=95c83b7e" />
|
|
|
|
<!-- So that users can add custom icons -->
|
|
<script src="_static/scripts/fontawesome.js?digest=26a4bc78f4c0ddb94549"></script>
|
|
<!-- Pre-loaded scripts that we'll load fully later -->
|
|
<link rel="preload" as="script" href="_static/scripts/bootstrap.js?digest=26a4bc78f4c0ddb94549" />
|
|
<link rel="preload" as="script" href="_static/scripts/pydata-sphinx-theme.js?digest=26a4bc78f4c0ddb94549" />
|
|
|
|
<script src="_static/documentation_options.js?v=9eb32ce0"></script>
|
|
<script src="_static/doctools.js?v=9a2dae69"></script>
|
|
<script src="_static/sphinx_highlight.js?v=dc90522c"></script>
|
|
<script src="_static/clipboard.min.js?v=a7894cd8"></script>
|
|
<script src="_static/copybutton.js?v=f281be69"></script>
|
|
<script src="_static/scripts/sphinx-book-theme.js?v=887ef09a"></script>
|
|
<script>let toggleHintShow = 'Click to show';</script>
|
|
<script>let toggleHintHide = 'Click to hide';</script>
|
|
<script>let toggleOpenOnPrint = 'true';</script>
|
|
<script src="_static/togglebutton.js?v=4a39c7ea"></script>
|
|
<script>var togglebuttonSelector = '.toggle, .admonition.dropdown';</script>
|
|
<script src="_static/design-tabs.js?v=f930bc37"></script>
|
|
<script>const THEBE_JS_URL = "https://unpkg.com/thebe@0.8.2/lib/index.js"; const thebe_selector = ".thebe,.cell"; const thebe_selector_input = "pre"; const thebe_selector_output = ".output, .cell_output"</script>
|
|
<script async="async" src="_static/sphinx-thebe.js?v=c100c467"></script>
|
|
<script>var togglebuttonSelector = '.toggle, .admonition.dropdown';</script>
|
|
<script>const THEBE_JS_URL = "https://unpkg.com/thebe@0.8.2/lib/index.js"; const thebe_selector = ".thebe,.cell"; const thebe_selector_input = "pre"; const thebe_selector_output = ".output, .cell_output"</script>
|
|
<script>window.MathJax = {"options": {"processHtmlClass": "tex2jax_process|mathjax_process|math|output_area"}}</script>
|
|
<script defer="defer" src="https://cdn.jsdelivr.net/npm/mathjax@3/es5/tex-mml-chtml.js"></script>
|
|
<script>DOCUMENTATION_OPTIONS.pagename = 'exercisesweek38';</script>
|
|
<link rel="index" title="Index" href="genindex.html" />
|
|
<link rel="search" title="Search" href="search.html" />
|
|
<link rel="next" title="Week 38: Logistic Regression and Optimization" href="week38.html" />
|
|
<link rel="prev" title="Week 37: Statistical interpretations and Resampling Methods" href="week37.html" />
|
|
<meta name="viewport" content="width=device-width, initial-scale=1"/>
|
|
<meta name="docsearch:language" content="en"/>
|
|
<meta name="docsearch:version" content="" />
|
|
</head>
|
|
|
|
|
|
<body data-bs-spy="scroll" data-bs-target=".bd-toc-nav" data-offset="180" data-bs-root-margin="0px 0px -60%" data-default-mode="">
|
|
|
|
|
|
|
|
<div id="pst-skip-link" class="skip-link d-print-none"><a href="#main-content">Skip to main content</a></div>
|
|
|
|
<div id="pst-scroll-pixel-helper"></div>
|
|
|
|
<button type="button" class="btn rounded-pill" id="pst-back-to-top">
|
|
<i class="fa-solid fa-arrow-up"></i>Back to top</button>
|
|
|
|
|
|
<dialog id="pst-search-dialog">
|
|
|
|
<form class="bd-search d-flex align-items-center"
|
|
action="search.html"
|
|
method="get">
|
|
<i class="fa-solid fa-magnifying-glass"></i>
|
|
<input type="search"
|
|
class="form-control"
|
|
name="q"
|
|
placeholder="Search this book..."
|
|
aria-label="Search this book..."
|
|
autocomplete="off"
|
|
autocorrect="off"
|
|
autocapitalize="off"
|
|
spellcheck="false"/>
|
|
<span class="search-button__kbd-shortcut"><kbd class="kbd-shortcut__modifier">Ctrl</kbd>+<kbd>K</kbd></span>
|
|
</form>
|
|
</dialog>
|
|
|
|
<div class="pst-async-banner-revealer d-none">
|
|
<aside id="bd-header-version-warning" class="d-none d-print-none" aria-label="Version warning"></aside>
|
|
</div>
|
|
|
|
|
|
<header class="bd-header navbar navbar-expand-lg bd-navbar d-print-none">
|
|
</header>
|
|
|
|
|
|
<div class="bd-container">
|
|
<div class="bd-container__inner bd-page-width">
|
|
|
|
|
|
|
|
<dialog id="pst-primary-sidebar-modal"></dialog>
|
|
<div id="pst-primary-sidebar" class="bd-sidebar-primary bd-sidebar">
|
|
|
|
|
|
|
|
<div class="sidebar-header-items sidebar-primary__section">
|
|
|
|
|
|
|
|
|
|
</div>
|
|
|
|
<div class="sidebar-primary-items__start sidebar-primary__section">
|
|
<div class="sidebar-primary-item">
|
|
|
|
|
|
|
|
|
|
|
|
<a class="navbar-brand logo" href="intro.html">
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
<img src="_static/logo.png" class="logo__image only-light" alt="Applied Data Analysis and Machine Learning - Home"/>
|
|
<img src="_static/logo.png" class="logo__image only-dark pst-js-only" alt="Applied Data Analysis and Machine Learning - Home"/>
|
|
|
|
|
|
</a></div>
|
|
<div class="sidebar-primary-item">
|
|
|
|
<button class="btn search-button-field search-button__button pst-js-only" title="Search" aria-label="Search" data-bs-placement="bottom" data-bs-toggle="tooltip">
|
|
<i class="fa-solid fa-magnifying-glass"></i>
|
|
<span class="search-button__default-text">Search</span>
|
|
<span class="search-button__kbd-shortcut"><kbd class="kbd-shortcut__modifier">Ctrl</kbd>+<kbd class="kbd-shortcut__modifier">K</kbd></span>
|
|
</button></div>
|
|
<div class="sidebar-primary-item"><nav class="bd-links bd-docs-nav" aria-label="Main">
|
|
<div class="bd-toc-item navbar-nav active">
|
|
|
|
<ul class="nav bd-sidenav bd-sidenav__home-link">
|
|
<li class="toctree-l1">
|
|
<a class="reference internal" href="intro.html">
|
|
Applied Data Analysis and Machine Learning
|
|
</a>
|
|
</li>
|
|
</ul>
|
|
<p aria-level="2" class="caption" role="heading"><span class="caption-text">About the course</span></p>
|
|
<ul class="nav bd-sidenav">
|
|
<li class="toctree-l1"><a class="reference internal" href="schedule.html">Teaching schedule with links to material</a></li>
|
|
<li class="toctree-l1"><a class="reference internal" href="teachers.html">Teachers and Grading</a></li>
|
|
<li class="toctree-l1"><a class="reference internal" href="textbooks.html">Textbooks</a></li>
|
|
|
|
</ul>
|
|
<p aria-level="2" class="caption" role="heading"><span class="caption-text">Review of Statistics with Resampling Techniques and Linear Algebra</span></p>
|
|
<ul class="nav bd-sidenav">
|
|
<li class="toctree-l1"><a class="reference internal" href="statistics.html">1. Elements of Probability Theory and Statistical Data Analysis</a></li>
|
|
<li class="toctree-l1"><a class="reference internal" href="linalg.html">2. Linear Algebra, Handling of Arrays and more Python Features</a></li>
|
|
</ul>
|
|
<p aria-level="2" class="caption" role="heading"><span class="caption-text">From Regression to Support Vector Machines</span></p>
|
|
<ul class="nav bd-sidenav">
|
|
<li class="toctree-l1"><a class="reference internal" href="chapter1.html">3. Linear Regression</a></li>
|
|
<li class="toctree-l1"><a class="reference internal" href="chapter2.html">4. Ridge and Lasso Regression</a></li>
|
|
<li class="toctree-l1"><a class="reference internal" href="chapter3.html">5. Resampling Methods</a></li>
|
|
<li class="toctree-l1"><a class="reference internal" href="chapter4.html">6. Logistic Regression</a></li>
|
|
<li class="toctree-l1"><a class="reference internal" href="chapteroptimization.html">7. Optimization, the central part of any Machine Learning algortithm</a></li>
|
|
<li class="toctree-l1"><a class="reference internal" href="chapter5.html">8. Support Vector Machines, overarching aims</a></li>
|
|
</ul>
|
|
<p aria-level="2" class="caption" role="heading"><span class="caption-text">Decision Trees, Ensemble Methods and Boosting</span></p>
|
|
<ul class="nav bd-sidenav">
|
|
<li class="toctree-l1"><a class="reference internal" href="chapter6.html">9. Decision trees, overarching aims</a></li>
|
|
<li class="toctree-l1"><a class="reference internal" href="chapter7.html">10. Ensemble Methods: From a Single Tree to Many Trees and Extreme Boosting, Meet the Jungle of Methods</a></li>
|
|
</ul>
|
|
<p aria-level="2" class="caption" role="heading"><span class="caption-text">Dimensionality Reduction</span></p>
|
|
<ul class="nav bd-sidenav">
|
|
<li class="toctree-l1"><a class="reference internal" href="chapter8.html">11. Basic ideas of the Principal Component Analysis (PCA)</a></li>
|
|
<li class="toctree-l1"><a class="reference internal" href="clustering.html">12. Clustering and Unsupervised Learning</a></li>
|
|
</ul>
|
|
<p aria-level="2" class="caption" role="heading"><span class="caption-text">Deep Learning Methods</span></p>
|
|
<ul class="nav bd-sidenav">
|
|
<li class="toctree-l1"><a class="reference internal" href="chapter9.html">13. Neural networks</a></li>
|
|
<li class="toctree-l1"><a class="reference internal" href="chapter10.html">14. Building a Feed Forward Neural Network</a></li>
|
|
<li class="toctree-l1"><a class="reference internal" href="chapter11.html">15. Solving Differential Equations with Deep Learning</a></li>
|
|
<li class="toctree-l1"><a class="reference internal" href="chapter12.html">16. Convolutional Neural Networks</a></li>
|
|
<li class="toctree-l1"><a class="reference internal" href="chapter13.html">17. Recurrent neural networks: Overarching view</a></li>
|
|
|
|
</ul>
|
|
<p aria-level="2" class="caption" role="heading"><span class="caption-text">Weekly material, notes and exercises</span></p>
|
|
<ul class="current nav bd-sidenav">
|
|
<li class="toctree-l1"><a class="reference internal" href="exercisesweek34.html">Exercises week 34</a></li>
|
|
<li class="toctree-l1"><a class="reference internal" href="week34.html">Week 34: Introduction to the course, Logistics and Practicalities</a></li>
|
|
<li class="toctree-l1"><a class="reference internal" href="exercisesweek35.html">Exercises week 35</a></li>
|
|
<li class="toctree-l1"><a class="reference internal" href="week35.html">Week 35: From Ordinary Linear Regression to Ridge and Lasso Regression</a></li>
|
|
<li class="toctree-l1"><a class="reference internal" href="exercisesweek36.html">Exercises week 36</a></li>
|
|
<li class="toctree-l1"><a class="reference internal" href="week36.html">Week 36: Linear Regression and Statistical interpretations</a></li>
|
|
<li class="toctree-l1"><a class="reference internal" href="exercisesweek37.html">Exercises week 37</a></li>
|
|
<li class="toctree-l1"><a class="reference internal" href="week37.html">Week 37: Statistical interpretations and Resampling Methods</a></li>
|
|
<li class="toctree-l1 current active"><a class="current reference internal" href="#">Exercises week 38</a></li>
|
|
<li class="toctree-l1"><a class="reference internal" href="week38.html">Week 38: Logistic Regression and Optimization</a></li>
|
|
<li class="toctree-l1"><a class="reference internal" href="exercisesweek39.html">Exercises week 39</a></li>
|
|
<li class="toctree-l1"><a class="reference internal" href="week39.html">Week 39: Optimization and Gradient Methods</a></li>
|
|
<li class="toctree-l1"><a class="reference internal" href="week40.html">Week 40: Gradient descent methods (continued) and start Neural networks</a></li>
|
|
<li class="toctree-l1"><a class="reference internal" href="exercisesweek41.html">Exercises week 41</a></li>
|
|
|
|
|
|
<li class="toctree-l1"><a class="reference internal" href="week41.html">Week 41 Neural networks and constructing a neural network code</a></li>
|
|
<li class="toctree-l1"><a class="reference internal" href="exercisesweek42.html">Exercises week 42</a></li>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
<li class="toctree-l1"><a class="reference internal" href="week42.html">Week 42 Constructing a Neural Network code with examples</a></li>
|
|
<li class="toctree-l1"><a class="reference internal" href="additionweek42.html">Exercises Week 42: Logistic Regression and Optimization, reminders from week 38 and week 40</a></li>
|
|
<li class="toctree-l1"><a class="reference internal" href="week43.html">Week 43: Deep Learning: Constructing a Neural Network code and solving differential equations</a></li>
|
|
<li class="toctree-l1"><a class="reference internal" href="exercisesweek43.html">Exercises week 43</a></li>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
<li class="toctree-l1"><a class="reference internal" href="week44.html">Week 44, Convolutional Neural Networks (CNN)</a></li>
|
|
<li class="toctree-l1"><a class="reference internal" href="week45.html">Week 45, Convolutional Neural Networks (CCNs) and Recurrent Neural Networks (RNNs)</a></li>
|
|
<li class="toctree-l1"><a class="reference internal" href="week46.html">Week 46: Decision Trees, Ensemble methods and Random Forests</a></li>
|
|
<li class="toctree-l1"><a class="reference internal" href="week47.html">Week 47: From Decision Trees to Ensemble Methods, Random Forests and Boosting Methods</a></li>
|
|
<li class="toctree-l1"><a class="reference internal" href="exercisesweek47.html">Exercise week 47</a></li>
|
|
|
|
<li class="toctree-l1"><a class="reference internal" href="week48.html">Week 48: Gradient boosting and summary of course</a></li>
|
|
<li class="toctree-l1"><a class="reference internal" href="exercisesweek48.html">Exercises week 48</a></li>
|
|
|
|
</ul>
|
|
<p aria-level="2" class="caption" role="heading"><span class="caption-text">Projects</span></p>
|
|
<ul class="nav bd-sidenav">
|
|
<li class="toctree-l1"><a class="reference internal" href="project1.html">Project 1 on Machine Learning, deadline October 7 (midnight), 2024</a></li>
|
|
<li class="toctree-l1"><a class="reference internal" href="project2.html">Project 2 on Machine Learning, deadline November 4 (Midnight)</a></li>
|
|
<li class="toctree-l1"><a class="reference internal" href="project3.html">Project 3 on Machine Learning, deadline December 9 (midnight), 2024</a></li>
|
|
|
|
</ul>
|
|
|
|
</div>
|
|
</nav></div>
|
|
</div>
|
|
|
|
|
|
<div class="sidebar-primary-items__end sidebar-primary__section">
|
|
</div>
|
|
|
|
<div id="rtd-footer-container"></div>
|
|
|
|
|
|
</div>
|
|
|
|
<main id="main-content" class="bd-main" role="main">
|
|
|
|
|
|
|
|
<div class="sbt-scroll-pixel-helper"></div>
|
|
|
|
<div class="bd-content">
|
|
<div class="bd-article-container">
|
|
|
|
<div class="bd-header-article d-print-none">
|
|
<div class="header-article-items header-article__inner">
|
|
|
|
<div class="header-article-items__start">
|
|
|
|
<div class="header-article-item"><button class="sidebar-toggle primary-toggle btn btn-sm" title="Toggle primary sidebar" data-bs-placement="bottom" data-bs-toggle="tooltip">
|
|
<span class="fa-solid fa-bars"></span>
|
|
</button></div>
|
|
|
|
</div>
|
|
|
|
|
|
<div class="header-article-items__end">
|
|
|
|
<div class="header-article-item">
|
|
|
|
<div class="article-header-buttons">
|
|
|
|
|
|
|
|
|
|
|
|
<div class="dropdown dropdown-launch-buttons">
|
|
<button class="btn dropdown-toggle" type="button" data-bs-toggle="dropdown" aria-expanded="false" aria-label="Launch interactive content">
|
|
<i class="fas fa-rocket"></i>
|
|
</button>
|
|
<ul class="dropdown-menu">
|
|
|
|
|
|
|
|
<li><a href="https://mybinder.org/v2/git/https%3A//compphysics.github.io/MachineLearning/doc/LectureNotes/_build/html/index.html/master?urlpath=tree/exercisesweek38.ipynb" target="_blank"
|
|
class="btn btn-sm dropdown-item"
|
|
title="Launch on Binder"
|
|
data-bs-placement="left" data-bs-toggle="tooltip"
|
|
>
|
|
|
|
|
|
<span class="btn__icon-container">
|
|
|
|
<img alt="Binder logo" src="_static/images/logo_binder.svg">
|
|
</span>
|
|
<span class="btn__text-container">Binder</span>
|
|
</a>
|
|
</li>
|
|
|
|
</ul>
|
|
</div>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
<div class="dropdown dropdown-download-buttons">
|
|
<button class="btn dropdown-toggle" type="button" data-bs-toggle="dropdown" aria-expanded="false" aria-label="Download this page">
|
|
<i class="fas fa-download"></i>
|
|
</button>
|
|
<ul class="dropdown-menu">
|
|
|
|
|
|
|
|
<li><a href="_sources/exercisesweek38.ipynb" target="_blank"
|
|
class="btn btn-sm btn-download-source-button dropdown-item"
|
|
title="Download source file"
|
|
data-bs-placement="left" data-bs-toggle="tooltip"
|
|
>
|
|
|
|
|
|
<span class="btn__icon-container">
|
|
<i class="fas fa-file"></i>
|
|
</span>
|
|
<span class="btn__text-container">.ipynb</span>
|
|
</a>
|
|
</li>
|
|
|
|
|
|
|
|
|
|
<li>
|
|
<button onclick="window.print()"
|
|
class="btn btn-sm btn-download-pdf-button dropdown-item"
|
|
title="Print to PDF"
|
|
data-bs-placement="left" data-bs-toggle="tooltip"
|
|
>
|
|
|
|
|
|
<span class="btn__icon-container">
|
|
<i class="fas fa-file-pdf"></i>
|
|
</span>
|
|
<span class="btn__text-container">.pdf</span>
|
|
</button>
|
|
</li>
|
|
|
|
</ul>
|
|
</div>
|
|
|
|
|
|
|
|
|
|
<button onclick="toggleFullScreen()"
|
|
class="btn btn-sm btn-fullscreen-button"
|
|
title="Fullscreen mode"
|
|
data-bs-placement="bottom" data-bs-toggle="tooltip"
|
|
>
|
|
|
|
|
|
<span class="btn__icon-container">
|
|
<i class="fas fa-expand"></i>
|
|
</span>
|
|
|
|
</button>
|
|
|
|
|
|
|
|
<button class="btn btn-sm nav-link pst-navbar-icon theme-switch-button pst-js-only" aria-label="Color mode" data-bs-title="Color mode" data-bs-placement="bottom" data-bs-toggle="tooltip">
|
|
<i class="theme-switch fa-solid fa-sun fa-lg" data-mode="light" title="Light"></i>
|
|
<i class="theme-switch fa-solid fa-moon fa-lg" data-mode="dark" title="Dark"></i>
|
|
<i class="theme-switch fa-solid fa-circle-half-stroke fa-lg" data-mode="auto" title="System Settings"></i>
|
|
</button>
|
|
|
|
|
|
<button class="btn btn-sm pst-navbar-icon search-button search-button__button pst-js-only" title="Search" aria-label="Search" data-bs-placement="bottom" data-bs-toggle="tooltip">
|
|
<i class="fa-solid fa-magnifying-glass fa-lg"></i>
|
|
</button>
|
|
<button class="sidebar-toggle secondary-toggle btn btn-sm" title="Toggle secondary sidebar" data-bs-placement="bottom" data-bs-toggle="tooltip">
|
|
<span class="fa-solid fa-list"></span>
|
|
</button>
|
|
</div></div>
|
|
|
|
</div>
|
|
|
|
</div>
|
|
</div>
|
|
|
|
|
|
|
|
<div id="jb-print-docs-body" class="onlyprint">
|
|
<h1>Exercises week 38</h1>
|
|
<!-- Table of contents -->
|
|
<div id="print-main-content">
|
|
<div id="jb-print-toc">
|
|
|
|
<div>
|
|
<h2> Contents </h2>
|
|
</div>
|
|
<nav aria-label="Page">
|
|
<ul class="visible nav section-nav flex-column">
|
|
<li class="toc-h2 nav-item toc-entry"><a class="reference internal nav-link" href="#overarching-aims-of-the-exercises-this-week">Overarching aims of the exercises this week</a></li>
|
|
</ul>
|
|
</nav>
|
|
</div>
|
|
</div>
|
|
</div>
|
|
|
|
|
|
|
|
<div id="searchbox"></div>
|
|
<article class="bd-article">
|
|
|
|
<!-- HTML file automatically generated from DocOnce source (https://github.com/doconce/doconce/)
|
|
doconce format html exercisesweek38.do.txt -->
|
|
<!-- dom:TITLE: Exercises week 38 --><section class="tex2jax_ignore mathjax_ignore" id="exercises-week-38">
|
|
<h1>Exercises week 38<a class="headerlink" href="#exercises-week-38" title="Link to this heading">#</a></h1>
|
|
<p><strong>September 16-20, 2024</strong></p>
|
|
<p>Date: <strong>Deadline is Friday September 20 at midnight</strong></p>
|
|
<section id="overarching-aims-of-the-exercises-this-week">
|
|
<h2>Overarching aims of the exercises this week<a class="headerlink" href="#overarching-aims-of-the-exercises-this-week" title="Link to this heading">#</a></h2>
|
|
<p>The aim of the exercises this week is to derive the equations for the bias-variance tradeoff to be used in project 1 as well as testing this for a simpler function using the bootstrap method. The exercises here can be reused in project 1 as well.</p>
|
|
<p>Consider a
|
|
dataset <span class="math notranslate nohighlight">\(\mathcal{L}\)</span> consisting of the data
|
|
<span class="math notranslate nohighlight">\(\mathbf{X}_\mathcal{L}=\{(y_j, \boldsymbol{x}_j), j=0\ldots n-1\}\)</span>.</p>
|
|
<p>We assume that the true data is generated from a noisy model</p>
|
|
<div class="math notranslate nohighlight">
|
|
\[
|
|
\boldsymbol{y}=f(\boldsymbol{x}) + \boldsymbol{\epsilon}.
|
|
\]</div>
|
|
<p>Here <span class="math notranslate nohighlight">\(\epsilon\)</span> is normally distributed with mean zero and standard
|
|
deviation <span class="math notranslate nohighlight">\(\sigma^2\)</span>.</p>
|
|
<p>In our derivation of the ordinary least squares method we defined
|
|
an approximation to the function <span class="math notranslate nohighlight">\(f\)</span> in terms of the parameters
|
|
<span class="math notranslate nohighlight">\(\boldsymbol{\beta}\)</span> and the design matrix <span class="math notranslate nohighlight">\(\boldsymbol{X}\)</span> which embody our model,
|
|
that is <span class="math notranslate nohighlight">\(\boldsymbol{\tilde{y}}=\boldsymbol{X}\boldsymbol{\beta}\)</span>.</p>
|
|
<p>The parameters <span class="math notranslate nohighlight">\(\boldsymbol{\beta}\)</span> are in turn found by optimizing the mean
|
|
squared error via the so-called cost function</p>
|
|
<div class="math notranslate nohighlight">
|
|
\[
|
|
C(\boldsymbol{X},\boldsymbol{\beta}) =\frac{1}{n}\sum_{i=0}^{n-1}(y_i-\tilde{y}_i)^2=\mathbb{E}\left[(\boldsymbol{y}-\boldsymbol{\tilde{y}})^2\right].
|
|
\]</div>
|
|
<p>Here the expected value <span class="math notranslate nohighlight">\(\mathbb{E}\)</span> is the sample value.</p>
|
|
<p>Show that you can rewrite this in terms of a term which contains the variance of the model itself (the so-called variance term), a
|
|
term which measures the deviation from the true data and the mean value of the model (the bias term) and finally the variance of the noise.
|
|
That is, show that</p>
|
|
<div class="math notranslate nohighlight">
|
|
\[
|
|
\mathbb{E}\left[(\boldsymbol{y}-\boldsymbol{\tilde{y}})^2\right]=\mathrm{Bias}[\tilde{y}]+\mathrm{var}[\tilde{y}]+\sigma^2,
|
|
\]</div>
|
|
<p>with</p>
|
|
<div class="math notranslate nohighlight">
|
|
\[
|
|
\mathrm{Bias}[\tilde{y}]=\mathbb{E}\left[\left(\boldsymbol{y}-\mathbb{E}\left[\boldsymbol{\tilde{y}}\right]\right)^2\right],
|
|
\]</div>
|
|
<p>and</p>
|
|
<div class="math notranslate nohighlight">
|
|
\[
|
|
\mathrm{var}[\tilde{y}]=\mathbb{E}\left[\left(\tilde{\boldsymbol{y}}-\mathbb{E}\left[\boldsymbol{\tilde{y}}\right]\right)^2\right]=\frac{1}{n}\sum_i(\tilde{y}_i-\mathbb{E}\left[\boldsymbol{\tilde{y}}\right])^2.
|
|
\]</div>
|
|
<p>Explain what the terms mean and discuss their interpretations.</p>
|
|
<p>Perform then a bias-variance analysis of a simple one-dimensional (or other models of your choice) function by
|
|
studying the MSE value as function of the complexity of your model. Use ordinary least squares only.</p>
|
|
<p>Discuss the bias and variance trade-off as function
|
|
of your model complexity (the degree of the polynomial) and the number
|
|
of data points, and possibly also your training and test data using the <strong>bootstrap</strong> resampling method.
|
|
You can follow the code example in the jupyter-book at <a class="reference external" href="https://compphysics.github.io/MachineLearning/doc/LectureNotes/_build/html/chapter3.html#the-bias-variance-tradeoff">https://compphysics.github.io/MachineLearning/doc/LectureNotes/_build/html/chapter3.html#the-bias-variance-tradeoff</a>.</p>
|
|
</section>
|
|
</section>
|
|
|
|
<script type="text/x-thebe-config">
|
|
{
|
|
requestKernel: true,
|
|
binderOptions: {
|
|
repo: "binder-examples/jupyter-stacks-datascience",
|
|
ref: "master",
|
|
},
|
|
codeMirrorConfig: {
|
|
theme: "abcdef",
|
|
mode: "python"
|
|
},
|
|
kernelOptions: {
|
|
name: "python3",
|
|
path: "./."
|
|
},
|
|
predefinedOutput: true
|
|
}
|
|
</script>
|
|
<script>kernelName = 'python3'</script>
|
|
|
|
</article>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
<footer class="prev-next-footer d-print-none">
|
|
|
|
<div class="prev-next-area">
|
|
<a class="left-prev"
|
|
href="week37.html"
|
|
title="previous page">
|
|
<i class="fa-solid fa-angle-left"></i>
|
|
<div class="prev-next-info">
|
|
<p class="prev-next-subtitle">previous</p>
|
|
<p class="prev-next-title">Week 37: Statistical interpretations and Resampling Methods</p>
|
|
</div>
|
|
</a>
|
|
<a class="right-next"
|
|
href="week38.html"
|
|
title="next page">
|
|
<div class="prev-next-info">
|
|
<p class="prev-next-subtitle">next</p>
|
|
<p class="prev-next-title">Week 38: Logistic Regression and Optimization</p>
|
|
</div>
|
|
<i class="fa-solid fa-angle-right"></i>
|
|
</a>
|
|
</div>
|
|
</footer>
|
|
|
|
</div>
|
|
|
|
|
|
|
|
<dialog id="pst-secondary-sidebar-modal"></dialog>
|
|
<div id="pst-secondary-sidebar" class="bd-sidebar-secondary bd-toc"><div class="sidebar-secondary-items sidebar-secondary__inner">
|
|
|
|
|
|
<div class="sidebar-secondary-item">
|
|
<div class="page-toc tocsection onthispage">
|
|
<i class="fa-solid fa-list"></i> Contents
|
|
</div>
|
|
<nav class="bd-toc-nav page-toc">
|
|
<ul class="visible nav section-nav flex-column">
|
|
<li class="toc-h2 nav-item toc-entry"><a class="reference internal nav-link" href="#overarching-aims-of-the-exercises-this-week">Overarching aims of the exercises this week</a></li>
|
|
</ul>
|
|
</nav></div>
|
|
|
|
</div></div>
|
|
|
|
|
|
</div>
|
|
<footer class="bd-footer-content">
|
|
|
|
<div class="bd-footer-content__inner container">
|
|
|
|
<div class="footer-item">
|
|
|
|
<p class="component-author">
|
|
By Morten Hjorth-Jensen
|
|
</p>
|
|
|
|
</div>
|
|
|
|
<div class="footer-item">
|
|
|
|
|
|
<p class="copyright">
|
|
|
|
© Copyright 2023.
|
|
<br/>
|
|
|
|
</p>
|
|
|
|
</div>
|
|
|
|
<div class="footer-item">
|
|
|
|
</div>
|
|
|
|
<div class="footer-item">
|
|
|
|
</div>
|
|
|
|
</div>
|
|
</footer>
|
|
|
|
|
|
</main>
|
|
</div>
|
|
</div>
|
|
|
|
<!-- Scripts loaded after <body> so the DOM is not blocked -->
|
|
<script defer src="_static/scripts/bootstrap.js?digest=26a4bc78f4c0ddb94549"></script>
|
|
<script defer src="_static/scripts/pydata-sphinx-theme.js?digest=26a4bc78f4c0ddb94549"></script>
|
|
|
|
<footer class="bd-footer">
|
|
</footer>
|
|
</body>
|
|
</html> |