Morten Hjorth-Jensen
488 lines
32 KiB
HTML
488 lines
32 KiB
HTML
<!--
|
|
HTML file automatically generated from DocOnce source
|
|
(https://github.com/doconce/doconce/)
|
|
doconce format html week47.do.txt --html_style=bootstrap --pygments_html_style=default --html_admon=bootstrap_panel --html_output=week47-bs --no_mako
|
|
-->
|
|
<html>
|
|
<head>
|
|
<meta http-equiv="Content-Type" content="text/html; charset=utf-8" />
|
|
<meta name="generator" content="DocOnce: https://github.com/doconce/doconce/" />
|
|
<meta name="viewport" content="width=device-width, initial-scale=1.0" />
|
|
<meta name="description" content="Week 47: Unsupervised learning (PCA and Clustering) and Summary of Course">
|
|
<title>Week 47: Unsupervised learning (PCA and Clustering) and Summary of Course</title>
|
|
<!-- Bootstrap style: bootstrap -->
|
|
<!-- doconce format html week47.do.txt --html_style=bootstrap --pygments_html_style=default --html_admon=bootstrap_panel --html_output=week47-bs --no_mako -->
|
|
<link href="https://netdna.bootstrapcdn.com/bootstrap/3.1.1/css/bootstrap.min.css" rel="stylesheet">
|
|
<!-- not necessary
|
|
<link href="https://netdna.bootstrapcdn.com/font-awesome/4.0.3/css/font-awesome.css" rel="stylesheet">
|
|
-->
|
|
<style type="text/css">
|
|
/* Add scrollbar to dropdown menus in bootstrap navigation bar */
|
|
.dropdown-menu {
|
|
height: auto;
|
|
max-height: 400px;
|
|
overflow-x: hidden;
|
|
}
|
|
/* Adds an invisible element before each target to offset for the navigation
|
|
bar */
|
|
.anchor::before {
|
|
content:"";
|
|
display:block;
|
|
height:50px; /* fixed header height for style bootstrap */
|
|
margin:-50px 0 0; /* negative fixed header height */
|
|
}
|
|
</style>
|
|
</head>
|
|
|
|
<!-- tocinfo
|
|
{'highest level': 2,
|
|
'sections': [('Overview of week 47', 2, None, 'overview-of-week-47'),
|
|
('Basic ideas of the Principal Component Analysis (PCA)',
|
|
2,
|
|
None,
|
|
'basic-ideas-of-the-principal-component-analysis-pca'),
|
|
('Introducing the Covariance and Correlation functions',
|
|
2,
|
|
None,
|
|
'introducing-the-covariance-and-correlation-functions'),
|
|
('More on the covariance', 2, None, 'more-on-the-covariance'),
|
|
('Reminding ourselves about Linear Regression',
|
|
2,
|
|
None,
|
|
'reminding-ourselves-about-linear-regression'),
|
|
('Simple Example', 2, None, 'simple-example'),
|
|
('The Correlation Matrix', 2, None, 'the-correlation-matrix'),
|
|
('Numpy Functionality', 2, None, 'numpy-functionality'),
|
|
('Correlation Matrix again', 2, None, 'correlation-matrix-again'),
|
|
('Using Pandas', 2, None, 'using-pandas'),
|
|
('And then the Franke Function',
|
|
2,
|
|
None,
|
|
'and-then-the-franke-function'),
|
|
('Links with the Design Matrix',
|
|
2,
|
|
None,
|
|
'links-with-the-design-matrix'),
|
|
('Computing the Expectation Values',
|
|
2,
|
|
None,
|
|
'computing-the-expectation-values'),
|
|
('Towards the PCA theorem', 2, None, 'towards-the-pca-theorem'),
|
|
('More on the PCA Theorem', 2, None, 'more-on-the-pca-theorem'),
|
|
("A kind of Bird's view on PCA",
|
|
2,
|
|
None,
|
|
'a-kind-of-bird-s-view-on-pca'),
|
|
('Writing our own PCA code', 2, None, 'writing-our-own-pca-code'),
|
|
('Implementing it', 2, None, 'implementing-it'),
|
|
('First Step', 2, None, 'first-step'),
|
|
('Scaling', 2, None, 'scaling'),
|
|
('Centered Data', 2, None, 'centered-data'),
|
|
('Exploring', 2, None, 'exploring'),
|
|
('Diagonalize the sample covariance matrix to obtain the '
|
|
'principal components',
|
|
2,
|
|
None,
|
|
'diagonalize-the-sample-covariance-matrix-to-obtain-the-principal-components'),
|
|
('Collecting all Steps', 2, None, 'collecting-all-steps'),
|
|
('Classical PCA Theorem', 2, None, 'classical-pca-theorem'),
|
|
('The PCA Theorem', 2, None, 'the-pca-theorem'),
|
|
('Geometric Interpretation and link with Singular Value '
|
|
'Decomposition',
|
|
2,
|
|
None,
|
|
'geometric-interpretation-and-link-with-singular-value-decomposition'),
|
|
('PCA and scikit-learn', 2, None, 'pca-and-scikit-learn'),
|
|
('Back to the Cancer Data', 2, None, 'back-to-the-cancer-data'),
|
|
('Incremental PCA', 2, None, 'incremental-pca'),
|
|
('Randomized PCA', 3, None, 'randomized-pca'),
|
|
('Kernel PCA', 3, None, 'kernel-pca'),
|
|
('Other techniques', 2, None, 'other-techniques'),
|
|
('Clustering and Unsupervised Learning',
|
|
2,
|
|
None,
|
|
'clustering-and-unsupervised-learning'),
|
|
('Basic Idea of the $k$-means Clustering Algorithm',
|
|
2,
|
|
None,
|
|
'basic-idea-of-the-k-means-clustering-algorithm'),
|
|
('The $k$-means Algorithm', 2, None, 'the-k-means-algorithm'),
|
|
('Basic Math of the $k$-means Algorithm',
|
|
2,
|
|
None,
|
|
'basic-math-of-the-k-means-algorithm'),
|
|
('Within Cluster Point Scatter',
|
|
2,
|
|
None,
|
|
'within-cluster-point-scatter'),
|
|
('More Details', 2, None, 'more-details'),
|
|
('Total Cluster Variance', 2, None, 'total-cluster-variance'),
|
|
('The $k$-means Clustering Algorithm',
|
|
2,
|
|
None,
|
|
'the-k-means-clustering-algorithm'),
|
|
('Summarizing', 2, None, 'summarizing'),
|
|
('Writing our own Code, the Data Set',
|
|
2,
|
|
None,
|
|
'writing-our-own-code-the-data-set'),
|
|
('Implementing the $k$-means Algorithm',
|
|
2,
|
|
None,
|
|
'implementing-the-k-means-algorithm'),
|
|
('Plotting', 2, None, 'plotting'),
|
|
('Continuing', 2, None, 'continuing'),
|
|
('Wrapping it up', 2, None, 'wrapping-it-up'),
|
|
('Summary of course', 2, None, 'summary-of-course'),
|
|
('What? Me worry? No final exam in this course!',
|
|
2,
|
|
None,
|
|
'what-me-worry-no-final-exam-in-this-course'),
|
|
('What is the link between Artificial Intelligence and Machine '
|
|
'Learning and some general Remarks',
|
|
2,
|
|
None,
|
|
'what-is-the-link-between-artificial-intelligence-and-machine-learning-and-some-general-remarks'),
|
|
('Going back to the beginning of the semester',
|
|
2,
|
|
None,
|
|
'going-back-to-the-beginning-of-the-semester'),
|
|
('Not so sharp distinctions',
|
|
2,
|
|
None,
|
|
'not-so-sharp-distinctions'),
|
|
('Topics we have covered this year',
|
|
2,
|
|
None,
|
|
'topics-we-have-covered-this-year'),
|
|
('Statistical analysis and optimization of data',
|
|
2,
|
|
None,
|
|
'statistical-analysis-and-optimization-of-data'),
|
|
('Machine learning', 2, None, 'machine-learning'),
|
|
('Learning outcomes and overarching aims of this course',
|
|
2,
|
|
None,
|
|
'learning-outcomes-and-overarching-aims-of-this-course'),
|
|
('Perspective on Machine Learning',
|
|
2,
|
|
None,
|
|
'perspective-on-machine-learning'),
|
|
('Machine Learning Research',
|
|
2,
|
|
None,
|
|
'machine-learning-research'),
|
|
('Starting your Machine Learning Project',
|
|
2,
|
|
None,
|
|
'starting-your-machine-learning-project'),
|
|
('Choose a Model and Algorithm',
|
|
2,
|
|
None,
|
|
'choose-a-model-and-algorithm'),
|
|
('Preparing Your Data', 2, None, 'preparing-your-data'),
|
|
('Which Activation and Weights to Choose in Neural Networks',
|
|
2,
|
|
None,
|
|
'which-activation-and-weights-to-choose-in-neural-networks'),
|
|
('Optimization Methods and Hyperparameters',
|
|
2,
|
|
None,
|
|
'optimization-methods-and-hyperparameters'),
|
|
('Resampling', 2, None, 'resampling'),
|
|
('Other courses on Data science and Machine Learning at UiO',
|
|
2,
|
|
None,
|
|
'other-courses-on-data-science-and-machine-learning-at-uio'),
|
|
('Additional courses of interest',
|
|
2,
|
|
None,
|
|
'additional-courses-of-interest'),
|
|
("What's the future like?", 2, None, 'what-s-the-future-like'),
|
|
('Types of Machine Learning, a repetition',
|
|
2,
|
|
None,
|
|
'types-of-machine-learning-a-repetition'),
|
|
('Why Boltzmann machines?', 2, None, 'why-boltzmann-machines'),
|
|
('Boltzmann Machines', 2, None, 'boltzmann-machines'),
|
|
('Some similarities and differences from DNNs',
|
|
2,
|
|
None,
|
|
'some-similarities-and-differences-from-dnns'),
|
|
('Boltzmann machines (BM)', 2, None, 'boltzmann-machines-bm'),
|
|
('A standard BM setup', 2, None, 'a-standard-bm-setup'),
|
|
('The structure of the RBM network',
|
|
2,
|
|
None,
|
|
'the-structure-of-the-rbm-network'),
|
|
('The network', 2, None, 'the-network'),
|
|
('Goals', 2, None, 'goals'),
|
|
('Joint distribution', 2, None, 'joint-distribution'),
|
|
('Network Elements, the energy function',
|
|
2,
|
|
None,
|
|
'network-elements-the-energy-function'),
|
|
('Defining different types of RBMs',
|
|
2,
|
|
None,
|
|
'defining-different-types-of-rbms'),
|
|
('More about RBMs', 2, None, 'more-about-rbms'),
|
|
('Autoencoders: Overarching view',
|
|
2,
|
|
None,
|
|
'autoencoders-overarching-view'),
|
|
('Bayesian Machine Learning',
|
|
2,
|
|
None,
|
|
'bayesian-machine-learning'),
|
|
('Reinforcement Learning', 2, None, 'reinforcement-learning'),
|
|
('Transfer learning', 2, None, 'transfer-learning'),
|
|
('Adversarial learning', 2, None, 'adversarial-learning'),
|
|
('Dual learning', 2, None, 'dual-learning'),
|
|
('Distributed machine learning',
|
|
2,
|
|
None,
|
|
'distributed-machine-learning'),
|
|
('Meta learning', 2, None, 'meta-learning'),
|
|
('The Challenges Facing Machine Learning',
|
|
2,
|
|
None,
|
|
'the-challenges-facing-machine-learning'),
|
|
('Explainable machine learning',
|
|
2,
|
|
None,
|
|
'explainable-machine-learning'),
|
|
('Scientific Machine Learning',
|
|
2,
|
|
None,
|
|
'scientific-machine-learning'),
|
|
('Quantum machine learning', 2, None, 'quantum-machine-learning'),
|
|
('Quantum machine learning algorithms based on linear algebra',
|
|
2,
|
|
None,
|
|
'quantum-machine-learning-algorithms-based-on-linear-algebra'),
|
|
('Quantum reinforcement learning',
|
|
2,
|
|
None,
|
|
'quantum-reinforcement-learning'),
|
|
('Quantum deep learning', 2, None, 'quantum-deep-learning'),
|
|
('Social machine learning', 2, None, 'social-machine-learning'),
|
|
('The last words?', 2, None, 'the-last-words'),
|
|
('AI/ML and some statements you may have heard (and what do they '
|
|
'mean?)',
|
|
2,
|
|
None,
|
|
'ai-ml-and-some-statements-you-may-have-heard-and-what-do-they-mean'),
|
|
('Best wishes to you all and thanks so much for your heroic '
|
|
'efforts this semester',
|
|
2,
|
|
None,
|
|
'best-wishes-to-you-all-and-thanks-so-much-for-your-heroic-efforts-this-semester')]}
|
|
end of tocinfo -->
|
|
|
|
<body>
|
|
|
|
|
|
|
|
<script type="text/x-mathjax-config">
|
|
MathJax.Hub.Config({
|
|
TeX: {
|
|
equationNumbers: { autoNumber: "none" },
|
|
extensions: ["AMSmath.js", "AMSsymbols.js", "autobold.js", "color.js"]
|
|
}
|
|
});
|
|
</script>
|
|
<script type="text/javascript" async
|
|
src="https://cdnjs.cloudflare.com/ajax/libs/mathjax/2.7.1/MathJax.js?config=TeX-AMS-MML_HTMLorMML">
|
|
</script>
|
|
|
|
|
|
<!-- Bootstrap navigation bar -->
|
|
<div class="navbar navbar-default navbar-fixed-top">
|
|
<div class="navbar-header">
|
|
<button type="button" class="navbar-toggle" data-toggle="collapse" data-target=".navbar-responsive-collapse">
|
|
<span class="icon-bar"></span>
|
|
<span class="icon-bar"></span>
|
|
<span class="icon-bar"></span>
|
|
</button>
|
|
<a class="navbar-brand" href="week47-bs.html">Week 47: Unsupervised learning (PCA and Clustering) and Summary of Course</a>
|
|
</div>
|
|
<div class="navbar-collapse collapse navbar-responsive-collapse">
|
|
<ul class="nav navbar-nav navbar-right">
|
|
<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="._week47-bs001.html#overview-of-week-47" style="font-size: 80%;"><b>Overview of week 47</b></a></li>
|
|
<!-- navigation toc: --> <li><a href="._week47-bs002.html#basic-ideas-of-the-principal-component-analysis-pca" style="font-size: 80%;"><b>Basic ideas of the Principal Component Analysis (PCA)</b></a></li>
|
|
<!-- navigation toc: --> <li><a href="._week47-bs003.html#introducing-the-covariance-and-correlation-functions" style="font-size: 80%;"><b>Introducing the Covariance and Correlation functions</b></a></li>
|
|
<!-- navigation toc: --> <li><a href="._week47-bs004.html#more-on-the-covariance" style="font-size: 80%;"><b>More on the covariance</b></a></li>
|
|
<!-- navigation toc: --> <li><a href="._week47-bs005.html#reminding-ourselves-about-linear-regression" style="font-size: 80%;"><b>Reminding ourselves about Linear Regression</b></a></li>
|
|
<!-- navigation toc: --> <li><a href="._week47-bs006.html#simple-example" style="font-size: 80%;"><b>Simple Example</b></a></li>
|
|
<!-- navigation toc: --> <li><a href="._week47-bs007.html#the-correlation-matrix" style="font-size: 80%;"><b>The Correlation Matrix</b></a></li>
|
|
<!-- navigation toc: --> <li><a href="._week47-bs008.html#numpy-functionality" style="font-size: 80%;"><b>Numpy Functionality</b></a></li>
|
|
<!-- navigation toc: --> <li><a href="._week47-bs009.html#correlation-matrix-again" style="font-size: 80%;"><b>Correlation Matrix again</b></a></li>
|
|
<!-- navigation toc: --> <li><a href="._week47-bs010.html#using-pandas" style="font-size: 80%;"><b>Using Pandas</b></a></li>
|
|
<!-- navigation toc: --> <li><a href="._week47-bs011.html#and-then-the-franke-function" style="font-size: 80%;"><b>And then the Franke Function</b></a></li>
|
|
<!-- navigation toc: --> <li><a href="._week47-bs012.html#links-with-the-design-matrix" style="font-size: 80%;"><b>Links with the Design Matrix</b></a></li>
|
|
<!-- navigation toc: --> <li><a href="._week47-bs013.html#computing-the-expectation-values" style="font-size: 80%;"><b>Computing the Expectation Values</b></a></li>
|
|
<!-- navigation toc: --> <li><a href="._week47-bs014.html#towards-the-pca-theorem" style="font-size: 80%;"><b>Towards the PCA theorem</b></a></li>
|
|
<!-- navigation toc: --> <li><a href="._week47-bs015.html#more-on-the-pca-theorem" style="font-size: 80%;"><b>More on the PCA Theorem</b></a></li>
|
|
<!-- navigation toc: --> <li><a href="._week47-bs016.html#a-kind-of-bird-s-view-on-pca" style="font-size: 80%;"><b>A kind of Bird's view on PCA</b></a></li>
|
|
<!-- navigation toc: --> <li><a href="._week47-bs017.html#writing-our-own-pca-code" style="font-size: 80%;"><b>Writing our own PCA code</b></a></li>
|
|
<!-- navigation toc: --> <li><a href="._week47-bs018.html#implementing-it" style="font-size: 80%;"><b>Implementing it</b></a></li>
|
|
<!-- navigation toc: --> <li><a href="._week47-bs019.html#first-step" style="font-size: 80%;"><b>First Step</b></a></li>
|
|
<!-- navigation toc: --> <li><a href="._week47-bs020.html#scaling" style="font-size: 80%;"><b>Scaling</b></a></li>
|
|
<!-- navigation toc: --> <li><a href="._week47-bs021.html#centered-data" style="font-size: 80%;"><b>Centered Data</b></a></li>
|
|
<!-- navigation toc: --> <li><a href="._week47-bs022.html#exploring" style="font-size: 80%;"><b>Exploring</b></a></li>
|
|
<!-- navigation toc: --> <li><a href="._week47-bs023.html#diagonalize-the-sample-covariance-matrix-to-obtain-the-principal-components" style="font-size: 80%;"><b>Diagonalize the sample covariance matrix to obtain the principal components</b></a></li>
|
|
<!-- navigation toc: --> <li><a href="._week47-bs024.html#collecting-all-steps" style="font-size: 80%;"><b>Collecting all Steps</b></a></li>
|
|
<!-- navigation toc: --> <li><a href="._week47-bs025.html#classical-pca-theorem" style="font-size: 80%;"><b>Classical PCA Theorem</b></a></li>
|
|
<!-- navigation toc: --> <li><a href="._week47-bs026.html#the-pca-theorem" style="font-size: 80%;"><b>The PCA Theorem</b></a></li>
|
|
<!-- navigation toc: --> <li><a href="._week47-bs027.html#geometric-interpretation-and-link-with-singular-value-decomposition" style="font-size: 80%;"><b>Geometric Interpretation and link with Singular Value Decomposition</b></a></li>
|
|
<!-- navigation toc: --> <li><a href="._week47-bs028.html#pca-and-scikit-learn" style="font-size: 80%;"><b>PCA and scikit-learn</b></a></li>
|
|
<!-- navigation toc: --> <li><a href="._week47-bs029.html#back-to-the-cancer-data" style="font-size: 80%;"><b>Back to the Cancer Data</b></a></li>
|
|
<!-- navigation toc: --> <li><a href="._week47-bs030.html#incremental-pca" style="font-size: 80%;"><b>Incremental PCA</b></a></li>
|
|
<!-- navigation toc: --> <li><a href="._week47-bs030.html#randomized-pca" style="font-size: 80%;"> Randomized PCA</a></li>
|
|
<!-- navigation toc: --> <li><a href="._week47-bs030.html#kernel-pca" style="font-size: 80%;"> Kernel PCA</a></li>
|
|
<!-- navigation toc: --> <li><a href="._week47-bs031.html#other-techniques" style="font-size: 80%;"><b>Other techniques</b></a></li>
|
|
<!-- navigation toc: --> <li><a href="._week47-bs032.html#clustering-and-unsupervised-learning" style="font-size: 80%;"><b>Clustering and Unsupervised Learning</b></a></li>
|
|
<!-- navigation toc: --> <li><a href="._week47-bs033.html#basic-idea-of-the-k-means-clustering-algorithm" style="font-size: 80%;"><b>Basic Idea of the \( k \)-means Clustering Algorithm</b></a></li>
|
|
<!-- navigation toc: --> <li><a href="._week47-bs034.html#the-k-means-algorithm" style="font-size: 80%;"><b>The \( k \)-means Algorithm</b></a></li>
|
|
<!-- navigation toc: --> <li><a href="._week47-bs035.html#basic-math-of-the-k-means-algorithm" style="font-size: 80%;"><b>Basic Math of the \( k \)-means Algorithm</b></a></li>
|
|
<!-- navigation toc: --> <li><a href="._week47-bs036.html#within-cluster-point-scatter" style="font-size: 80%;"><b>Within Cluster Point Scatter</b></a></li>
|
|
<!-- navigation toc: --> <li><a href="._week47-bs037.html#more-details" style="font-size: 80%;"><b>More Details</b></a></li>
|
|
<!-- navigation toc: --> <li><a href="._week47-bs038.html#total-cluster-variance" style="font-size: 80%;"><b>Total Cluster Variance</b></a></li>
|
|
<!-- navigation toc: --> <li><a href="._week47-bs039.html#the-k-means-clustering-algorithm" style="font-size: 80%;"><b>The \( k \)-means Clustering Algorithm</b></a></li>
|
|
<!-- navigation toc: --> <li><a href="._week47-bs040.html#summarizing" style="font-size: 80%;"><b>Summarizing</b></a></li>
|
|
<!-- navigation toc: --> <li><a href="._week47-bs041.html#writing-our-own-code-the-data-set" style="font-size: 80%;"><b>Writing our own Code, the Data Set</b></a></li>
|
|
<!-- navigation toc: --> <li><a href="._week47-bs042.html#implementing-the-k-means-algorithm" style="font-size: 80%;"><b>Implementing the \( k \)-means Algorithm</b></a></li>
|
|
<!-- navigation toc: --> <li><a href="._week47-bs043.html#plotting" style="font-size: 80%;"><b>Plotting</b></a></li>
|
|
<!-- navigation toc: --> <li><a href="._week47-bs044.html#continuing" style="font-size: 80%;"><b>Continuing</b></a></li>
|
|
<!-- navigation toc: --> <li><a href="._week47-bs045.html#wrapping-it-up" style="font-size: 80%;"><b>Wrapping it up</b></a></li>
|
|
<!-- navigation toc: --> <li><a href="._week47-bs046.html#summary-of-course" style="font-size: 80%;"><b>Summary of course</b></a></li>
|
|
<!-- navigation toc: --> <li><a href="._week47-bs047.html#what-me-worry-no-final-exam-in-this-course" style="font-size: 80%;"><b>What? Me worry? No final exam in this course!</b></a></li>
|
|
<!-- navigation toc: --> <li><a href="._week47-bs048.html#what-is-the-link-between-artificial-intelligence-and-machine-learning-and-some-general-remarks" style="font-size: 80%;"><b>What is the link between Artificial Intelligence and Machine Learning and some general Remarks</b></a></li>
|
|
<!-- navigation toc: --> <li><a href="._week47-bs049.html#going-back-to-the-beginning-of-the-semester" style="font-size: 80%;"><b>Going back to the beginning of the semester</b></a></li>
|
|
<!-- navigation toc: --> <li><a href="._week47-bs050.html#not-so-sharp-distinctions" style="font-size: 80%;"><b>Not so sharp distinctions</b></a></li>
|
|
<!-- navigation toc: --> <li><a href="._week47-bs051.html#topics-we-have-covered-this-year" style="font-size: 80%;"><b>Topics we have covered this year</b></a></li>
|
|
<!-- navigation toc: --> <li><a href="._week47-bs052.html#statistical-analysis-and-optimization-of-data" style="font-size: 80%;"><b>Statistical analysis and optimization of data</b></a></li>
|
|
<!-- navigation toc: --> <li><a href="._week47-bs053.html#machine-learning" style="font-size: 80%;"><b>Machine learning</b></a></li>
|
|
<!-- navigation toc: --> <li><a href="._week47-bs054.html#learning-outcomes-and-overarching-aims-of-this-course" style="font-size: 80%;"><b>Learning outcomes and overarching aims of this course</b></a></li>
|
|
<!-- navigation toc: --> <li><a href="._week47-bs055.html#perspective-on-machine-learning" style="font-size: 80%;"><b>Perspective on Machine Learning</b></a></li>
|
|
<!-- navigation toc: --> <li><a href="._week47-bs056.html#machine-learning-research" style="font-size: 80%;"><b>Machine Learning Research</b></a></li>
|
|
<!-- navigation toc: --> <li><a href="._week47-bs057.html#starting-your-machine-learning-project" style="font-size: 80%;"><b>Starting your Machine Learning Project</b></a></li>
|
|
<!-- navigation toc: --> <li><a href="._week47-bs058.html#choose-a-model-and-algorithm" style="font-size: 80%;"><b>Choose a Model and Algorithm</b></a></li>
|
|
<!-- navigation toc: --> <li><a href="._week47-bs059.html#preparing-your-data" style="font-size: 80%;"><b>Preparing Your Data</b></a></li>
|
|
<!-- navigation toc: --> <li><a href="._week47-bs060.html#which-activation-and-weights-to-choose-in-neural-networks" style="font-size: 80%;"><b>Which Activation and Weights to Choose in Neural Networks</b></a></li>
|
|
<!-- navigation toc: --> <li><a href="._week47-bs061.html#optimization-methods-and-hyperparameters" style="font-size: 80%;"><b>Optimization Methods and Hyperparameters</b></a></li>
|
|
<!-- navigation toc: --> <li><a href="._week47-bs062.html#resampling" style="font-size: 80%;"><b>Resampling</b></a></li>
|
|
<!-- navigation toc: --> <li><a href="._week47-bs063.html#other-courses-on-data-science-and-machine-learning-at-uio" style="font-size: 80%;"><b>Other courses on Data science and Machine Learning at UiO</b></a></li>
|
|
<!-- navigation toc: --> <li><a href="._week47-bs064.html#additional-courses-of-interest" style="font-size: 80%;"><b>Additional courses of interest</b></a></li>
|
|
<!-- navigation toc: --> <li><a href="#what-s-the-future-like" style="font-size: 80%;"><b>What's the future like?</b></a></li>
|
|
<!-- navigation toc: --> <li><a href="._week47-bs066.html#types-of-machine-learning-a-repetition" style="font-size: 80%;"><b>Types of Machine Learning, a repetition</b></a></li>
|
|
<!-- navigation toc: --> <li><a href="._week47-bs067.html#why-boltzmann-machines" style="font-size: 80%;"><b>Why Boltzmann machines?</b></a></li>
|
|
<!-- navigation toc: --> <li><a href="._week47-bs068.html#boltzmann-machines" style="font-size: 80%;"><b>Boltzmann Machines</b></a></li>
|
|
<!-- navigation toc: --> <li><a href="._week47-bs069.html#some-similarities-and-differences-from-dnns" style="font-size: 80%;"><b>Some similarities and differences from DNNs</b></a></li>
|
|
<!-- navigation toc: --> <li><a href="._week47-bs070.html#boltzmann-machines-bm" style="font-size: 80%;"><b>Boltzmann machines (BM)</b></a></li>
|
|
<!-- navigation toc: --> <li><a href="._week47-bs071.html#a-standard-bm-setup" style="font-size: 80%;"><b>A standard BM setup</b></a></li>
|
|
<!-- navigation toc: --> <li><a href="._week47-bs072.html#the-structure-of-the-rbm-network" style="font-size: 80%;"><b>The structure of the RBM network</b></a></li>
|
|
<!-- navigation toc: --> <li><a href="._week47-bs073.html#the-network" style="font-size: 80%;"><b>The network</b></a></li>
|
|
<!-- navigation toc: --> <li><a href="._week47-bs074.html#goals" style="font-size: 80%;"><b>Goals</b></a></li>
|
|
<!-- navigation toc: --> <li><a href="._week47-bs075.html#joint-distribution" style="font-size: 80%;"><b>Joint distribution</b></a></li>
|
|
<!-- navigation toc: --> <li><a href="._week47-bs076.html#network-elements-the-energy-function" style="font-size: 80%;"><b>Network Elements, the energy function</b></a></li>
|
|
<!-- navigation toc: --> <li><a href="._week47-bs077.html#defining-different-types-of-rbms" style="font-size: 80%;"><b>Defining different types of RBMs</b></a></li>
|
|
<!-- navigation toc: --> <li><a href="._week47-bs078.html#more-about-rbms" style="font-size: 80%;"><b>More about RBMs</b></a></li>
|
|
<!-- navigation toc: --> <li><a href="._week47-bs079.html#autoencoders-overarching-view" style="font-size: 80%;"><b>Autoencoders: Overarching view</b></a></li>
|
|
<!-- navigation toc: --> <li><a href="._week47-bs080.html#bayesian-machine-learning" style="font-size: 80%;"><b>Bayesian Machine Learning</b></a></li>
|
|
<!-- navigation toc: --> <li><a href="._week47-bs081.html#reinforcement-learning" style="font-size: 80%;"><b>Reinforcement Learning</b></a></li>
|
|
<!-- navigation toc: --> <li><a href="._week47-bs082.html#transfer-learning" style="font-size: 80%;"><b>Transfer learning</b></a></li>
|
|
<!-- navigation toc: --> <li><a href="._week47-bs083.html#adversarial-learning" style="font-size: 80%;"><b>Adversarial learning</b></a></li>
|
|
<!-- navigation toc: --> <li><a href="._week47-bs084.html#dual-learning" style="font-size: 80%;"><b>Dual learning</b></a></li>
|
|
<!-- navigation toc: --> <li><a href="._week47-bs085.html#distributed-machine-learning" style="font-size: 80%;"><b>Distributed machine learning</b></a></li>
|
|
<!-- navigation toc: --> <li><a href="._week47-bs086.html#meta-learning" style="font-size: 80%;"><b>Meta learning</b></a></li>
|
|
<!-- navigation toc: --> <li><a href="._week47-bs087.html#the-challenges-facing-machine-learning" style="font-size: 80%;"><b>The Challenges Facing Machine Learning</b></a></li>
|
|
<!-- navigation toc: --> <li><a href="._week47-bs088.html#explainable-machine-learning" style="font-size: 80%;"><b>Explainable machine learning</b></a></li>
|
|
<!-- navigation toc: --> <li><a href="._week47-bs089.html#scientific-machine-learning" style="font-size: 80%;"><b>Scientific Machine Learning</b></a></li>
|
|
<!-- navigation toc: --> <li><a href="._week47-bs090.html#quantum-machine-learning" style="font-size: 80%;"><b>Quantum machine learning</b></a></li>
|
|
<!-- navigation toc: --> <li><a href="._week47-bs091.html#quantum-machine-learning-algorithms-based-on-linear-algebra" style="font-size: 80%;"><b>Quantum machine learning algorithms based on linear algebra</b></a></li>
|
|
<!-- navigation toc: --> <li><a href="._week47-bs092.html#quantum-reinforcement-learning" style="font-size: 80%;"><b>Quantum reinforcement learning</b></a></li>
|
|
<!-- navigation toc: --> <li><a href="._week47-bs093.html#quantum-deep-learning" style="font-size: 80%;"><b>Quantum deep learning</b></a></li>
|
|
<!-- navigation toc: --> <li><a href="._week47-bs094.html#social-machine-learning" style="font-size: 80%;"><b>Social machine learning</b></a></li>
|
|
<!-- navigation toc: --> <li><a href="._week47-bs095.html#the-last-words" style="font-size: 80%;"><b>The last words?</b></a></li>
|
|
<!-- navigation toc: --> <li><a href="._week47-bs096.html#ai-ml-and-some-statements-you-may-have-heard-and-what-do-they-mean" style="font-size: 80%;"><b>AI/ML and some statements you may have heard (and what do they mean?)</b></a></li>
|
|
<!-- navigation toc: --> <li><a href="._week47-bs097.html#best-wishes-to-you-all-and-thanks-so-much-for-your-heroic-efforts-this-semester" style="font-size: 80%;"><b>Best wishes to you all and thanks so much for your heroic efforts this semester</b></a></li>
|
|
|
|
</ul>
|
|
</li>
|
|
</ul>
|
|
</div>
|
|
</div>
|
|
</div> <!-- end of navigation bar -->
|
|
<div class="container">
|
|
<p> </p><p> </p><p> </p> <!-- add vertical space -->
|
|
<a name="part0065"></a>
|
|
<!-- !split -->
|
|
<h2 id="what-s-the-future-like" class="anchor">What's the future like? </h2>
|
|
|
|
<p>Based on multi-layer nonlinear neural networks, deep learning can
|
|
learn directly from raw data, automatically extract and abstract
|
|
features from layer to layer, and then achieve the goal of regression,
|
|
classification, or ranking. Deep learning has made breakthroughs in
|
|
computer vision, speech processing and natural language, and reached
|
|
or even surpassed human level. The success of deep learning is mainly
|
|
due to the three factors: big data, big model, and big computing.
|
|
</p>
|
|
|
|
<p>In the past few decades, many different architectures of deep neural
|
|
networks have been proposed, such as
|
|
</p>
|
|
<ol>
|
|
<li> Convolutional neural networks, which are mostly used in image and video data processing, and have also been applied to sequential data such as text processing;</li>
|
|
<li> Recurrent neural networks, which can process sequential data of variable length and have been widely used in natural language understanding and speech processing;</li>
|
|
<li> Encoder-decoder framework, which is mostly used for image or sequence generation, such as machine translation, text summarization, and image captioning.</li>
|
|
</ol>
|
|
<p>
|
|
<!-- navigation buttons at the bottom of the page -->
|
|
<ul class="pagination">
|
|
<li><a href="._week47-bs064.html">«</a></li>
|
|
<li><a href="._week47-bs000.html">1</a></li>
|
|
<li><a href="">...</a></li>
|
|
<li><a href="._week47-bs057.html">58</a></li>
|
|
<li><a href="._week47-bs058.html">59</a></li>
|
|
<li><a href="._week47-bs059.html">60</a></li>
|
|
<li><a href="._week47-bs060.html">61</a></li>
|
|
<li><a href="._week47-bs061.html">62</a></li>
|
|
<li><a href="._week47-bs062.html">63</a></li>
|
|
<li><a href="._week47-bs063.html">64</a></li>
|
|
<li><a href="._week47-bs064.html">65</a></li>
|
|
<li class="active"><a href="._week47-bs065.html">66</a></li>
|
|
<li><a href="._week47-bs066.html">67</a></li>
|
|
<li><a href="._week47-bs067.html">68</a></li>
|
|
<li><a href="._week47-bs068.html">69</a></li>
|
|
<li><a href="._week47-bs069.html">70</a></li>
|
|
<li><a href="._week47-bs070.html">71</a></li>
|
|
<li><a href="._week47-bs071.html">72</a></li>
|
|
<li><a href="._week47-bs072.html">73</a></li>
|
|
<li><a href="._week47-bs073.html">74</a></li>
|
|
<li><a href="._week47-bs074.html">75</a></li>
|
|
<li><a href="">...</a></li>
|
|
<li><a href="._week47-bs097.html">98</a></li>
|
|
<li><a href="._week47-bs066.html">»</a></li>
|
|
</ul>
|
|
<!-- ------------------- end of main content --------------- -->
|
|
</div> <!-- end container -->
|
|
<!-- include javascript, jQuery *first* -->
|
|
<script src="https://ajax.googleapis.com/ajax/libs/jquery/1.10.2/jquery.min.js"></script>
|
|
<script src="https://netdna.bootstrapcdn.com/bootstrap/3.0.0/js/bootstrap.min.js"></script>
|
|
<!-- Bootstrap footer
|
|
<footer>
|
|
<a href="https://..."><img width="250" align=right src="https://..."></a>
|
|
</footer>
|
|
-->
|
|
<center style="font-size:80%">
|
|
<!-- copyright only on the titlepage -->
|
|
</center>
|
|
</body>
|
|
</html>
|
|
|