Data

Tools

Indexes

Applications

Experiments

Open Source Science

bit

Forked template from Christoph Molnar, testing out website integration

https://github.com/firmai/bit

Science Score: 44.0%

This score indicates how likely this project is to be science-related based on various indicators:

  • ✓
    CITATION.cff file
    Found CITATION.cff file
  • ✓
    codemeta.json file
    Found codemeta.json file
  • ✓
    .zenodo.json file
    Found .zenodo.json file
  • ○
    DOI references
  • ○
    Academic links in README
  • ○
    Academic email domains
  • ○
    Institutional organization owner
  • ○
    JOSS paper metadata
  • ○
    Scientific vocabulary similarity
    Low similarity (0.6%) to scientific vocabulary
Last synced: 9 months ago · JSON representation ·

Repository

Forked template from Christoph Molnar, testing out website integration

Basic Info
Statistics
  • Stars: 1
  • Watchers: 1
  • Forks: 3
  • Open Issues: 0
  • Releases: 0
Created over 7 years ago · Last pushed almost 7 years ago
Metadata Files
Citation

Owner

  • Name: Derek Snow
  • Login: firmai
  • Kind: user
  • Company: NYU | Sov.ai

Citation (citation.html) 

<!DOCTYPE html>
<html >

<head>

  <meta charset="UTF-8">
  <meta http-equiv="X-UA-Compatible" content="IE=edge">
  <title>Interpretable Machine Learning</title>
  <meta name="description" content="Machine learning algorithms usually operate as black boxes and it is unclear how they derived a certain decision. This book is a guide for practitioners on how to make machine learning decisions more interpretable.">
  <meta name="generator" content="bookdown 0.7 and GitBook 2.6.7">

  <meta property="og:title" content="Interpretable Machine Learning" />
  <meta property="og:type" content="book" />
  
  
  <meta property="og:description" content="Machine learning algorithms usually operate as black boxes and it is unclear how they derived a certain decision. This book is a guide for practitioners on how to make machine learning decisions more interpretable." />
  <meta name="github-repo" content="christophM/interpretable-ml-book" />

  <meta name="twitter:card" content="summary" />
  <meta name="twitter:title" content="Interpretable Machine Learning" />
  
  <meta name="twitter:description" content="Machine learning algorithms usually operate as black boxes and it is unclear how they derived a certain decision. This book is a guide for practitioners on how to make machine learning decisions more interpretable." />
  

<meta name="author" content="Christoph Molnar">


<meta name="date" content="2018-10-14">

  <meta name="viewport" content="width=device-width, initial-scale=1">
  <meta name="apple-mobile-web-app-capable" content="yes">
  <meta name="apple-mobile-web-app-status-bar-style" content="black">
  
  
<link rel="prev" href="contribute.html">
<link rel="next" href="acknowledgements.html">
<script src="libs/jquery-2.2.3/jquery.min.js"></script>
<link href="libs/gitbook-2.6.7/css/style.css" rel="stylesheet" />
<link href="libs/gitbook-2.6.7/css/plugin-bookdown.css" rel="stylesheet" />
<link href="libs/gitbook-2.6.7/css/plugin-highlight.css" rel="stylesheet" />
<link href="libs/gitbook-2.6.7/css/plugin-search.css" rel="stylesheet" />
<link href="libs/gitbook-2.6.7/css/plugin-fontsettings.css" rel="stylesheet" />







<!-- Global site tag (gtag.js) - Google Analytics -->
<script>
(function(i,s,o,g,r,a,m){i['GoogleAnalyticsObject']=r;i[r]=i[r]||function(){
(i[r].q=i[r].q||[]).push(arguments)},i[r].l=1*new Date();a=s.createElement(o),
m=s.getElementsByTagName(o)[0];a.async=1;a.src=g;m.parentNode.insertBefore(a,m)
})(window,document,'script','//www.google-analytics.com/analytics.js','ga');

ga('create', 'UA-110543840-1', 'https://christophm.github.io/interpretable-ml-book/', {
  'anonymizeIp': true
  , 'storage': 'none'
  , 'clientId': window.localStorage.getItem('ga_clientId')
});
ga(function(tracker) {
  window.localStorage.setItem('ga_clientId', tracker.get('clientId'));
});
ga('send', 'pageview');
</script>

<link rel="stylesheet" type="text/css" href="css/cookieconsent.min.css" />
<script src="javascript/cookieconsent.min.js"></script>
<script>
window.addEventListener("load", function(){
window.cookieconsent.initialise({
  "palette": {
    "popup": {
      "background": "#000"
    },
    "button": {
      "background": "#f1d600"
    }
  },
  "position": "bottom-right",
  "content": {
    "message": "This website uses cookies for Google Analytics so that I know how many people are reading the book and which chapters are the most popular. The book website doesn't collect any personal data."
  }
})});
</script>



<link rel="stylesheet" href="css/style.css" type="text/css" />
</head>

<body>



  <div class="book without-animation with-summary font-size-2 font-family-1" data-basepath=".">

    <div class="book-summary">
      <nav role="navigation">

<ul class="summary">
<li><a href="./">Interpretable machine learning</a></li>

<li class="divider"></li>
<li class="chapter" data-level="1" data-path="index.html"><a href="index.html"><i class="fa fa-check"></i><b>1</b> Preface</a></li>
<li class="chapter" data-level="2" data-path="intro.html"><a href="intro.html"><i class="fa fa-check"></i><b>2</b> Introduction</a><ul>
<li class="chapter" data-level="2.1" data-path="storytime.html"><a href="storytime.html"><i class="fa fa-check"></i><b>2.1</b> Storytime</a><ul>
<li class="chapter" data-level="" data-path="storytime.html"><a href="storytime.html#lightning-never-strikes-twice"><i class="fa fa-check"></i>Lightning Never Strikes Twice</a></li>
<li class="chapter" data-level="" data-path="storytime.html"><a href="storytime.html#trust-fall"><i class="fa fa-check"></i>Trust Fall</a></li>
<li class="chapter" data-level="" data-path="storytime.html"><a href="storytime.html#fermis-paperclips"><i class="fa fa-check"></i>Fermi’s Paperclips</a></li>
</ul></li>
<li class="chapter" data-level="2.2" data-path="what-is-machine-learning.html"><a href="what-is-machine-learning.html"><i class="fa fa-check"></i><b>2.2</b> What Is Machine Learning?</a></li>
<li class="chapter" data-level="2.3" data-path="definitions.html"><a href="definitions.html"><i class="fa fa-check"></i><b>2.3</b> Definitions</a></li>
</ul></li>
<li class="chapter" data-level="3" data-path="interpretability.html"><a href="interpretability.html"><i class="fa fa-check"></i><b>3</b> Interpretability</a><ul>
<li class="chapter" data-level="3.1" data-path="interpretability-importance.html"><a href="interpretability-importance.html"><i class="fa fa-check"></i><b>3.1</b> The Importance of Interpretability</a></li>
<li class="chapter" data-level="3.2" data-path="criteria-for-interpretability-methods.html"><a href="criteria-for-interpretability-methods.html"><i class="fa fa-check"></i><b>3.2</b> Criteria for Interpretability Methods</a></li>
<li class="chapter" data-level="3.3" data-path="scope-of-interpretability.html"><a href="scope-of-interpretability.html"><i class="fa fa-check"></i><b>3.3</b> Scope of Interpretability</a><ul>
<li class="chapter" data-level="3.3.1" data-path="scope-of-interpretability.html"><a href="scope-of-interpretability.html#algorithm-transparency"><i class="fa fa-check"></i><b>3.3.1</b> Algorithm transparency</a></li>
<li class="chapter" data-level="3.3.2" data-path="scope-of-interpretability.html"><a href="scope-of-interpretability.html#global-holistic-model-interpretability"><i class="fa fa-check"></i><b>3.3.2</b> Global, Holistic Model Interpretability</a></li>
<li class="chapter" data-level="3.3.3" data-path="scope-of-interpretability.html"><a href="scope-of-interpretability.html#global-model-interpretability-on-a-modular-level"><i class="fa fa-check"></i><b>3.3.3</b> Global Model Interpretability on a Modular Level</a></li>
<li class="chapter" data-level="3.3.4" data-path="scope-of-interpretability.html"><a href="scope-of-interpretability.html#local-interpretability-for-a-single-prediction"><i class="fa fa-check"></i><b>3.3.4</b> Local Interpretability for a Single Prediction</a></li>
<li class="chapter" data-level="3.3.5" data-path="scope-of-interpretability.html"><a href="scope-of-interpretability.html#local-interpretability-for-a-group-of-predictions"><i class="fa fa-check"></i><b>3.3.5</b> Local Interpretability for a Group of Predictions</a></li>
</ul></li>
<li class="chapter" data-level="3.4" data-path="evaluating-interpretability.html"><a href="evaluating-interpretability.html"><i class="fa fa-check"></i><b>3.4</b> Evaluating Interpretability</a></li>
<li class="chapter" data-level="3.5" data-path="explanation.html"><a href="explanation.html"><i class="fa fa-check"></i><b>3.5</b> Human-friendly Explanations</a><ul>
<li class="chapter" data-level="3.5.1" data-path="explanation.html"><a href="explanation.html#what-is-an-explanation"><i class="fa fa-check"></i><b>3.5.1</b> What is an explanation?</a></li>
<li class="chapter" data-level="3.5.2" data-path="explanation.html"><a href="explanation.html#good-explanation"><i class="fa fa-check"></i><b>3.5.2</b> What is a “good” explanation?</a></li>
</ul></li>
</ul></li>
<li class="chapter" data-level="4" data-path="data.html"><a href="data.html"><i class="fa fa-check"></i><b>4</b> Datasets</a><ul>
<li class="chapter" data-level="4.1" data-path="bike-data.html"><a href="bike-data.html"><i class="fa fa-check"></i><b>4.1</b> Bike Sharing Counts (Regression)</a></li>
<li class="chapter" data-level="4.2" data-path="spam-data.html"><a href="spam-data.html"><i class="fa fa-check"></i><b>4.2</b> YouTube Spam Comments (Text Classification)</a></li>
<li class="chapter" data-level="4.3" data-path="cervical.html"><a href="cervical.html"><i class="fa fa-check"></i><b>4.3</b> Risk Factors for Cervical Cancer (Classification)</a></li>
</ul></li>
<li class="chapter" data-level="5" data-path="simple.html"><a href="simple.html"><i class="fa fa-check"></i><b>5</b> Interpretable Models</a><ul>
<li class="chapter" data-level="5.1" data-path="limo.html"><a href="limo.html"><i class="fa fa-check"></i><b>5.1</b> Linear Model</a><ul>
<li class="chapter" data-level="5.1.1" data-path="limo.html"><a href="limo.html#interpretation"><i class="fa fa-check"></i><b>5.1.1</b> Interpretation</a></li>
<li class="chapter" data-level="5.1.2" data-path="limo.html"><a href="limo.html#interpretation-example"><i class="fa fa-check"></i><b>5.1.2</b> Interpretation Example</a></li>
<li class="chapter" data-level="5.1.3" data-path="limo.html"><a href="limo.html#interpretation-templates"><i class="fa fa-check"></i><b>5.1.3</b> Interpretation templates</a></li>
<li class="chapter" data-level="5.1.4" data-path="limo.html"><a href="limo.html#visual-parameter-interpretation"><i class="fa fa-check"></i><b>5.1.4</b> Visual parameter interpretation</a></li>
<li class="chapter" data-level="5.1.5" data-path="limo.html"><a href="limo.html#explaining-single-predictions"><i class="fa fa-check"></i><b>5.1.5</b> Explaining Single Predictions</a></li>
<li class="chapter" data-level="5.1.6" data-path="limo.html"><a href="limo.html#cat-code"><i class="fa fa-check"></i><b>5.1.6</b> Coding Categorical Features</a></li>
<li class="chapter" data-level="5.1.7" data-path="limo.html"><a href="limo.html#the-disadvantages-of-linear-models"><i class="fa fa-check"></i><b>5.1.7</b> The disadvantages of linear models</a></li>
<li class="chapter" data-level="5.1.8" data-path="limo.html"><a href="limo.html#do-linear-models-create-good-explanations"><i class="fa fa-check"></i><b>5.1.8</b> Do linear models create good explanations?</a></li>
<li class="chapter" data-level="5.1.9" data-path="limo.html"><a href="limo.html#extending-linear-models"><i class="fa fa-check"></i><b>5.1.9</b> Extending Linear Models</a></li>
<li class="chapter" data-level="5.1.10" data-path="limo.html"><a href="limo.html#sparse-linear"><i class="fa fa-check"></i><b>5.1.10</b> Sparse linear models</a></li>
</ul></li>
<li class="chapter" data-level="5.2" data-path="logistic.html"><a href="logistic.html"><i class="fa fa-check"></i><b>5.2</b> Logistic Regression</a><ul>
<li class="chapter" data-level="5.2.1" data-path="logistic.html"><a href="logistic.html#whats-wrong-with-linear-regression-models-for-classification"><i class="fa fa-check"></i><b>5.2.1</b> What’s Wrong with Linear Regression Models for Classification?</a></li>
<li class="chapter" data-level="5.2.2" data-path="logistic.html"><a href="logistic.html#logistic-regression"><i class="fa fa-check"></i><b>5.2.2</b> Logistic Regression</a></li>
<li class="chapter" data-level="5.2.3" data-path="logistic.html"><a href="logistic.html#interpretation-1"><i class="fa fa-check"></i><b>5.2.3</b> Interpretation</a></li>
<li class="chapter" data-level="5.2.4" data-path="logistic.html"><a href="logistic.html#example"><i class="fa fa-check"></i><b>5.2.4</b> Example</a></li>
</ul></li>
<li class="chapter" data-level="5.3" data-path="tree.html"><a href="tree.html"><i class="fa fa-check"></i><b>5.3</b> Decision Tree</a><ul>
<li class="chapter" data-level="5.3.1" data-path="tree.html"><a href="tree.html#interpretation-2"><i class="fa fa-check"></i><b>5.3.1</b> Interpretation</a></li>
<li class="chapter" data-level="5.3.2" data-path="tree.html"><a href="tree.html#interpretation-example-1"><i class="fa fa-check"></i><b>5.3.2</b> Interpretation Example</a></li>
<li class="chapter" data-level="5.3.3" data-path="tree.html"><a href="tree.html#advantages"><i class="fa fa-check"></i><b>5.3.3</b> Advantages</a></li>
<li class="chapter" data-level="5.3.4" data-path="tree.html"><a href="tree.html#disadvantages"><i class="fa fa-check"></i><b>5.3.4</b> Disadvantages</a></li>
</ul></li>
<li class="chapter" data-level="5.4" data-path="rules.html"><a href="rules.html"><i class="fa fa-check"></i><b>5.4</b> Decision Rules (IF-THEN)</a><ul>
<li class="chapter" data-level="5.4.1" data-path="rules.html"><a href="rules.html#learn-rules-from-a-single-feature-oner"><i class="fa fa-check"></i><b>5.4.1</b> Learn Rules from a Single Feature (OneR)</a></li>
<li class="chapter" data-level="5.4.2" data-path="rules.html"><a href="rules.html#sequential-covering"><i class="fa fa-check"></i><b>5.4.2</b> Sequential Covering</a></li>
<li class="chapter" data-level="5.4.3" data-path="rules.html"><a href="rules.html#bayesian-rule-lists"><i class="fa fa-check"></i><b>5.4.3</b> Bayesian Rule Lists</a></li>
<li class="chapter" data-level="5.4.4" data-path="rules.html"><a href="rules.html#advantages-1"><i class="fa fa-check"></i><b>5.4.4</b> Advantages</a></li>
<li class="chapter" data-level="5.4.5" data-path="rules.html"><a href="rules.html#disadvantages-1"><i class="fa fa-check"></i><b>5.4.5</b> Disadvantages</a></li>
<li class="chapter" data-level="5.4.6" data-path="rules.html"><a href="rules.html#software-and-alternatives"><i class="fa fa-check"></i><b>5.4.6</b> Software and Alternatives</a></li>
</ul></li>
<li class="chapter" data-level="5.5" data-path="rulefit.html"><a href="rulefit.html"><i class="fa fa-check"></i><b>5.5</b> RuleFit</a><ul>
<li class="chapter" data-level="5.5.1" data-path="rulefit.html"><a href="rulefit.html#interpretation-and-example"><i class="fa fa-check"></i><b>5.5.1</b> Interpretation and Example</a></li>
<li class="chapter" data-level="5.5.2" data-path="rulefit.html"><a href="rulefit.html#guidelines"><i class="fa fa-check"></i><b>5.5.2</b> Guidelines</a></li>
<li class="chapter" data-level="5.5.3" data-path="rulefit.html"><a href="rulefit.html#theory"><i class="fa fa-check"></i><b>5.5.3</b> Theory</a></li>
</ul></li>
<li class="chapter" data-level="5.6" data-path="other-interpretable.html"><a href="other-interpretable.html"><i class="fa fa-check"></i><b>5.6</b> Other Interpretable Models</a><ul>
<li class="chapter" data-level="5.6.1" data-path="other-interpretable.html"><a href="other-interpretable.html#naive-bayes-classifier"><i class="fa fa-check"></i><b>5.6.1</b> Naive Bayes classifier</a></li>
<li class="chapter" data-level="5.6.2" data-path="other-interpretable.html"><a href="other-interpretable.html#k-nearest-neighbours"><i class="fa fa-check"></i><b>5.6.2</b> K-Nearest Neighbours</a></li>
<li class="chapter" data-level="5.6.3" data-path="other-interpretable.html"><a href="other-interpretable.html#and-so-many-more"><i class="fa fa-check"></i><b>5.6.3</b> And so many more …</a></li>
</ul></li>
</ul></li>
<li class="chapter" data-level="6" data-path="agnostic.html"><a href="agnostic.html"><i class="fa fa-check"></i><b>6</b> Model-Agnostic Methods</a><ul>
<li class="chapter" data-level="6.1" data-path="pdp.html"><a href="pdp.html"><i class="fa fa-check"></i><b>6.1</b> Partial Dependence Plot (PDP)</a><ul>
<li class="chapter" data-level="6.1.1" data-path="pdp.html"><a href="pdp.html#examples"><i class="fa fa-check"></i><b>6.1.1</b> Examples</a></li>
<li class="chapter" data-level="6.1.2" data-path="pdp.html"><a href="pdp.html#advantages-2"><i class="fa fa-check"></i><b>6.1.2</b> Advantages</a></li>
<li class="chapter" data-level="6.1.3" data-path="pdp.html"><a href="pdp.html#disadvantages-2"><i class="fa fa-check"></i><b>6.1.3</b> Disadvantages</a></li>
</ul></li>
<li class="chapter" data-level="6.2" data-path="ice.html"><a href="ice.html"><i class="fa fa-check"></i><b>6.2</b> Individual Conditional Expectation (ICE)</a><ul>
<li class="chapter" data-level="6.2.1" data-path="ice.html"><a href="ice.html#example-1"><i class="fa fa-check"></i><b>6.2.1</b> Example</a></li>
<li class="chapter" data-level="6.2.2" data-path="ice.html"><a href="ice.html#advantages-3"><i class="fa fa-check"></i><b>6.2.2</b> Advantages</a></li>
<li class="chapter" data-level="6.2.3" data-path="ice.html"><a href="ice.html#disadvantages-3"><i class="fa fa-check"></i><b>6.2.3</b> Disadvantages</a></li>
</ul></li>
<li class="chapter" data-level="6.3" data-path="ale.html"><a href="ale.html"><i class="fa fa-check"></i><b>6.3</b> Accumulated Local Effects (ALE) Plot</a><ul>
<li class="chapter" data-level="6.3.1" data-path="ale.html"><a href="ale.html#motivation-and-intuition"><i class="fa fa-check"></i><b>6.3.1</b> Motivation and Intuition</a></li>
<li class="chapter" data-level="6.3.2" data-path="ale.html"><a href="ale.html#theory-1"><i class="fa fa-check"></i><b>6.3.2</b> Theory</a></li>
<li class="chapter" data-level="6.3.3" data-path="ale.html"><a href="ale.html#estimation"><i class="fa fa-check"></i><b>6.3.3</b> Estimation</a></li>
<li class="chapter" data-level="6.3.4" data-path="ale.html"><a href="ale.html#examples-1"><i class="fa fa-check"></i><b>6.3.4</b> Examples</a></li>
<li class="chapter" data-level="6.3.5" data-path="ale.html"><a href="ale.html#advantages-4"><i class="fa fa-check"></i><b>6.3.5</b> Advantages</a></li>
<li class="chapter" data-level="6.3.6" data-path="ale.html"><a href="ale.html#disadvantages-4"><i class="fa fa-check"></i><b>6.3.6</b> Disadvantages</a></li>
<li class="chapter" data-level="6.3.7" data-path="ale.html"><a href="ale.html#implementation-and-alternatives"><i class="fa fa-check"></i><b>6.3.7</b> Implementation and Alternatives</a></li>
</ul></li>
<li class="chapter" data-level="6.4" data-path="interaction.html"><a href="interaction.html"><i class="fa fa-check"></i><b>6.4</b> Feature Interaction</a><ul>
<li class="chapter" data-level="6.4.1" data-path="interaction.html"><a href="interaction.html#feature-interaction"><i class="fa fa-check"></i><b>6.4.1</b> Feature Interaction?</a></li>
<li class="chapter" data-level="6.4.2" data-path="interaction.html"><a href="interaction.html#theory-friedmans-h-statistic"><i class="fa fa-check"></i><b>6.4.2</b> Theory: Friedman’s H-statistic</a></li>
<li class="chapter" data-level="6.4.3" data-path="interaction.html"><a href="interaction.html#examples-2"><i class="fa fa-check"></i><b>6.4.3</b> Examples</a></li>
<li class="chapter" data-level="6.4.4" data-path="interaction.html"><a href="interaction.html#advantages-5"><i class="fa fa-check"></i><b>6.4.4</b> Advantages</a></li>
<li class="chapter" data-level="6.4.5" data-path="interaction.html"><a href="interaction.html#disadvantages-5"><i class="fa fa-check"></i><b>6.4.5</b> Disadvantages</a></li>
<li class="chapter" data-level="6.4.6" data-path="interaction.html"><a href="interaction.html#implementations"><i class="fa fa-check"></i><b>6.4.6</b> Implementations</a></li>
<li class="chapter" data-level="6.4.7" data-path="interaction.html"><a href="interaction.html#alternatives"><i class="fa fa-check"></i><b>6.4.7</b> Alternatives</a></li>
</ul></li>
<li class="chapter" data-level="6.5" data-path="feature-importance.html"><a href="feature-importance.html"><i class="fa fa-check"></i><b>6.5</b> Feature Importance</a><ul>
<li class="chapter" data-level="6.5.1" data-path="feature-importance.html"><a href="feature-importance.html#the-theory"><i class="fa fa-check"></i><b>6.5.1</b> The Theory</a></li>
<li class="chapter" data-level="6.5.2" data-path="feature-importance.html"><a href="feature-importance.html#example-and-interpretation"><i class="fa fa-check"></i><b>6.5.2</b> Example and Interpretation</a></li>
<li class="chapter" data-level="6.5.3" data-path="feature-importance.html"><a href="feature-importance.html#advantages-6"><i class="fa fa-check"></i><b>6.5.3</b> Advantages</a></li>
<li class="chapter" data-level="6.5.4" data-path="feature-importance.html"><a href="feature-importance.html#disadvantages-6"><i class="fa fa-check"></i><b>6.5.4</b> Disadvantages</a></li>
</ul></li>
<li class="chapter" data-level="6.6" data-path="global.html"><a href="global.html"><i class="fa fa-check"></i><b>6.6</b> Global Surrogate Models</a><ul>
<li class="chapter" data-level="6.6.1" data-path="global.html"><a href="global.html#theory-2"><i class="fa fa-check"></i><b>6.6.1</b> Theory</a></li>
<li class="chapter" data-level="6.6.2" data-path="global.html"><a href="global.html#example-3"><i class="fa fa-check"></i><b>6.6.2</b> Example</a></li>
<li class="chapter" data-level="6.6.3" data-path="global.html"><a href="global.html#advantages-7"><i class="fa fa-check"></i><b>6.6.3</b> Advantages</a></li>
<li class="chapter" data-level="6.6.4" data-path="global.html"><a href="global.html#disadvantages-7"><i class="fa fa-check"></i><b>6.6.4</b> Disadvantages</a></li>
</ul></li>
<li class="chapter" data-level="6.7" data-path="lime.html"><a href="lime.html"><i class="fa fa-check"></i><b>6.7</b> Local Surrogate Models (LIME)</a><ul>
<li class="chapter" data-level="6.7.1" data-path="lime.html"><a href="lime.html#lime-for-tabular-data"><i class="fa fa-check"></i><b>6.7.1</b> LIME for Tabular Data</a></li>
<li class="chapter" data-level="6.7.2" data-path="lime.html"><a href="lime.html#lime-for-text"><i class="fa fa-check"></i><b>6.7.2</b> LIME for Text</a></li>
<li class="chapter" data-level="6.7.3" data-path="lime.html"><a href="lime.html#images-lime"><i class="fa fa-check"></i><b>6.7.3</b> LIME for Images</a></li>
</ul></li>
<li class="chapter" data-level="6.8" data-path="shapley.html"><a href="shapley.html"><i class="fa fa-check"></i><b>6.8</b> Shapley Value Explanations</a><ul>
<li class="chapter" data-level="6.8.1" data-path="shapley.html"><a href="shapley.html#the-general-idea"><i class="fa fa-check"></i><b>6.8.1</b> The general idea</a></li>
<li class="chapter" data-level="6.8.2" data-path="shapley.html"><a href="shapley.html#examples-and-interpretation"><i class="fa fa-check"></i><b>6.8.2</b> Examples and Interpretation</a></li>
<li class="chapter" data-level="6.8.3" data-path="shapley.html"><a href="shapley.html#the-shapley-value-in-detail"><i class="fa fa-check"></i><b>6.8.3</b> The Shapley Value in Detail</a></li>
<li class="chapter" data-level="6.8.4" data-path="shapley.html"><a href="shapley.html#advantages-8"><i class="fa fa-check"></i><b>6.8.4</b> Advantages</a></li>
<li class="chapter" data-level="6.8.5" data-path="shapley.html"><a href="shapley.html#disadvantages-8"><i class="fa fa-check"></i><b>6.8.5</b> Disadvantages</a></li>
</ul></li>
</ul></li>
<li class="chapter" data-level="7" data-path="example-based.html"><a href="example-based.html"><i class="fa fa-check"></i><b>7</b> Example-based Explanations</a><ul>
<li class="chapter" data-level="7.1" data-path="counterfactual.html"><a href="counterfactual.html"><i class="fa fa-check"></i><b>7.1</b> Counterfactual explanations</a><ul>
<li class="chapter" data-level="7.1.1" data-path="counterfactual.html"><a href="counterfactual.html#generating-counterfactual-explanations"><i class="fa fa-check"></i><b>7.1.1</b> Generating counterfactual explanations</a></li>
<li class="chapter" data-level="7.1.2" data-path="counterfactual.html"><a href="counterfactual.html#examples-3"><i class="fa fa-check"></i><b>7.1.2</b> Examples</a></li>
<li class="chapter" data-level="7.1.3" data-path="counterfactual.html"><a href="counterfactual.html#advantages-9"><i class="fa fa-check"></i><b>7.1.3</b> Advantages</a></li>
<li class="chapter" data-level="7.1.4" data-path="counterfactual.html"><a href="counterfactual.html#disadvantages-9"><i class="fa fa-check"></i><b>7.1.4</b> Disadvantages</a></li>
<li class="chapter" data-level="7.1.5" data-path="counterfactual.html"><a href="counterfactual.html#example-software"><i class="fa fa-check"></i><b>7.1.5</b> Software and Alternatives</a></li>
</ul></li>
<li class="chapter" data-level="7.2" data-path="adversarial.html"><a href="adversarial.html"><i class="fa fa-check"></i><b>7.2</b> Adversarial Examples</a><ul>
<li class="chapter" data-level="7.2.1" data-path="adversarial.html"><a href="adversarial.html#methods-and-examples"><i class="fa fa-check"></i><b>7.2.1</b> Methods and Examples</a></li>
<li class="chapter" data-level="7.2.2" data-path="adversarial.html"><a href="adversarial.html#the-cybersecurity-perspective"><i class="fa fa-check"></i><b>7.2.2</b> The Cybersecurity Perspective</a></li>
</ul></li>
<li class="chapter" data-level="7.3" data-path="proto.html"><a href="proto.html"><i class="fa fa-check"></i><b>7.3</b> Prototypes and Criticisms</a><ul>
<li class="chapter" data-level="7.3.1" data-path="proto.html"><a href="proto.html#theory-3"><i class="fa fa-check"></i><b>7.3.1</b> Theory</a></li>
<li class="chapter" data-level="7.3.2" data-path="proto.html"><a href="proto.html#examples-4"><i class="fa fa-check"></i><b>7.3.2</b> Examples</a></li>
<li class="chapter" data-level="7.3.3" data-path="proto.html"><a href="proto.html#advantages-10"><i class="fa fa-check"></i><b>7.3.3</b> Advantages</a></li>
<li class="chapter" data-level="7.3.4" data-path="proto.html"><a href="proto.html#disadvantages-10"><i class="fa fa-check"></i><b>7.3.4</b> Disadvantages</a></li>
<li class="chapter" data-level="7.3.5" data-path="proto.html"><a href="proto.html#code-and-alternatives"><i class="fa fa-check"></i><b>7.3.5</b> Code and Alternatives</a></li>
</ul></li>
<li class="chapter" data-level="7.4" data-path="influential.html"><a href="influential.html"><i class="fa fa-check"></i><b>7.4</b> Influential Instances</a><ul>
<li class="chapter" data-level="7.4.1" data-path="influential.html"><a href="influential.html#deletion-diagnostics"><i class="fa fa-check"></i><b>7.4.1</b> Deletion Diagnostics</a></li>
<li class="chapter" data-level="7.4.2" data-path="influential.html"><a href="influential.html#influence-functions"><i class="fa fa-check"></i><b>7.4.2</b> Influence Functions</a></li>
<li class="chapter" data-level="7.4.3" data-path="influential.html"><a href="influential.html#advantages-of-identifying-influential-instances"><i class="fa fa-check"></i><b>7.4.3</b> Advantages of Identifying Influential Instances</a></li>
<li class="chapter" data-level="7.4.4" data-path="influential.html"><a href="influential.html#disadvantages-of-identifying-influential-instances"><i class="fa fa-check"></i><b>7.4.4</b> Disadvantages of Identifying Influential Instances</a></li>
<li class="chapter" data-level="7.4.5" data-path="influential.html"><a href="influential.html#software-and-alternatives-1"><i class="fa fa-check"></i><b>7.4.5</b> Software and Alternatives</a></li>
</ul></li>
</ul></li>
<li class="chapter" data-level="8" data-path="future.html"><a href="future.html"><i class="fa fa-check"></i><b>8</b> A Look into the Crystal Ball</a><ul>
<li class="chapter" data-level="8.1" data-path="the-future-of-machine-learning.html"><a href="the-future-of-machine-learning.html"><i class="fa fa-check"></i><b>8.1</b> The Future of Machine Learning</a></li>
<li class="chapter" data-level="8.2" data-path="the-future-of-interpretability.html"><a href="the-future-of-interpretability.html"><i class="fa fa-check"></i><b>8.2</b> The Future of Interpretability</a></li>
</ul></li>
<li class="chapter" data-level="9" data-path="contribute.html"><a href="contribute.html"><i class="fa fa-check"></i><b>9</b> Contribute</a></li>
<li class="chapter" data-level="10" data-path="citation.html"><a href="citation.html"><i class="fa fa-check"></i><b>10</b> Citation</a></li>
<li class="chapter" data-level="11" data-path="acknowledgements.html"><a href="acknowledgements.html"><i class="fa fa-check"></i><b>11</b> Acknowledgements</a></li>
<li class="divider"></li>
<li><a href="https://bookdown.org" target="blank">Published with bookdown</a></li>

</ul>

      </nav>
    </div>

    <div class="book-body">
      <div class="body-inner">
        <div class="book-header" role="navigation">
          <h1>
            <i class="fa fa-circle-o-notch fa-spin"></i><a href="./">Interpretable Machine Learning</a>
          </h1>
        </div>

        <div class="page-wrapper" tabindex="-1" role="main">
          <div class="page-inner">

            <section class="normal" id="section-">
<div id="citation" class="section level1">
<h1><span class="header-section-number">Chapter 10</span> Citation</h1>
<p>Cite the book like this:</p>
<pre><code>Molnar, C. (2018). Interpretable Machine Learning. Retrieved from https://christophm.github.io/interpretable-ml-book/</code></pre>
<p>Or use the following bibtex entry:</p>
<pre><code>@book{molnar,
  title = {Interpretable Machine Learning},
  author = {Christoph Molnar},
  publisher = {https://christophm.github.io/interpretable-ml-book/},
  note = {\url{https://christophm.github.io/interpretable-ml-book/}},
  year = {2018}
}</code></pre>
<p>If you use the book as a reference, it would be great if you write me a line and tell me what for.
This is of course optional and only serves to satisfy my own curiosity and perhaps to spark interesting exchanges.
My mail is <a href="mailto:christoph.molnar.ai@gmail.com">christoph.molnar.ai@gmail.com</a> .</p>

</div>
            </section>

          </div>
        </div>
      </div>
<a href="contribute.html" class="navigation navigation-prev " aria-label="Previous page"><i class="fa fa-angle-left"></i></a>
<a href="acknowledgements.html" class="navigation navigation-next " aria-label="Next page"><i class="fa fa-angle-right"></i></a>
    </div>
  </div>
<script src="libs/gitbook-2.6.7/js/app.min.js"></script>
<script src="libs/gitbook-2.6.7/js/lunr.js"></script>
<script src="libs/gitbook-2.6.7/js/plugin-search.js"></script>
<script src="libs/gitbook-2.6.7/js/plugin-sharing.js"></script>
<script src="libs/gitbook-2.6.7/js/plugin-fontsettings.js"></script>
<script src="libs/gitbook-2.6.7/js/plugin-bookdown.js"></script>
<script src="libs/gitbook-2.6.7/js/jquery.highlight.js"></script>
<script>
gitbook.require(["gitbook"], function(gitbook) {
gitbook.start({
"sharing": {
"github": true,
"facebook": true,
"twitter": true,
"google": false,
"linkedin": false,
"weibo": false,
"instapper": false,
"vk": false,
"all": ["facebook", "google", "twitter", "linkedin", "weibo", "instapaper"]
},
"fontsettings": {
"theme": "white",
"family": "sans",
"size": 2
},
"edit": {
"link": "https://github.com/christophM/interpretable-ml-book/edit/master/08-contribute.Rmd",
"text": "Edit"
},
"download": null,
"toc": {
"collapse": "subsection"
}
});
});
</script>

<!-- dynamically load mathjax for compatibility with self-contained -->
<script>
  (function () {
    var script = document.createElement("script");
    script.type = "text/javascript";
    var src = "true";
    if (src === "" || src === "true") src = "https://cdn.bootcss.com/mathjax/2.7.1/MathJax.js?config=TeX-MML-AM_CHTML";
    if (location.protocol !== "file:" && /^https?:/.test(src))
      src = src.replace(/^https?:/, '');
    script.src = src;
    document.getElementsByTagName("head")[0].appendChild(script);
  })();
</script>
</body>

</html>

GitHub Events

Total
Last Year

Issues and Pull Requests

Last synced: about 1 year ago

All Time
  • Total issues: 0
  • Total pull requests: 0
  • Average time to close issues: N/A
  • Average time to close pull requests: N/A
  • Total issue authors: 0
  • Total pull request authors: 0
  • Average comments per issue: 0
  • Average comments per pull request: 0
  • Merged pull requests: 0
  • Bot issues: 0
  • Bot pull requests: 0
Past Year
  • Issues: 0
  • Pull requests: 0
  • Average time to close issues: N/A
  • Average time to close pull requests: N/A
  • Issue authors: 0
  • Pull request authors: 0
  • Average comments per issue: 0
  • Average comments per pull request: 0
  • Merged pull requests: 0
  • Bot issues: 0
  • Bot pull requests: 0
View more stats
Top Authors
Issue Authors
Pull Request Authors
Top Labels
Issue Labels
Pull Request Labels