<p style="text-align:center;">
Yao Ming, Huamin Qu, and Enrico Bertini
</p>
<hr />
<figure>
<img src="/projects/rule-matrix/./teaser.jpg" alt="&quot;teaser&quot;" /><figcaption>"teaser"</figcaption>
</figure>
<h2 id="summary">Summary</h2>
<p>RuleMatrix is an interactive visualization technique that helps users understand the input-output behavior of machine learning models. By viewing a classifier as a black box, we extract a standardized rule-based knowledge representation (a rule list) from its input-output behavior. The extracted rule list is presented as RuleMatrix, a matrix-based visualization, to help users navigate and verify the rules and the black-box model.</p>
<h2 id="software">Software</h2>
<p>The software RuleMatrix and its documentation can be found on <a href="https://github.com/rulematrix/rule-matrix-py">Github</a>.</p>
<h2 id="video-tutorial">Video Tutorial</h2>
<div class="video-container">
<iframe src="//www.youtube.com/embed/r3waU2AhWKE" frameborder="0" allowfullscreen>
</iframe>
</div>
<h2 id="publication">Publication</h2>
<p>Yao Ming, Huamin Qu, Enrico Bertini. <strong>RuleMatrix: Visualizing and Understanding Classifiers using Rules</strong>. <em>IEEE Transactions on Visualization and Computer Graphic, 2018 (to appear)</em>.</p>
<h2 id="materials">Materials</h2>
<p>[<a href="/projects/rule-matrix/./rule-matrix-preprint-jul17.pdf">preprint</a>] | [<a href="https://github.com/rulematrix/rule-matrix-py">code</a>]</p>


RuleMatrix: Visualizing and Understanding Classifiers using Rules