StackOverflow2013

Note that there are some explanatory texts on larger screens.

plurals

POLiterature on many-vs-many classifier
text
Body
copied!<p>In the context of <a href="http://en.wikipedia.org/wiki/Multiclass_classification" rel="nofollow">Multi-Class Classification</a> (MCC) problem, a common approach is to build final solution from multiple binary classifiers. Two composition strategy typically mentioned are one-vs-all and one-vs-one.</p> <p>In order to distinguish the approach, it is clearer to look at what each binary classifier attempt to do. One-vs-all's primitive classifier attempt to separate just one class from the rest. Whereas one-vs-one's primitive attempts to separate one against <a href="http://www.mit.edu/~9.520/spring09/Classes/multiclass.pdf" rel="nofollow">One-vs-one is also, quite confusingly, called all-vs-all and all-pairs.</a></p> <p>I want to investigate this rather simple idea of building MCC classifier by composing binary classifier in binary-decision-tree-like manner. For an illustrative example:</p> <pre><code> has wings? / \ quack? nyan? / \ / \ duck bird cat dog </code></pre> <p>As you can see the <code>has wings?</code> does a 2-vs-2 classification, so I am calling the approach many-vs-many. <strong>The problem is</strong>, I don't know where to start reading. Is there a good paper you would recommend?</p> <p>To give a bit more context, I'm considering using a multilevel evolutionary algorithm (MLEA) to build the tree. So if there is an even more direct answer, it would be most welcomed.</p> <p><strong>Edit</strong>: For more context (and perhaps you might find it useful), I read <a href="http://dl.acm.org/citation.cfm?id=2001576.2001765" rel="nofollow">this paper</a> which is one of the <a href="http://www.sigevo.org/wiki/tiki-index.php?page=GECCO%20Best%20Paper%20Awards" rel="nofollow">GECCO 2011 best paper</a> winners; It uses MLEA to compose MCC in one-vs-all manner. This is what inspired me to look for a way to modify it as decision tree builder.</p>

Querying!

Guidance

An individual column

Larger individual text columns get their own page to allow for proper reading.

SQuiL has stopped working due to an internal error.

If you are curious you may find further information in the browser console, which is accessible through the devtools (F12).

Reload