<?xml version="1.0" encoding="utf-8"?><rss version="2.0"
	xmlns:content="http://purl.org/rss/1.0/modules/content/"
	xmlns:dc="http://purl.org/dc/elements/1.1/"
	xmlns:atom="http://www.w3.org/2005/Atom"
	>
<channel>
	<title>Comments on: Decision Tree Learning in Ruby</title>
	<atom:link href="http://www.igvita.com/2007/04/16/decision-tree-learning-in-ruby/feed/" rel="self" type="application/rss+xml" />
	<link>http://www.igvita.com/2007/04/16/decision-tree-learning-in-ruby/</link>
	<description>A goal is a dream with a deadline.</description>
	<pubDate>Sun, 20 Jul 2008 21:48:23 +0000</pubDate>
	<generator>http://wordpress.org/?v=2.5.1</generator>
		<item>
		<title>By: Ilya Grigorik</title>
		<link>http://www.igvita.com/2007/04/16/decision-tree-learning-in-ruby/#comment-102114</link>
		<dc:creator>Ilya Grigorik</dc:creator>
		<pubDate>Tue, 18 Mar 2008 12:37:34 +0000</pubDate>
		<guid isPermaLink="false">http://www.igvita.com/blog/2007/04/16/decision-tree-learning-in-ruby/#comment-102114</guid>
		<description>Thanks Raf! 

Amir, Pireland, &lt;a href="http://www.igvita.com/2008/01/07/support-vector-machines-svm-in-ruby/" rel="nofollow"&gt;svm article&lt;/a&gt;, as Raf suggested.</description>
		<content:encoded><![CDATA[<p>Thanks Raf! </p>
<p>Amir, Pireland, <a href="http://www.igvita.com/2008/01/07/support-vector-machines-svm-in-ruby/" rel="nofollow">svm article</a>, as Raf suggested.</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: Raf</title>
		<link>http://www.igvita.com/2007/04/16/decision-tree-learning-in-ruby/#comment-101901</link>
		<dc:creator>Raf</dc:creator>
		<pubDate>Mon, 10 Mar 2008 16:53:55 +0000</pubDate>
		<guid isPermaLink="false">http://www.igvita.com/blog/2007/04/16/decision-tree-learning-in-ruby/#comment-101901</guid>
		<description>Privet, nu ti postaralsa!

Great article! 

To Amir and Pireland, you can try  SVM as well for your purposes.</description>
		<content:encoded><![CDATA[<p>Privet, nu ti postaralsa!</p>
<p>Great article! </p>
<p>To Amir and Pireland, you can try  SVM as well for your purposes.</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: 筆記與流年 &#187; links for 2008-03-02</title>
		<link>http://www.igvita.com/2007/04/16/decision-tree-learning-in-ruby/#comment-101735</link>
		<dc:creator>筆記與流年 &#187; links for 2008-03-02</dc:creator>
		<pubDate>Sun, 02 Mar 2008 16:25:12 +0000</pubDate>
		<guid isPermaLink="false">http://www.igvita.com/blog/2007/04/16/decision-tree-learning-in-ruby/#comment-101735</guid>
		<description>[...] Decision Tree Learning in Ruby - igvita.com (tags: ruby machinelearning tree classification) [...]</description>
		<content:encoded><![CDATA[<p>[...] Decision Tree Learning in Ruby - igvita.com (tags: ruby machinelearning tree classification) [...]</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: Magisterarbeit &#187; Blog Archive &#187; Andere Methoden zu quantitativen Klassifizierung</title>
		<link>http://www.igvita.com/2007/04/16/decision-tree-learning-in-ruby/#comment-95171</link>
		<dc:creator>Magisterarbeit &#187; Blog Archive &#187; Andere Methoden zu quantitativen Klassifizierung</dc:creator>
		<pubDate>Mon, 03 Dec 2007 07:21:39 +0000</pubDate>
		<guid isPermaLink="false">http://www.igvita.com/blog/2007/04/16/decision-tree-learning-in-ruby/#comment-95171</guid>
		<description>[...] Hier sind noch zwei Beispiele, wie eine Klassifizierung gemacht werden kann. Die erste Methode ist der Entscheidungsbaum (siehe Decision Tree Learning in Ruby, bzw. Building Decision Trees in Python). Wie bei Bayesschen Filtern sind auch Entscheidungsbäume künstliche Intelligenzen, die aus Beispielen lernen und die erlernten Regeln auf neue Beispiele anwenden, um zu einer Entscheidung oder Klassifizierung zu kommen. Auch hierzu gibt es eine praktische Ruby-Bibliothek: decisiontree. Kann einfach über &#8220;gem install decisiontree&#8221; installiert werden. [...]</description>
		<content:encoded><![CDATA[<p>[...] Hier sind noch zwei Beispiele, wie eine Klassifizierung gemacht werden kann. Die erste Methode ist der Entscheidungsbaum (siehe Decision Tree Learning in Ruby, bzw. Building Decision Trees in Python). Wie bei Bayesschen Filtern sind auch Entscheidungsbäume künstliche Intelligenzen, die aus Beispielen lernen und die erlernten Regeln auf neue Beispiele anwenden, um zu einer Entscheidung oder Klassifizierung zu kommen. Auch hierzu gibt es eine praktische Ruby-Bibliothek: decisiontree. Kann einfach über &#8220;gem install decisiontree&#8221; installiert werden. [...]</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: Ilya Grigorik</title>
		<link>http://www.igvita.com/2007/04/16/decision-tree-learning-in-ruby/#comment-83192</link>
		<dc:creator>Ilya Grigorik</dc:creator>
		<pubDate>Thu, 08 Nov 2007 15:49:23 +0000</pubDate>
		<guid isPermaLink="false">http://www.igvita.com/blog/2007/04/16/decision-tree-learning-in-ruby/#comment-83192</guid>
		<description>Amir, if that's the case, I would seriously look at neural nets. Decision trees are best for simple, linear-type classification. If you have a huge dataset, it is likely that you'll need something beyond a linear separating function. 

Also, neural nets are very compact when it comes to storage requirements.</description>
		<content:encoded><![CDATA[<p>Amir, if that&#8217;s the case, I would seriously look at neural nets. Decision trees are best for simple, linear-type classification. If you have a huge dataset, it is likely that you&#8217;ll need something beyond a linear separating function. </p>
<p>Also, neural nets are very compact when it comes to storage requirements.</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: I am just a programmer &#187; Decision Tree Learning in Ruby</title>
		<link>http://www.igvita.com/2007/04/16/decision-tree-learning-in-ruby/#comment-82747</link>
		<dc:creator>I am just a programmer &#187; Decision Tree Learning in Ruby</dc:creator>
		<pubDate>Wed, 07 Nov 2007 15:54:27 +0000</pubDate>
		<guid isPermaLink="false">http://www.igvita.com/blog/2007/04/16/decision-tree-learning-in-ruby/#comment-82747</guid>
		<description>[...] read more &#124; digg story [...]</description>
		<content:encoded><![CDATA[<p>[...] read more | digg story [...]</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: Amir</title>
		<link>http://www.igvita.com/2007/04/16/decision-tree-learning-in-ruby/#comment-82130</link>
		<dc:creator>Amir</dc:creator>
		<pubDate>Tue, 06 Nov 2007 07:49:22 +0000</pubDate>
		<guid isPermaLink="false">http://www.igvita.com/blog/2007/04/16/decision-tree-learning-in-ruby/#comment-82130</guid>
		<description>What if the training data set is big like few hundred thousand rows. do you have any suggestion to improve the performance and not overload the memory?</description>
		<content:encoded><![CDATA[<p>What if the training data set is big like few hundred thousand rows. do you have any suggestion to improve the performance and not overload the memory?</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: Ilya Grigorik</title>
		<link>http://www.igvita.com/2007/04/16/decision-tree-learning-in-ruby/#comment-81069</link>
		<dc:creator>Ilya Grigorik</dc:creator>
		<pubDate>Sat, 03 Nov 2007 15:09:21 +0000</pubDate>
		<guid isPermaLink="false">http://www.igvita.com/blog/2007/04/16/decision-tree-learning-in-ruby/#comment-81069</guid>
		<description>Doug, that's awesome, I'm glad you found the gem useful. Interesting application as well!</description>
		<content:encoded><![CDATA[<p>Doug, that&#8217;s awesome, I&#8217;m glad you found the gem useful. Interesting application as well!</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: doug</title>
		<link>http://www.igvita.com/2007/04/16/decision-tree-learning-in-ruby/#comment-80848</link>
		<dc:creator>doug</dc:creator>
		<pubDate>Fri, 02 Nov 2007 16:33:52 +0000</pubDate>
		<guid isPermaLink="false">http://www.igvita.com/blog/2007/04/16/decision-tree-learning-in-ruby/#comment-80848</guid>
		<description>Hi Ilya:  I've relied a lot on your new Gem for a prof. project related to predicting outcomes in legal disputes.  The downside is that the Gem is so complete that have running code but still don't have a solid understanding of the underlying theory though having running code to do test runs, etc. certainly helps with that. Anyway, your dt Gem is an excellent API, thanks. (Also good to find others from Minsk--many people i meet don't even know where it is!)
--doug</description>
		<content:encoded><![CDATA[<p>Hi Ilya:  I&#8217;ve relied a lot on your new Gem for a prof. project related to predicting outcomes in legal disputes.  The downside is that the Gem is so complete that have running code but still don&#8217;t have a solid understanding of the underlying theory though having running code to do test runs, etc. certainly helps with that. Anyway, your dt Gem is an excellent API, thanks. (Also good to find others from Minsk&#8211;many people i meet don&#8217;t even know where it is!)<br />
&#8211;doug</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: Ilya Grigorik</title>
		<link>http://www.igvita.com/2007/04/16/decision-tree-learning-in-ruby/#comment-74624</link>
		<dc:creator>Ilya Grigorik</dc:creator>
		<pubDate>Tue, 09 Oct 2007 19:15:06 +0000</pubDate>
		<guid isPermaLink="false">http://www.igvita.com/blog/2007/04/16/decision-tree-learning-in-ruby/#comment-74624</guid>
		<description>Joe, run &lt;i&gt;require 'rubygems'&lt;/i&gt; prior to including the decisiontree gem. That should do the trick!</description>
		<content:encoded><![CDATA[<p>Joe, run <i>require &#8216;rubygems&#8217;</i> prior to including the decisiontree gem. That should do the trick!</p>
]]></content:encoded>
	</item>
</channel>
</rss>
