<?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"
	xmlns:sy="http://purl.org/rss/1.0/modules/syndication/"
		>
<channel>
	<title>Comments for brain of matpalm</title>
	<atom:link href="http://matpalm.com/blog/comments/feed/" rel="self" type="application/rss+xml" />
	<link>http://matpalm.com/blog</link>
	<description>thoughts from a data scientist wannabe</description>
	<lastBuildDate>Sun, 06 Jun 2010 19:38:46 -0400</lastBuildDate>
	<generator>http://wordpress.org/?v=2.9.2</generator>
	<sy:updatePeriod>hourly</sy:updatePeriod>
	<sy:updateFrequency>1</sy:updateFrequency>
		<item>
		<title>Comment on 5 minute ggobi demo by matpalm</title>
		<link>http://matpalm.com/blog/2010/06/04/5-minute-ggobi-demo/comment-page-1/#comment-156</link>
		<dc:creator>matpalm</dc:creator>
		<pubDate>Sun, 06 Jun 2010 19:38:46 +0000</pubDate>
		<guid isPermaLink="false">http://matpalm.com/blog/?p=634#comment-156</guid>
		<description>you&#039;ll love ggobi jeremy, there is heaps of tight R integration</description>
		<content:encoded><![CDATA[<p>you&#8217;ll love ggobi jeremy, there is heaps of tight R integration</p>
]]></content:encoded>
	</item>
	<item>
		<title>Comment on 5 minute ggobi demo by Jeromy Anglim</title>
		<link>http://matpalm.com/blog/2010/06/04/5-minute-ggobi-demo/comment-page-1/#comment-155</link>
		<dc:creator>Jeromy Anglim</dc:creator>
		<pubDate>Sun, 06 Jun 2010 14:37:55 +0000</pubDate>
		<guid isPermaLink="false">http://matpalm.com/blog/?p=634#comment-155</guid>
		<description>Awesome video. There&#039;s lots of multidimensional data in psychology research, where I&#039;m coming from. I think I&#039;ll have to pull out ggobi next time I&#039;m analysing a tricky multidimensional problem.</description>
		<content:encoded><![CDATA[<p>Awesome video. There&#8217;s lots of multidimensional data in psychology research, where I&#8217;m coming from. I think I&#8217;ll have to pull out ggobi next time I&#8217;m analysing a tricky multidimensional problem.</p>
]]></content:encoded>
	</item>
	<item>
		<title>Comment on 5 minute ggobi demo by Tweets that mention 5 minute ggobi demo « brain of matpalm -- Topsy.com</title>
		<link>http://matpalm.com/blog/2010/06/04/5-minute-ggobi-demo/comment-page-1/#comment-154</link>
		<dc:creator>Tweets that mention 5 minute ggobi demo « brain of matpalm -- Topsy.com</dc:creator>
		<pubDate>Sun, 06 Jun 2010 10:40:42 +0000</pubDate>
		<guid isPermaLink="false">http://matpalm.com/blog/?p=634#comment-154</guid>
		<description>[...] This post was mentioned on Twitter by neil kodner, mat kelcey. mat kelcey said: brutally short demo (&lt;5 minute) of my fav data viz tool; GGOBI! http://bit.ly/dkyssV [...]</description>
		<content:encoded><![CDATA[<p>[...] This post was mentioned on Twitter by neil kodner, mat kelcey. mat kelcey said: brutally short demo (&lt;5 minute) of my fav data viz tool; GGOBI! <a href="http://bit.ly/dkyssV" rel="nofollow">http://bit.ly/dkyssV</a> [...]</p>
]]></content:encoded>
	</item>
	<item>
		<title>Comment on latent semantic analysis via the singular value decomposition (for dummies) by matpalm</title>
		<link>http://matpalm.com/blog/2010/04/19/lsa-via-svd-for-dummies/comment-page-1/#comment-126</link>
		<dc:creator>matpalm</dc:creator>
		<pubDate>Wed, 12 May 2010 08:37:53 +0000</pubDate>
		<guid isPermaLink="false">http://matpalm.com/blog/?p=454#comment-126</guid>
		<description>thanks nicholas, 
my initial tf-idf normalisation attempts performed quite poorly.
i&#039;ll have to give it another crack.
mat</description>
		<content:encoded><![CDATA[<p>thanks nicholas,<br />
my initial tf-idf normalisation attempts performed quite poorly.<br />
i&#8217;ll have to give it another crack.<br />
mat</p>
]]></content:encoded>
	</item>
	<item>
		<title>Comment on latent semantic analysis via the singular value decomposition (for dummies) by Nicholas Dronen</title>
		<link>http://matpalm.com/blog/2010/04/19/lsa-via-svd-for-dummies/comment-page-1/#comment-125</link>
		<dc:creator>Nicholas Dronen</dc:creator>
		<pubDate>Wed, 12 May 2010 03:08:45 +0000</pubDate>
		<guid isPermaLink="false">http://matpalm.com/blog/?p=454#comment-125</guid>
		<description>I believe the log-entropy term weighting scheme described in the following paper is commonly applied to term-document matrices before performing the SVD:

    http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.118.6313

It&#039;s use in LSA is described in the Handbook of Latent Semantic Analysis:

    http://books.google.com/books?id=jgVWCuFXePEC</description>
		<content:encoded><![CDATA[<p>I believe the log-entropy term weighting scheme described in the following paper is commonly applied to term-document matrices before performing the SVD:</p>
<p>    <a href="http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.118.6313" rel="nofollow">http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.118.6313</a></p>
<p>It&#8217;s use in LSA is described in the Handbook of Latent Semantic Analysis:</p>
<p>    <a href="http://books.google.com/books?id=jgVWCuFXePEC" rel="nofollow">http://books.google.com/books?id=jgVWCuFXePEC</a></p>
]]></content:encoded>
	</item>
	<item>
		<title>Comment on how many terms in a trend? by Tweets that mention how many terms in a trend? « brain of matpalm -- Topsy.com</title>
		<link>http://matpalm.com/blog/2010/05/11/how-many-terms-in-a-trend/comment-page-1/#comment-122</link>
		<dc:creator>Tweets that mention how many terms in a trend? « brain of matpalm -- Topsy.com</dc:creator>
		<pubDate>Tue, 11 May 2010 10:29:37 +0000</pubDate>
		<guid isPermaLink="false">http://matpalm.com/blog/?p=627#comment-122</guid>
		<description>[...] This post was mentioned on Twitter by Alex Dong, mat kelcey. mat kelcey said: multi term trending? can&#039;t decide which way to try... http://bit.ly/9vC7wu #blog [...]</description>
		<content:encoded><![CDATA[<p>[...] This post was mentioned on Twitter by Alex Dong, mat kelcey. mat kelcey said: multi term trending? can&#39;t decide which way to try&#8230; <a href="http://bit.ly/9vC7wu" rel="nofollow">http://bit.ly/9vC7wu</a> #blog [...]</p>
]]></content:encoded>
	</item>
	<item>
		<title>Comment on e10.6 community detection for my twitter network by Tweets that mention e10.6 community detection for my twitter network « matpalm.com/blog -- Topsy.com</title>
		<link>http://matpalm.com/blog/2010/04/04/375/comment-page-1/#comment-102</link>
		<dc:creator>Tweets that mention e10.6 community detection for my twitter network « matpalm.com/blog -- Topsy.com</dc:creator>
		<pubDate>Sun, 04 Apr 2010 07:14:22 +0000</pubDate>
		<guid isPermaLink="false">http://matpalm.com/blog/?p=375#comment-102</guid>
		<description>[...] This post was mentioned on Twitter by Luke Venediger, mat kelcey. mat kelcey said: e10.6 community detection for my twitter network http://bit.ly/bvwPB2 [...]</description>
		<content:encoded><![CDATA[<p>[...] This post was mentioned on Twitter by Luke Venediger, mat kelcey. mat kelcey said: e10.6 community detection for my twitter network <a href="http://bit.ly/bvwPB2" rel="nofollow">http://bit.ly/bvwPB2</a> [...]</p>
]]></content:encoded>
	</item>
	<item>
		<title>Comment on semi supervised naive bayes for text classification by My Data Mining Weblog &#187; Top 10 Algorithms in Data Mining (Slide)</title>
		<link>http://matpalm.com/blog/2010/02/14/semi-supervised-naive-bayes-for-text-classification/comment-page-1/#comment-82</link>
		<dc:creator>My Data Mining Weblog &#187; Top 10 Algorithms in Data Mining (Slide)</dc:creator>
		<pubDate>Thu, 04 Mar 2010 11:25:47 +0000</pubDate>
		<guid isPermaLink="false">http://matpalm.com/blog/?p=299#comment-82</guid>
		<description>[...] semi supervised naive bayes for text classification [...]</description>
		<content:encoded><![CDATA[<p>[...] semi supervised naive bayes for text classification [...]</p>
]]></content:encoded>
	</item>
	<item>
		<title>Comment on what to do with a week off? by matpalm</title>
		<link>http://matpalm.com/blog/2010/02/22/what-to-do-with-a-week-off/comment-page-1/#comment-79</link>
		<dc:creator>matpalm</dc:creator>
		<pubDate>Mon, 22 Feb 2010 11:17:36 +0000</pubDate>
		<guid isPermaLink="false">http://matpalm.com/blog/?p=304#comment-79</guid>
		<description>i must admit it&#039;s tempting! a lot of this week is already filled in with things to do with the young one so i guess i&#039;m just trying to fill the gaps!</description>
		<content:encoded><![CDATA[<p>i must admit it&#8217;s tempting! a lot of this week is already filled in with things to do with the young one so i guess i&#8217;m just trying to fill the gaps!</p>
]]></content:encoded>
	</item>
	<item>
		<title>Comment on what to do with a week off? by OJ</title>
		<link>http://matpalm.com/blog/2010/02/22/what-to-do-with-a-week-off/comment-page-1/#comment-78</link>
		<dc:creator>OJ</dc:creator>
		<pubDate>Mon, 22 Feb 2010 09:55:20 +0000</pubDate>
		<guid isPermaLink="false">http://matpalm.com/blog/?p=304#comment-78</guid>
		<description>Take a week off tech, and come back suitably refreshed and ready to take them &lt;strong&gt;all&lt;/strong&gt; on :)</description>
		<content:encoded><![CDATA[<p>Take a week off tech, and come back suitably refreshed and ready to take them <strong>all</strong> on :)</p>
]]></content:encoded>
	</item>
</channel>
</rss>
