<?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 on: Commercial Science</title>
	<atom:link href="http://lillesvin.net/archives/97/feed" rel="self" type="application/rss+xml" />
	<link>http://lillesvin.net/archives/97</link>
	<description></description>
	<lastBuildDate>Sat, 18 Feb 2012 16:53:49 +0000</lastBuildDate>
	<sy:updatePeriod>hourly</sy:updatePeriod>
	<sy:updateFrequency>1</sy:updateFrequency>
	<generator>http://wordpress.org/?v=3.1.2</generator>
	<item>
		<title>By: Madsen</title>
		<link>http://lillesvin.net/archives/97/comment-page-1#comment-396</link>
		<dc:creator>Madsen</dc:creator>
		<pubDate>Wed, 15 Feb 2006 15:49:45 +0000</pubDate>
		<guid isPermaLink="false">http://blog.lillesvin.net/archives/97#comment-396</guid>
		<description>Hehe, not that surprising I think. I don&#039;t know how the semantic model of Google Sets work and how it&#039;s trained, but I imagine that they at least look for &quot;neighbours&quot;, so if the training program encounters the sentence &quot;my favourite cars are Ford, Citroën and Yugo&quot;, then it&#039;ll learn that &quot;Ford&quot;, &quot;Citroën&quot; and &quot;Yugo&quot; are all in the same semantic category - namely cars. So if you afterwards give it a set containing &quot;Ford&quot;, &quot;Audi&quot;, &quot;Mazda&quot; and &quot;Citroën&quot;, then it&#039;ll know to include Yugo.

It might not have encountered (or recognized) that many band names and sound synthesis programs... Yet. :)</description>
		<content:encoded><![CDATA[<p>Hehe, not that surprising I think. I don&#8217;t know how the semantic model of Google Sets work and how it&#8217;s trained, but I imagine that they at least look for &#8220;neighbours&#8221;, so if the training program encounters the sentence &#8220;my favourite cars are Ford, Citroën and Yugo&#8221;, then it&#8217;ll learn that &#8220;Ford&#8221;, &#8220;Citroën&#8221; and &#8220;Yugo&#8221; are all in the same semantic category &#8211; namely cars. So if you afterwards give it a set containing &#8220;Ford&#8221;, &#8220;Audi&#8221;, &#8220;Mazda&#8221; and &#8220;Citroën&#8221;, then it&#8217;ll know to include Yugo.</p>
<p>It might not have encountered (or recognized) that many band names and sound synthesis programs&#8230; Yet. :)</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: stfi</title>
		<link>http://lillesvin.net/archives/97/comment-page-1#comment-395</link>
		<dc:creator>stfi</dc:creator>
		<pubDate>Wed, 15 Feb 2006 13:22:37 +0000</pubDate>
		<guid isPermaLink="false">http://blog.lillesvin.net/archives/97#comment-395</guid>
		<description>Agreed. Btw Google Sets returned zero results on the following stets (who do i, system, dub tractor) and (pure data, max, jmax). I found that disapointing, too.</description>
		<content:encoded><![CDATA[<p>Agreed. Btw Google Sets returned zero results on the following stets (who do i, system, dub tractor) and (pure data, max, jmax). I found that disapointing, too.</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: stfi</title>
		<link>http://lillesvin.net/archives/97/comment-page-1#comment-394</link>
		<dc:creator>stfi</dc:creator>
		<pubDate>Wed, 15 Feb 2006 13:18:17 +0000</pubDate>
		<guid isPermaLink="false">http://blog.lillesvin.net/archives/97#comment-394</guid>
		<description>Agreed. Btw Google Sets returned zero results on the following stets (who do i, system, dub tractor) and (pure data, max, jmax). I found that disapointing, too.</description>
		<content:encoded><![CDATA[<p>Agreed. Btw Google Sets returned zero results on the following stets (who do i, system, dub tractor) and (pure data, max, jmax). I found that disapointing, too.</p>
]]></content:encoded>
	</item>
</channel>
</rss>

