<?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: Songsmith&#8230; and then what?</title>
	<atom:link href="http://www.vinhly.com/2009/02/05/songsmith-and-then-what/feed/" rel="self" type="application/rss+xml" />
	<link>http://www.vinhly.com/2009/02/05/songsmith-and-then-what/</link>
	<description>Commenting is caring</description>
	<lastBuildDate>Sat, 09 Nov 2024 17:54:30 +0000</lastBuildDate>
	
	<sy:updatePeriod>hourly</sy:updatePeriod>
	<sy:updateFrequency>1</sy:updateFrequency>
		<item>
		<title>By: Vinh</title>
		<link>http://www.vinhly.com/2009/02/05/songsmith-and-then-what/comment-page-1/#comment-274</link>
		<dc:creator>Vinh</dc:creator>
		<pubDate>Thu, 05 Feb 2009 21:43:00 +0000</pubDate>
		<guid isPermaLink="false">http://www.vinhly.com/?p=337#comment-274</guid>
		<description>Well you just have to find the basic canonical ideas and combine them together...&lt;br/&gt;&lt;br/&gt;I think semantic is a good way to start.</description>
		<content:encoded><![CDATA[<p>Well you just have to find the basic canonical ideas and combine them together&#8230;</p>
<p>I think semantic is a good way to start.</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: Régis</title>
		<link>http://www.vinhly.com/2009/02/05/songsmith-and-then-what/comment-page-1/#comment-273</link>
		<dc:creator>Régis</dc:creator>
		<pubDate>Thu, 05 Feb 2009 06:24:00 +0000</pubDate>
		<guid isPermaLink="false">http://www.vinhly.com/?p=337#comment-273</guid>
		<description>You make me think of this machine learning professor who wanted to mine the space of possible paintings to create new exhibits. The hardest thing will not be to copy human creations but to come up with a systematic way to produce creatively. In other words: ideas, not works of art, should be mined. When I told this professor that he ought to explore the space of ideas, that left him pondering how big this space was.</description>
		<content:encoded><![CDATA[<p>You make me think of this machine learning professor who wanted to mine the space of possible paintings to create new exhibits. The hardest thing will not be to copy human creations but to come up with a systematic way to produce creatively. In other words: ideas, not works of art, should be mined. When I told this professor that he ought to explore the space of ideas, that left him pondering how big this space was.</p>
]]></content:encoded>
	</item>
</channel>
</rss>
