<?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: Numenta</title>
	<atom:link href="http://yarivsblog.com/articles/2008/06/29/numenta/feed/" rel="self" type="application/rss+xml" />
	<link>http://yarivsblog.com/articles/2008/06/29/numenta/</link>
	<description>Adventures in Open Source Erlang</description>
	<pubDate>Sat, 22 Nov 2008 03:50:07 +0000</pubDate>
	<generator>http://wordpress.org/?v=2.6.2</generator>
		<item>
		<title>By: mikhailfranco</title>
		<link>http://yarivsblog.com/articles/2008/06/29/numenta/#comment-305934</link>
		<dc:creator>mikhailfranco</dc:creator>
		<pubDate>Mon, 17 Nov 2008 12:47:59 +0000</pubDate>
		<guid isPermaLink="false">http://yarivsblog.com/?p=195#comment-305934</guid>
		<description>Why not implement the HTM directly in Erlang ?

Make it easy to develop, then worry about performance later,
and you don't have to pay Numenta anything :)

Mik</description>
		<content:encoded><![CDATA[<p>Why not implement the HTM directly in Erlang ?</p>
<p>Make it easy to develop, then worry about performance later,<br />
and you don&#8217;t have to pay Numenta anything :)</p>
<p>Mik</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: Benjamin Nortier</title>
		<link>http://yarivsblog.com/articles/2008/06/29/numenta/#comment-187822</link>
		<dc:creator>Benjamin Nortier</dc:creator>
		<pubDate>Tue, 01 Jul 2008 14:04:18 +0000</pubDate>
		<guid isPermaLink="false">http://yarivsblog.com/?p=195#comment-187822</guid>
		<description>Nice, I'm jealous! I've been keeping an eye on Numenta for a while now, and think it has some very interesting possibilities.

I aim to (hopefully soon) write a little evolutionary engine on top of Nupic (using Erlang of course) to try and "answer" some of the questions you highlighted, such as "How many nodes? How many levels in the hierarchy? How much training data to use? How many categories?".</description>
		<content:encoded><![CDATA[<p>Nice, I&#8217;m jealous! I&#8217;ve been keeping an eye on Numenta for a while now, and think it has some very interesting possibilities.</p>
<p>I aim to (hopefully soon) write a little evolutionary engine on top of Nupic (using Erlang of course) to try and &#8220;answer&#8221; some of the questions you highlighted, such as &#8220;How many nodes? How many levels in the hierarchy? How much training data to use? How many categories?&#8221;.</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: Yariv</title>
		<link>http://yarivsblog.com/articles/2008/06/29/numenta/#comment-187033</link>
		<dc:creator>Yariv</dc:creator>
		<pubDate>Mon, 30 Jun 2008 17:07:17 +0000</pubDate>
		<guid isPermaLink="false">http://yarivsblog.com/?p=195#comment-187033</guid>
		<description>@Joe I think I might have stumbled upon jaanix at some point. It looks interesting. Good use of machine learning techniques.</description>
		<content:encoded><![CDATA[<p>@Joe I think I might have stumbled upon jaanix at some point. It looks interesting. Good use of machine learning techniques.</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: Joe Petviashvili</title>
		<link>http://yarivsblog.com/articles/2008/06/29/numenta/#comment-186767</link>
		<dc:creator>Joe Petviashvili</dc:creator>
		<pubDate>Mon, 30 Jun 2008 06:17:02 +0000</pubDate>
		<guid isPermaLink="false">http://yarivsblog.com/?p=195#comment-186767</guid>
		<description>Have you seen jaanix? It is using machine learning to find stories that might interest you. It is like del.icio.us mashup with pandora, only it lets you "tune-in" into what (or who!) you're interested in.</description>
		<content:encoded><![CDATA[<p>Have you seen jaanix? It is using machine learning to find stories that might interest you. It is like del.icio.us mashup with pandora, only it lets you &#8220;tune-in&#8221; into what (or who!) you&#8217;re interested in.</p>
]]></content:encoded>
	</item>
</channel>
</rss>
