<?xml version="1.0" encoding="UTF-8"?>
<rss version="2.0"
	xmlns:content="http://purl.org/rss/1.0/modules/content/"
	xmlns:wfw="http://wellformedweb.org/CommentAPI/"
	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/"
	xmlns:slash="http://purl.org/rss/1.0/modules/slash/"
	>

<channel>
	<title>Armando Fox &#187; SML</title>
	<atom:link href="http://www.armandofox.com/geek/category/sml/feed/" rel="self" type="application/rss+xml" />
	<link>http://www.armandofox.com/geek</link>
	<description>A breadth-first traversal of life</description>
	<lastBuildDate>Sun, 05 May 2013 22:09:08 +0000</lastBuildDate>
	<generator>http://wordpress.org/?v=2.9.2</generator>
	<language>en</language>
	<sy:updatePeriod>hourly</sy:updatePeriod>
	<sy:updateFrequency>1</sy:updateFrequency>
			<item>
		<title>Opportunities for // and multicore in SML</title>
		<link>http://www.armandofox.com/geek/2009/05/opportunities-for-and-multicore-in-sml/</link>
		<comments>http://www.armandofox.com/geek/2009/05/opportunities-for-and-multicore-in-sml/#comments</comments>
		<pubDate>Tue, 05 May 2009 20:34:55 +0000</pubDate>
		<dc:creator>fox</dc:creator>
				<category><![CDATA[SML]]></category>
		<category><![CDATA[SWDYFORPs]]></category>

		<guid isPermaLink="false">http://radlab.cs.berkeley.edu/people/fox/wp/?p=101</guid>
		<description><![CDATA[Parallelizing/decomposing big models and trading off accuracy, precision, etc.  (Similar to trading consistency for availability/scalability in storage.)  EG: EM training with Markov models, you have a single big data structure (the translation table) that everyone uses and then has to be globally updated (in the M-step). A NIPS paper (described as &#8220;hacky&#8221; by Alex Smola) partitions the model and [...]]]></description>
			<content:encoded><![CDATA[<p>Parallelizing/decomposing big models and trading off accuracy, precision, etc.  (Similar to trading consistency for availability/scalability in storage.)  EG: EM training with Markov models, you have a single big data structure (the translation table) that everyone uses and then has to be globally updated (in the M-step). A NIPS paper (described as &#8220;hacky&#8221; by Alex Smola) partitions the model and uses peer-peer anti-entropy to periodically try to sync models.</p>
<p>In general, one avenue of opportunity is to improve performance or power of most sophistiacted models.  But another avenue is: what can we do with yesterday&#8217;s/less sophisticated models, which may be perfectly adequate for some app domains esp. if they could run in real time or be portable, and/or they could be used in a layered approach with more sophisticated models within a particular domain.</p>
<div></div>
]]></content:encoded>
			<wfw:commentRss>http://www.armandofox.com/geek/2009/05/opportunities-for-and-multicore-in-sml/feed/</wfw:commentRss>
		<slash:comments>0</slash:comments>
		</item>
		<item>
		<title>Universal data interchange format for SML data structures &amp; models</title>
		<link>http://www.armandofox.com/geek/2009/05/universal-data-interchange-format-for-sml-data-structures-models/</link>
		<comments>http://www.armandofox.com/geek/2009/05/universal-data-interchange-format-for-sml-data-structures-models/#comments</comments>
		<pubDate>Tue, 05 May 2009 20:33:23 +0000</pubDate>
		<dc:creator>fox</dc:creator>
				<category><![CDATA[SML]]></category>
		<category><![CDATA[SWDYFORPs]]></category>

		<guid isPermaLink="false">http://radlab.cs.berkeley.edu/people/fox/wp/?p=99</guid>
		<description><![CDATA[Given that interesting apps will use multiple languages/frameworks (if not at the productivity layer, then at the efficiency layer), we should be working on portable in-memory and on-disk data formats for various types of ML models (and fast swizzling/unswizzling). Use Google Code Protocol Buffers and define some standard schemata?
]]></description>
			<content:encoded><![CDATA[<p>Given that interesting apps will use multiple languages/frameworks (if not at the productivity layer, then at the efficiency layer), we should be working on portable in-memory and on-disk data formats for various types of ML models (and fast swizzling/unswizzling). Use Google Code Protocol Buffers and define some standard schemata?</p>
]]></content:encoded>
			<wfw:commentRss>http://www.armandofox.com/geek/2009/05/universal-data-interchange-format-for-sml-data-structures-models/feed/</wfw:commentRss>
		<slash:comments>0</slash:comments>
		</item>
	</channel>
</rss>
