<?xml version="1.0" encoding="UTF-8" ?>
<?xml-stylesheet type="text/xsl" href="http://blogs.technet.com/utility/FeedStylesheets/rss.xsl" media="screen"?><rss version="2.0" xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:slash="http://purl.org/rss/1.0/modules/slash/" xmlns:wfw="http://wellformedweb.org/CommentAPI/"><channel><title>Blogging from TechEd: Exchange SP1 and IMF released</title><link>http://blogs.technet.com/dlemson/archive/2004/05/25/141278.aspx</link><description>I'm sure you've read it elsewhere, but here's one more link. It was hard to sit on this as people were commenting their lament over not being able to get IMF, but trust me, it's worth the wait. You can find both SP1 and IMF linked off of http://www.microsoft.com/exchange</description><dc:language>en-US</dc:language><generator>CommunityServer 2.1 SP1 (Build: 61025.2)</generator><item><title>re: Blogging from TechEd: Exchange SP1 and IMF released</title><link>http://blogs.technet.com/dlemson/archive/2004/05/25/141278.aspx#145751</link><pubDate>Tue, 01 Jun 2004 20:01:00 GMT</pubDate><guid isPermaLink="false">d5e57398-b9ef-4490-9955-07cbb4e4a80d:145751</guid><dc:creator>Bill Boswell</dc:creator><description>Quick question on the IMF. I've seen a couple of references to the IMF being a Bayesian filter. I wonder if you could confirm this. If the IMF does use Bayesian logic, how does it get trained? After all, it does not accept input from users as to whether it guessed correctly about an SCL. </description></item></channel></rss>