hello everyone,
i tried this question in olap room but there was no reply.
i had a question regarding Expectation-Maximization
algorithm used by microsoft for data mining in ole db.
Does anyone know how good this algorithm is when compared
to the latest clustering algorithms like chameleon, cure,
rock. Does EM create clusters of hybrid shapes or else
just it forms only circular shaped clusters. If there is
any document that compares this algorithm then it would
be helpful for me a lot. i need this information
desperately. Can anyone of u please reply me about ur
knowledge about this.hope someone will reply me soon.my
email id is mailkonda (AT) yahoo (DOT) com
thanks in advance,
praveen

..

Well, um, how shall I put this politely........ you're in the wrong
newsgroup.

This newsgroup deals with having multiple servers appear as one, or work
cooperatively in a "cluster".

However you might want to check out some of these links.

http://www.microsoft.com/technet/pro...in/dmperf.mspx

http://research.microsoft.com/resear...aspx?pubid=268

http://research.microsoft.com/resear...aspx?pubid=267

http://research.microsoft.com/~thies...ning-curve.pdf

http://research.microsoft.com/users/...16477-wang.pdf

--
Hilary Cotter
Looking for a SQL Server replication book?
http://www.nwsu.com/0974973602.html


<anonymous (AT) discussions (DOT) microsoft.com> wrote

This newsgroups covers failover clustering and not datamining clustering
algorithms, so I am afraid you will not find an answer here either, there is
however a specific datamining newsgroup,
microsoft.public.sqlserver.datamining which should be able to be of help.

GertD (AT) SQLDev (DOT) Net

Please reply only to the newsgroups.
This posting is provided "AS IS" with no warranties, and confers no rights.
You assume all risk for your use.
Copyright © SQLDev.Net 1991-2004 All rights reserved.

<anonymous (AT) discussions (DOT) microsoft.com> wrote