From: tmoran@acm.org
Subject: Re: GC, existed? the foreigner
Date: Sat, 17 Jan 2004 22:11:06 GMT
Date: 2004-01-17T22:11:06+00:00 [thread overview]
Message-ID: <_piOb.76064$5V2.91744@attbi_s53> (raw)
In-Reply-To: bubi82$euq6c$1@ID-125932.news.uni-berlin.de
> > The initial description of Baysian filters included a rule that
> > anything unrecognized was considered 10% chance of being spam. In
> ...
> and have been using Naive Bayesian filtering ever since; there is NO
> such rule in the code I use, and I have never seen such a rule in the
> scientific literature.
Bayes Theorem has to do with modifying probability estimates based on
data. But there must be some initial (a priori) estimate to start with.
prev parent reply other threads:[~2004-01-17 22:11 UTC|newest]
Thread overview: 10+ messages / expand[flat|nested] mbox.gz Atom feed top
[not found] <mailman.27.1073938595.279.comp.lang.ada@ada-france.org>
2004-01-15 20:50 ` GC, existed? the foreigner Adam Beneschan
2004-01-16 1:59 ` Jeffrey Carter
2004-01-16 2:26 ` Christopher Browne
2004-01-16 21:20 ` Randy Brukardt
2004-01-16 22:29 ` Robert A Duff
2004-01-17 1:23 ` Jeffrey Carter
2004-01-17 5:20 ` Randy Brukardt
2004-01-17 17:26 ` Georg Bauhaus
2004-01-17 14:52 ` Christopher Browne
2004-01-17 22:11 ` tmoran [this message]
replies disabled
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox