Matthew Cline <[EMAIL PROTECTED]> writes:

> Why not do like Bayes, and promote all of them?  Then the GA can
> assign lower scores to the rules with more FPs.

I don't trust the GA/perceptron to assign good scores for range rules
with very few hits.  Also, the additional rules don't really cover much
territory unless Bayes.

Daniel

-- 
Daniel Quinlan                     anti-spam (SpamAssassin), Linux,
http://www.pathname.com/~quinlan/    and open source consulting

Reply via email to