FAQ: How to train

[David Relson]

At 02:47 PM 7/30/03, Peter Bishop wrote:
>Could you train on "near to error"
>i.e. if spam is near to the spam cut-off point, add it to the database
>even though the classification is correct. (ditto for ham)
>This might make the database less sensitive to extra messages

Seem like making small changes to the values of spam_cutoff and ham_cutoff 
would achieve the same effect.  No?

>Might be  easier to do this woth the Robinson algorithm which has a more
>linear spamicity range.(e.g. spam cutoff=0.54, add spam if <0.60)

The linear quality of the Robinson algorithm _would_ be valuable for 
this.  This is a bit awkward for someone who's run bogotune and has Fisher 
values for the cutoffs -- it would be necessary to rerun bogotune to get 
Robinson values :-(