Re: Roster of members ...

> On Tue, 17 Feb 2004 11:29:45 -0800, Jesse Dougherty wrote:
>
> >Maybe we could get things moving if we all identified ourselves and
> >determined if we may want to invite some other stakeholders to make
> >sure we've got a representative sample.
>
> I suppose I fall into two categories...
>
> I'm not exactly a filter developer, though I maintain an
> active interest
> in filter development and evaluation.  But what I have
> developed is an
> astonishingly effective method for optimizing classification accuracy
> for (any) rule-based classifier (spam filters being one
> special case of
> automatic classifiers).

Do tell ...

>
> I guess I think I also fall into category 5.  I'm a scientist by
> training, and I get really excited whenever data is substituted for
> opinion.  (Those who were at or who saw last month's MIT
> conference may
> recall me as the fellow who began his talk by quoting Artemus
> Ward: "It
> ain't so much the things we don't know that get us into trouble. It's
> the things we do know that just ain't so.")

I seem to recall there being discussions of eigenvectors etc ...  It was
a very  interesting talk. (Right talk, I hope!)

>
> - Terry
>