From: J. Maxwell Legg (income@ihug.co.nz)
Date: Sat Aug 15 1998 - 18:58:08 MDT
Nick Bostrom wrote:
> Doug Bailey wrote:
>
> > Got this off of Comline today:
> >
> > A team from NEC {6701} and the University of Tokyo have
> > discovered that applying noise to image recognition patterns
> > through such artificial intelligence (AI) systems as neural
> > networks will raise the accuracy of recognition systems.
> > This runs counter to the prevailing belief that an image
> > must be a neat as possible for clear pickup.
>
> Actually, it has been know in the neural networks community a long
> time that adding some noice often improves performance, especially
> when you have a small number of learning samples. The noice prevents
> the network from "overlearning", i.e. learning to recognize each
> sample pattern individually. It forces the network to discover the
> general regularities in the sample set.
>
> A clear picture is still better than a blurry one. You can
> always add noice afterwards if you like, but you can't go in the
> opposite direction.
>
Hey, I like this stuff. It's right up my alley. Anyway I say you can go
in the opposite direction as long as your using a inbrid network and
still have the database reference to the clear picture. It all depends
on your resources, surely? btw, what is noice or do you mean noise?
This archive was generated by hypermail 2.1.5 : Fri Nov 01 2002 - 14:49:28 MST