Re: Advantage

On Wed, 15 Oct 2003 15:50:32 +0100, "William Silvert"
<[EMAIL PROTECTED]> wrote:

>I came late to this discussion, having been away for a while, but I find the
>topic surprising. I did some work with a colleague from the Netherlands on
>using neural networks to generate fuzzy memberships, using as a training set
>the assignments of a team of experts, so I find the two approaches, fuzzy
>logic and neural networks, complementary rather than competitive.

Exactly

>About Dmitry's comment that neural nets are not tunable, it surprises me
>that no one has addressed this limitation.

I just reformulated "NN have no parameters". Whether it is an
advantage is abother question. But if we have no parameters there is
nothing to tune (directly at least).

>I recall once attending a talk
>where a NN was used to identify people from photographs, and with a training
>set of 10,000 photos it could make correct identification whether or not the
>subjects wore glasses. I asked whether the NN could be told to ignore
>glasses, which would reduce the training set to 5,000 pictures, but was told
>that couldn't be done. Why not?

That would not be easy for any system.

>As for whether expert systems require training sets, I would ask where the
>experts get their expertise. It seems to me that the expertise can be viewed
>as the result of processing the data in what could be considered a training
>set. If we could teach a NN to ignore eyeglasses it would become a bit more
>like an expert.

Right, it will have a knowledge about how "eyeglasses" and "persons"
are related. A model of the world.

---
Regards,
Dmitry Kazakov
www.dmitry-kazakov.de