From: Stirling Westrup (sti@cam.org)
Date: Mon Jan 31 2000 - 13:59:12 MST
Emlyn wrote:
> Stirling Westrup wrote:
> > The items you list, such as Neural Networks and Genetic Algorithms
> > are currently mathematically intractable, and most mathematicians I've
> > talked to don't have much to good to say about them.
>
> Interestingly, your last sentence sounds like what the geometers had to say,
> but they were talking about ars rei, the "art of the thing", more recently
> known as algebra.
I don't deny that. And if some mathematical 'handles' on this stuff were to be
created, more work would be done on it. I'm personally fairly down on the
entire scheme of Neural Nets, due to the inability of being able to certify a
Neural Net solution as being stable or accurate (All you can do is statistics,
proof is not possible), but some recent work (which I don't have a pointer to --
wish I did) at automatically converting to/from Neural Nets and Prolog-like
languages holds out some hope for not only being able to verify that a Neural
Net is gonna do what we hope, but that we will eventually gain the tools to
analyze natural neural nets.
--
Stirling Westrup | Use of the Internet by this poster
sti@cam.org | is not to be construed as a tacit
| endorsement of Western Technological
| Civilization or its appurtenances.
This archive was generated by hypermail 2.1.5 : Fri Nov 01 2002 - 15:26:33 MST