Neural Networks and fp

[Howie]

----- Original Message ----- 
From: "John Esak" <john at valar.com>
To: "Fplist (E-mail)" <filepro-list at seaslug.org>
Sent: Tuesday, November 30, 2004 11:56 PM
Subject: RE: Neural Networks and fp


|
|
| > -----Original Message-----
| > From: filepro-list-bounces at lists.celestial.com
| > [mailto:filepro-list-bounces at lists.celestial.com]On Behalf Of Howie
| > Sent: Tuesday, November 30, 2004 10:43 AM
| > To: Filepro 2 List
| > Subject: OT: Neural Networks and fp
| >
| >
| > Just curious if anyone has tried to implement a neural network using
| > filePro.
| >
| > I would love to see even (especially) the simplest example.
| >
| > It is something I would like to play with in my spare time but do not
know
| > how to even start.
| >
| > I've read some papers on it but they were far to academic for my
| > fileproised
| > brain.
| >
| > Thanks,
| >
| > Howie
| >
| > _______________________________________________
| > Filepro-list mailing list
| > Filepro-list at lists.celestial.com
| > http://mailman.celestial.com/mailman/listinfo/filepro-list
|
| Howie,
|
| The furthest I've ever gone into neural-net programming with filePro...
| is... I have a routine somewhere that puts up a browse as a selection tool
| for the user... one of the choices is "Other". If they select this, a
field
| comes up in which they can add the "other" choice. The next time the
browse
| is ever displayed, it contains this new addition.
|
| Now, you may scoff and laugh and jeer... :-)  But, this to me is about the
| most atomic explanation of what a neural-net actually does.  It learns.
:-)
| So, while it isn't much, I gladly offer it to you oh Grandfather of
filePro
| for your immediate slicing/dicing and improvement.  Knowing you, I fully
| expect to see little filePro robots crawling around everywhere within the
| next year. :-)
|
| Good luck,
|
| John Esak


Thanks for the reply John but that is not what I had in mind.

You do bring up an interesting point though.  If you define a neural network
as something that learns then my old animal game is a perfect example.  The
problem is that with both your solution and the animal game the user is
consciously teaching the system a new behavior - I want something that
teaches itself based on past experience.

If I ever come up with something I will let you and the group know.

Thanks

Howie