Re: Neural netss (was Re: death of the mind.)
From: Rick Craik (rick_at_@icebergideas..com)
Date: 09/07/04
- Next message: Lester Zick: "Re: the liver and the brain"
- Previous message: JPL Verhey: "Re: First Causes"
- In reply to: Eray Ozkural exa: "Re: Neural netss (was Re: death of the mind.)"
- Next in thread: Eray Ozkural exa: "Re: Neural netss (was Re: death of the mind.)"
- Reply: Eray Ozkural exa: "Re: Neural netss (was Re: death of the mind.)"
- Messages sorted by: [ date ] [ thread ]
Date: Tue, 7 Sep 2004 11:32:54 -0400
"Eray Ozkural exa" <erayo@bilkent.edu.tr> wrote in message
news:fa69ae35.0409041945.6befa124@posting.google.com...
> "Rick Craik" <rick@@icebergideas..com> wrote in message
news:<G0m_c.29402$7i2.1321016@news20.bellglobal.com>...
> > > As I see it, you can't really do something like "write a program"
> > > which will run on the NN [...]
> >
> > I think Eray is going on about virtual machines, not a virtual NN.
> > At this point is remains to be seen what the virtual machine is
> > comprised of, he's not imposing structure on it.
>
> Perhaps, yes. What is a virtual canon best represented by? It depends
> on the requirements of our cognitive system. I think very flexible
> models are needed indeed, because even in easy problems we seem to
> wield the power of Turing-complete computations.
Conway's Game of Life (2D, Life 2233) is a virtual machine, and
hasn't it been shown to be Turing-complete? Although in its
original form, it's unwieldy, there is some flexibility available
already. For example, a wrap-a-round universe can contain
computations, a programmable setting exactly like defining
the properties of a NN. Dan's point above amounts to training
versus "write a program" at this stage for a NN versus automata.
Surely we can investigate avenues of altering the Life automata
VM that approach the likes of a NN. Cognitive requirements
might guide us a way, perhaps not, but at least we might
have a venue for comparative models.
>
> In my mind, there ought to be programming language-like thingies that
> drive these virtual machines.
In my mind, there is always the problem of what is data and
what is a program. Can we say a NN is data driven and a VM
is program driven? [Hmm, seems like nurture vs. nature.] Perhaps
there is a point when altering Life automata, we find a data
driven nature.
Regards,
Rick
> I think like Minsky and a little like
> Fodor, I suppose. There could be countless programming languages in
> the brain.
>
> Regards,
>
> --
> Eray
- Next message: Lester Zick: "Re: the liver and the brain"
- Previous message: JPL Verhey: "Re: First Causes"
- In reply to: Eray Ozkural exa: "Re: Neural netss (was Re: death of the mind.)"
- Next in thread: Eray Ozkural exa: "Re: Neural netss (was Re: death of the mind.)"
- Reply: Eray Ozkural exa: "Re: Neural netss (was Re: death of the mind.)"
- Messages sorted by: [ date ] [ thread ]
Relevant Pages
|