Re: Neural netss (was Re: death of the mind.)
From: Rick Craik (rick_at_@icebergideas..com)
Date: 09/09/04
- Next message: Wolf Kirchmeir: "Re: Challenge to the behaviourists, #1"
- Previous message: JPL Verhey: "Re: Challenge to the behaviourists #2"
- In reply to: Eray Ozkural exa: "Re: Neural netss (was Re: death of the mind.)"
- Next in thread: ZZBunker: "Re: Neural netss (was Re: death of the mind.)"
- Messages sorted by: [ date ] [ thread ]
Date: Thu, 9 Sep 2004 09:36:45 -0400
"Eray Ozkural exa" <erayo@bilkent.edu.tr> wrote in message
news:fa69ae35.0409080502.79f70305@posting.google.com...
> "Rick Craik" <rick@@icebergideas..com> wrote in message
news:<vAk%c.12221$lP4.904168@news20.bellglobal.com>...
> > > 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.
>
> What kind of a programming language would emerge in a NN architecture?
[snip]
>
> A typical NN is data driven, but it's not that simple. First, a feed
> forward NN itself implements a nonlinear / combinatorial function of
> some sort. A recurrent neural net implements a Turing-complete
> program. In both cases training turns the data into program (we have
> little idea what the training algorithm is, our models are mostly
> mathematical ideas that are not really biologically plausible). In the
> second case, the program becomes data. I know that the distinction
> between data and program is less visible in neural networks, [...]
One other point concerning Life CA:
Conway's Life cellular automata is identical to a feed forward net
where all the cells have the same rule, connections are all the
same (the antithesis of connectionism), and so initial conditions
are the data/program. The Game of Life has be shown that it can
compute; signals reverberate in a NN that is extremely deep and
wide. Theoretically, it would be like programming with virtual
hardware using virtual gates, adding an operating system to it
would probably push the size of the net to an impractical size.
The other way to abstract Life is as a one layer recurrent net.
Regards,
Rick
- Next message: Wolf Kirchmeir: "Re: Challenge to the behaviourists, #1"
- Previous message: JPL Verhey: "Re: Challenge to the behaviourists #2"
- In reply to: Eray Ozkural exa: "Re: Neural netss (was Re: death of the mind.)"
- Next in thread: ZZBunker: "Re: Neural netss (was Re: death of the mind.)"
- Messages sorted by: [ date ] [ thread ]
Relevant Pages
|
