[Top] [All Lists]

Re: [ontolog-forum] Architecture of Intelligent Systems - Flexible Modul

To: "[ontolog-forum]" <ontolog-forum@xxxxxxxxxxxxxxxx>
From: Thomas Johnston <tmj44p@xxxxxxx>
Date: Wed, 27 May 2015 21:10:43 +0000 (UTC)
Message-id: <1680345088.819911.1432761043079.JavaMail.yahoo@xxxxxxxxxxxxxx>

The point is that anything that the most powerful computers can do, a Turing Machine can do.

Therefore, if an ANN can run a Turing Machine, it can run anything that any computer can run.

Therefore, all of the Language of Thought arguments about theorem-proving computers are not arguments against ANNs. 

This directly addresses arguments stretching over several decades, involving some very important names in cognitive science and philosophy of mind and language.

What anything that the most super of supercomputers actually does, these days, is beside the point.

On Wednesday, May 27, 2015 1:49 PM, Michael Brunnbauer <brunni@xxxxxxxxxxxx> wrote:

Hello John,

Thomas Johnston wrote:
> And recent connectionist research has apparently proven that ANNs can carry out deductive
> theorem-proving. Another claim is that ANNs have been proven to be able to
> implement Turing machines which, if true, should settle the matter.

You wrote:
> They worked independently, but they challenged one another with
> examples of what each of their methods could compute:  "Here's what
> my system can do.  Can yours do the same?"  As a result, they agreed
> that the three systems (and many other variations) are equivalent
> in computational power.
> Note the message format, p. 14 of http://www.jfsowa.com /pubs/arch.pdf .
> It allows arbitrary languages, which can be as complex as English, or
> as simple as a single bit.  Most messages are simple.  Also not the
> character strong for 'speech act'.  Most speech acts are also simple,
> such as tell (update), ask (query), or do (execute).  But they can also
> lead to complex transactions.
> I had not seen that article before I submitted mine.  If I had, I would
> have pointed out that the architectures in Figs 1, 2, 3, and 4 of that
> article (and many, many more) could have been implemented very quickly
> by putting together a collection of FMF agents.
> In fact, the various VivoMind applications use different architectures
> which are assembled by putting together previously written modules (or
> adding new ones).  In fact, the modules can reorganize themselves and
> create (AKA 'learn' or 'discover') new ways of interacting.  That's
> the point of http://www.jfsowa.com/pubs/paradigm.pdf
> By the way, the FMF is, in effect, a distributed operating system.
> We use modules written in Java, Prolog, C, and other languages.
> The software is very easy to port from Linux, to Windows, to Apple OS.
> And it can communicate with agents in other FMF systems anywhere on
> the WWW -- there may be a delay, but the message passing is independent
> of the location.

can can can can could. As the most simple systems are Turing complete, I'd say
what a system *can* do is not relevant, only what it actually does :-)


Michael Brunnbauer

++  Michael Brunnbauer
++  netEstate GmbH
++  Geisenhausener Straße 11a
++  81379 München
++  Tel +49 89 32 19 77 80
++  Fax +49 89 32 19 77 89
++  E-Mail brunni@xxxxxxxxxxxx
++  http://www.netestate.de/
++  Sitz: München, HRB Nr.142452 (Handelsregister B München)
++  USt-IdNr. DE221033342
++  Geschäftsführer: Michael Brunnbauer, Franz Brunnbauer
++  Prokurist: Dipl. Kfm. (Univ.) Markus Hendel

Message Archives: http://ontolog.cim3.net/forum/ontolog-forum/  
Config Subscr: http://ontolog.cim3.net/mailman/listinfo/ontolog-forum/  
Unsubscribe: mailto:ontolog-forum-leave@xxxxxxxxxxxxxxxx
Shared Files: http://ontolog.cim3.net/file/
Community Wiki: http://ontolog.cim3.net/wiki/ 
To join: http://ontolog.cim3.net/cgi-bin/wiki.pl?WikiHomePage#nid1J    (01)

<Prev in Thread] Current Thread [Next in Thread>