Philosophical foundations

[Freddy Offenga]

Gerry Wolff wrote:
>Regarding "symbolic" and "connectionist" approaches to AI etc, I feel
>that much of the confusion arises because neither term is very precise.

With "symbolic" I refer to the symbolic computational view of cognition.
In this classic approach the symbols have a certain meaning. They are
about something in the external world.
In the "connectionist" view the knowledge is represented in the weights
of the network. The 'symbols' have a distributed representation
(although there are also localist networks, where the units have
meaning). Anyhow, the weights are the most important properties for
connectionism while symbols are the most important for symbolicism.

>...
>
>I have indeed argued that the SP system can model a Turing machine (the
>relevant article needs some tightening up but I think the argument is
>sound). But, since current versions of the SP system are running as
>software simulations on a conventional computer (which is similar to a
>Turing machine), we do seem to have a paradox here.

Thank for the explanation. Indeed it doesn't matter on which hardware
the SP system runs. The Turing machine isn't questioned here.
But I think the fact that the SP system can model a Turing machine is
not so interesting for cognitive science. If it performs well enough,
it just shows the power of the SP system.

My concern is about the basic cognitive architecture. In my view CasC
produces a probably better architecture, because of the integration
of the many different reasoning mechanisms.

>...
>
>* A neural net might very well provide a foundation for an SP machine.
>This could be an interesting and fruitful exercise which might help to
>remedy some of the weaknesses of the current generation of neural nets
>in performing some kinds of 'symbolic' task.
>
>...

I agree with the 'exercise' part, but I'm not sure I understand what
you mean with the first sentence ('A neural net...').
Do you mean that a neural net could be the right way to implement
the SP system? If this isn't necessary, why do it? I was thinking
about a system with other elementary processes. These processes
should include the basic properties of CasC.
Ofcourse the question about what the best implementation is remains.

	

Freddy Offenga

F.Offenga at student.kun.nl
Software Engineer and Student Cognitive Science at:
Katholieke Universiteit Nijmegen, The Netherlands