Connectionism

[Sydney Lamb]

On Thu, 22 Mar 2001, dan everett wrote:

>      The basic idea is that phonological representations require the use of
>      variables and cannot be accounted for by different strengths of
>      connections or statistical generalizations. Evidence for variables is
>      problematic for connectionism.
>      ...

Variables are problematic only for a simple-minded version of
connectionism such as the well-known version of Rumelhart &
McClellan and their colleagues, with its limitation to three
layers, etc. But that simple-minded version has to be rejected
anyway as neurologically implausible.

  - Syd Lamb

> ______________________________ Reply Separator _________________________________
> Subject: Re: Dyslexia
> Author:  <Twright at accdvm.accd.edu> at Internet
> Date:    3/21/01 1:41 PM
>
>
> At 08:17 AM 3/21/01 -0500, dan everett wrote:
>
> >     We have a new paper either just out or nearly out in Cognitive
> >     Psychology on variables in Hebrew word representation, also arguing
> >     that phonological representation is nonconnectionist, symbolic and
> >     representational.
>
> What exactly is meant by "nonconnectionist" in this context?  I am familiar
> with the concepts of connectionism, but could you expand a bit about
> phonological representation being nonconnectionist?  Also, what is the
> difference between it being symbolic and being representational?  I am eager
> to know more about this line of inquiry, as it sounds very interesting.
>
> --Tony Wright
>

Sydney M. Lamb                  http://www.ruf.rice.edu/~lamb/
Linguistics and Cognitive Sciences
Rice University, Houston, TX