On 4/21/2015 4:06 PM, Thomas Johnston wrote:
> I'll look at that Fodor article on the Churchlands.
>
>> http://ruccs.rutgers.edu/tech_rpt/MeaningSim46.PDF
>> All at sea in semantic space:
>> Churchland on meaning similarity. (01)
OK. But there are many related papers in which Fodor and Lepore
debate the issues with many others. David Chalmers collected
quite a few of them: http://consc.net/mindpapers/6.3 (02)
See below for one of the critical papers by Chalmers. In the last
line of the abstract, he says "even if Fodor and Pylyshyn’s argument
that connectionist models of compositionality must be mere
implementations were correct, then this would still not be a
serious argument against connectionism as a theory of mind." (03)
But as neuroscientists admit, *nobody* has a truly serious theory
about how the brain works. All this bickering about one inadequate
theory being more inadequate than another is a waste of time. (04)
Summary: We know that (a) the brain is made of neurons plus other
stuff; (b) languages and other communication systems use symbols;
(c) no computational systems can learn and use language as quickly
and accurately as a three-year-old child. But some systems, such
as Watson, have made good progress by lashing together multiple
tools based on a combination of different paradigms. (05)
Bottom line: Two paradigms are better than one, and multiple paradigms
are even better: http://www.jfsowa.com/pubs/paradigm.pdf (06)
John (07)
____________________________________________________________________ (08)
Source: http://consc.net/papers/f-and-p.pdf (09)
Chalmers, David J. (1993). Connectionism and compositionality:
Why Fodor and Pylyshyn were wrong. (010)
Abstract: This paper offers both a theoretical and an experimental
perspective on the relationship between connectionist and Classical
(symbol-processing) models. Firstly, a serious flaw in Fodor and
Pylyshyn’s argument against connectionism is pointed out: if, in fact, a
part of their argument is valid, then it establishes a conclusion quite
different from that which they intend, a conclusion which is
demonstrably false. The source of this flaw is traced to an
underestimation of the differences between localist and distributed
representation. It has been claimed that distributed representations
cannot support systematic operations, or that if they can, then they
will be mere implementations of traditional ideas. This paper presents
experimental evidence against this conclusion: distributed
representations can be used to support direct structure-sensitive
operations, in a manner quite unlike the Classical approach. Finally, it
is argued that even if Fodor and Pylyshyn’s argument that connectionist
models of compositionality must be mere implementations were correct,
then this would still not be a serious argument against connectionism as
a theory of mind. (011)
_________________________________________________________________
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 (012)
|