Relay-Version: version B 2.10 5/3/83; site utzoo.UUCP
Path: utzoo!utgpu!water!watmath!clyde!rutgers!ames!husc6!diamond.bbn.com!aweinste
From: aweinste@diamond.bbn.com.UUCP
Newsgroups: comp.ai,comp.cog-eng
Subject: Re: The symbol grounding problem
Message-ID: <6553@diamond.BBN.COM>
Date: Sun, 14-Jun-87 15:45:33 EDT
Article-I.D.: diamond.6553
Posted: Sun Jun 14 15:45:33 1987
Date-Received: Sun, 14-Jun-87 23:40:15 EDT
References: <764@mind.UUCP> <768@mind.UUCP> <770@mind.UUCP> <6174@diamond.BBN.COM> <6521@diamond.BBN.COM> <1163@houdi.UUCP>
Reply-To: aweinste@Diamond.BBN.COM (Anders Weinstein)
Organization: BBN Laboratories, Inc., Cambridge, MA
Lines: 11
Keywords: icons, categories, symbols, grounding, modularity, cognition
Xref: utgpu comp.ai:482 comp.cog-eng:114

In article <1163@houdi.UUCP> marty1@houdi.UUCP (M.BRILLIANT) writes:
>> 	(A) The symbols in a purely symbolic system ...
>
>What exactly is this "purely" symbolic approach?  What impure approach
>might be necessary?  "Purely symbolic" sounds like a straw man ...

The phrase "purely symbolic" was just my short label for the AI strategy that
Stevan Harnad has been criticizing. Yes this strategy *does* encompass the
use of sensors and effectors and (maybe) motivations. Sorry if the term was
misleading, I was only using it as pointer;  consult Harnad's postings for a
fuller characterization.