Relay-Version: version B 2.10 5/3/83; site utzoo.UUCP Path: utzoo!mnetor!seismo!husc6!rutgers!princeton!mind!harnad From: harnad@mind.UUCP (Stevan Harnad) Newsgroups: comp.ai,comp.cog-eng Subject: Re: The symbol grounding problem Message-ID: <914@mind.UUCP> Date: Fri, 26-Jun-87 00:38:02 EDT Article-I.D.: mind.914 Posted: Fri Jun 26 00:38:02 1987 Date-Received: Sat, 27-Jun-87 05:02:03 EDT References: <764@mind.UUCP> <768@mind.UUCP> <770@mind.UUCP> <6174@diamond.BBN.COM> <1172@houdi.UUCP> Organization: Cognitive Science, Princeton University Lines: 26 Summary: Symbol grounding requires not only invertible iconic representations but selectively noninvertible and APPROXIMATE catgeorical reps too Xref: mnetor comp.ai:573 comp.cog-eng:146 John Cugini on ailist@stripe.sri.com writes: > What if there were a few-to-one transformation between the skin-level > sensors (remember Harnad proposes "skin-and-in" invertibility > as being necessary for grounding) and the (somewhat more internal) > iconic representation. My example was to suppose that #1: > a combination of both red and green retinal receptors and #2 a yellow > receptor BOTH generated the same iconic yellow. > Clearly this iconic representation is non-invertible back out to the > sensory surfaces, but intuitively it seems like it would be grounded > nonetheless - how about it? Invertibility is a necessary condition for iconic representation, not for grounding. Grounding symbolic representations (according to my hypothesis) requires both iconic and categorical representations. The latter are selective, many-to-few, invertible only in the features they pick out and, most important, APPROXIMATE (e.g., as between red-green and yellow in your example above). This point has by now come up several times... -- Stevan Harnad (609) - 921 7771 {bellcore, psuvax1, seismo, rutgers, packard} !princeton!mind!harnad harnad%mind@princeton.csnet harnad@mind.Princeton.EDU