From newshub.ccs.yorku.ca!ists!helios.physics.utoronto.ca!news-server.csri.toronto.edu!psych.toronto.edu!christo Tue Nov 19 11:10:50 EST 1991
Article 1393 of comp.ai.philosophy:
Xref: newshub.ccs.yorku.ca sci.philosophy.tech:989 comp.ai.philosophy:1393
Newsgroups: sci.philosophy.tech,comp.ai.philosophy
Path: newshub.ccs.yorku.ca!ists!helios.physics.utoronto.ca!news-server.csri.toronto.edu!psych.toronto.edu!christo
>From: christo@psych.toronto.edu (Christopher Green)
Subject: Re: Daniel Dennett (was Re: Commenting on the pos
Message-ID: <1991Nov19.045255.23267@psych.toronto.edu>
Organization: Department of Psychology, University of Toronto
References: <JMC.91Nov17135110@SAIL.Stanford.EDU> <1991Nov17.190935.5546@husc3.harvard.edu> <1991Nov18.152531.4246@newcastle.ac.uk>
Date: Tue, 19 Nov 1991 04:52:55 GMT

In article <1991Nov18.152531.4246@newcastle.ac.uk> Chris.Holt@newcastle.ac.uk (Chris Holt) writes:
>
>        [rec.arts.books deleted from Newsgroups line]
>
>Um, what's wrong with the following scenario?  Knowledge acquisition
>consists of the registering of primary sensory data by a neural net,
>that organizes it and finds regularities.  These regularities can be
>thought of as loci in a concept space, with fuzzy boundaries; as more
>input is processed, the inherent ambiguity is reduced.  When two loci
>are sufficiently distinguishable (the ambiguity between them crosses
>an arbitrary threshold), they are understood as distinct, and treated
>as points rather than balls (much as very small open intervals on the
>real line can be approximated as points).
>
To begin with, it sounds unbelievably verificationist to me. If that's
not enough to scare you off, then carry on. :-)

-- 
Christopher D. Green                christo@psych.toronto.edu
Psychology Department               cgreen@lake.scar.utoronto.ca
University of Toronto
---------------------


