Path: utzoo!utgpu!jarvis.csri.toronto.edu!mailrus!tut.cis.ohio-state.edu!rutgers!sunybcs!lammens
From: lammens@sunybcs.uucp (Jo Lammens)
Newsgroups: comp.ai
Subject: Symbolic Connectionism? (was Re: What IS a symbol?)
Summary: programmers still put the meaning in.
Keywords: connectionism, symbols
Message-ID: <5418@cs.Buffalo.EDU>
Date: 22 Apr 89 18:26:08 GMT
References: <11313@bcsaic.UUCP> <17467@cup.portal.com>
Sender: nobody@cs.Buffalo.EDU
Reply-To: lammens@sunybcs.UUCP (Jo Lammens)
Organization: SUNY/Buffalo Computer Science
Lines: 40

In article <17467@cup.portal.com> dan-hankins@cup.portal.com (Daniel B Hankins) writes:
>     This is important.  Traditional AI systems deal in English (or
>whatever language) words as their base symbol system.  The system is taught
>to manipulate these symbols on the basis of what the programmer has in mind
>as the meaning of the symbols.  Therefore, in some important sense, any
>meaning in the computer program was put there by the programmer.
>
>     However, Neural Networks are qualitatively different.  They use
>physical quantities (like synapse conductivities and neuron activation
>levels) as their base symbol system.  These 'symbols' then really do end up
>representing (in the sense you defined) external reality, because any
>'meaning' they acquire is a result of external experience rather than
>implicit assignment of meaning by a programmer.

As far as I know (correct me if I'm wrong), all neural network
topologies today are hand-crafted, and there is no prospect for any
sort of general-purpose topology. In other words, based on what the
'programmer' (should I say builder, or perhaps grower) has in mind as
the purpose of the network and the meaning of the symbols it
manipulates, a certain topology is chosen (number of layers, number of
neurons, number of connections, type of input/activation/output
functions, and what have you). Then the external symbols the net is
supposed to manipulate are assigned to (combinations of) input and/or
output values for the net. Then the net sets off, merrily manipulating
its 'symbols' (activation levels and connection strengths), until the
programmer/builder decides that the net converges successfully, or
not. This decision is based on the EXTERNAL INTERPRETATIONS of the
net's 'symbols', which are no more intrinsically related to the
activation levels etc. than the meaning of words are related to their
form, or the meaning of other symbols to the form of the symbols
(leaving the inevitable exceptions like pictograms etc out of
consideration). So where is the qualitative difference? The technique
used to learn the system how to manipulate the symbols is different,
but the relation between the symbols and their external interpretation
is not. This is not a plea for or against neural networks.

Jo Lammens

BITNET: lammens@sunybcs.BITNET          Internet:  lammens@cs.Buffalo.EDU
UUCP: ...!{watmath,boulder,decvax,rutgers}!sunybcs!lammens