X-Message-Number: 4090
From:  (David Stodolsky)
Subject: FWD: SYMBOLIC AND SUBSYMBOLIC COGNITIVE SCIENCE
Date: Sun, 26 Mar 95 10:33:53 +0100 (CET)


Forward of letter <> from PSYCOLOQUY 
<>:

Date:         Fri, 17 Mar 1995 05:59:02 -0500
Reply-To: psyc%
From: PSYCOLOQUY <>
Subject:      psycoloquy.95.6.04.language-network.13.miikkulainen (190 lines)
To: Multiple recipients of list PSYC <>

psycoloquy.95.6.04.language-network.13.miikkulainen  Friday 14 Mar 1995
ISSN 1055-0143                 (12 paragraphs, 9 references, 190 lines)
PSYCOLOQUY is sponsored by the American Psychological Association (APA)
                Copyright 1995 Risto Miikkulainen

                SYMBOLIC AND SUBSYMBOLIC COGNITIVE SCIENCE
                Reply to Dror & Young on Language-Network

                Risto Miikkulainen
                Department of Computer Sciences
                The University of Texas at Austin
                Austin, TX 78712
                

    ABSTRACT: Symbolic and subsymbolic cognitive science can be seen as
    not competing but complementary approaches, serving different
    roles. Even though they are perhaps based on incompatible
    foundations, symbolic research can serve as a guideline for
    developing subsymbolic models, pointing out ways in which a large
    cognitive process could be broken apart and made tractable with
    current techniques.

I. INTRODUCTION

1. By their very nature, the symbolic and subsymbolic approaches to
cognitive science appear to be incompatible. The main difference is
that symbolic representations, such as lisp structures, are
concatenative: it is possible to access and change them part by part.
On the other hand, distributed representations, such as associations
stored in the weights of a backpropagation network, cannot be modified
without affecting all other information in the network (see also van
Gelder, 1990). This leads to very different learning and performance
properties for the two approaches. Symbolic systems tend to be better
in processing structure and building abstractions, whereas neural
networks naturally discover surface-level regularities and perform
robustly under minor variations.

2. It may be that eventually all of cognition can be understood in
terms of neural processes operating at the subsymbolic level in the
brain.  However, this would by no means render the symbolic approach
irrelevant at this point. I agree with the possibility Dror and Young
(1994) outline in their review of Subsymbolic Natural Language
Processing (Miikkulainen, 1993; 1994), namely that the two approaches
may co-exist for a long time in cognitive science, serving distinctly
different roles. An often-used analogy is that of Newtonian physics and
relativity: It is sometimes necessary to take into account the
low-level neural mechanisms in explaining a particular phenomenon,
whereas in other cases a higher-level symbolic description is a
sufficient approximation and a more elegant and clear way of describing
the process.

David S. Stodolsky, PhD,  Euromath Center,  University of Copenhagen
Universitetsparken 5, DK-2100 Copenhagen, Denmark. 
 Tel.: +45 38 33 03 30. Fax: +45 38 33 88 80  (C)
 [ Keep USENET free! - http://iems.jpl.nasa.gov/~dave/voteno.html ]

Rate This Message: http://www.cryonet.org/cgi-bin/rate.cgi?msg=4090