hadley@fornax.UUCP (Bob Hadley) (05/25/90)
Connectionism, Rule Following, and Symbolic Manipulation
by
Robert F. Hadley
School of Computing Science
Simon Fraser University
Burnaby, Canada V5A 1S6
hadley@cs.sfu.ca
Abstract
At present, the prevailing Connectionist methodology for
representing rules is to implicitly embody rules in
"neurally-wired" networks. That is, the methodology adopts the stance
that rules must either be hard-wired or "trained into" neural
structures, rather than represented via explicit symbolic
structures. Even recent attempts to implement production
systems within connectionist networks have assumed that
condition-action rules (or rule schema) are to be embodied in
the structure of individual networks. Such networks must
be grown or trained over a significant span of time. However,
arguments are presented herein that humans sometimes follow
rules which are very rapidly assigned explicit internal
representations, and that humans possess general mechanisms
capable of interpreting and following such rules. In
particular, arguments are presented that the speed with which
humans are able to follow rules of novel structure
demonstrates the existence of general-purpose rule following
mechanisms. It is further argued that the existence of
general-purpose rule following mechanisms strongly indicates
that explicit rule following is not an isolated phenomenon,
but may well be a pervasive aspect of cognition. The
arguments presented here are pragmatic in nature, and are
contrasted with the kind of arguments developed by Fodor and
Pylyshyn in their recent, influential paper.