Connectionism, Rule Following, and Symbolic Manipulation

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 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.