Connectionism isn't magic

Ramsey, Stich and Garon's recent paper Connectionism, Eliminativism, and the Future of Folk Psychology claims a certain style of connectionism to be the final nail in the coffin of folk psychology. I argue that their paper fails to show this, and that the style of connectionism they illustrate can in fact supplement, rather than compete with, the claims of a theory of cognition based in folk psychology's ontology. Ramsey, Stich and Garon's argument relies on the lack of easily identifiable symbols inside the connectionist network they discuss, and they suggest that the existence of a system which behaves in a cognitively interesting way, but which cannot be explained by appeal to internal symbol processing, falsifies central assumptions of folk psychology. My claim is that this argument is flawed, and that the theorist need not discard folk psychology in order to accept that the network illustrated exhibits cognitively interesting behaviour, even if it is conceded that symbols cannot be readily identified within the network.This paper was in part prepared whilst I was a Vacation Scholar at the Automated Reasoning Project, Australian National University. It was presented in its present form to the Department of Philosophy, Institute of Advanced Studies, ANU. I owe a deep gratitude to many people who read and commented on earlier drafts of this paper, especially Phillip Staines and Phillip Cam from UNSW, Ed Mares from the Automated Reasoning Project at the ANU, and Frank Jackson, Karen Neander and David Braddon-Mitchell from the Philosophy Department, IAS, ANU. All the paper's faults are, of course, mine.