TY - JOUR
T1 - Rethinking Eliminative Connectionism
AU - Marcus, Gary F.
N1 - Funding Information:
For comments on earlier drafts, I thank Dan Anderson, Neil Berthier, Ned Block, Richard Bogartz, Michael Brent, Mike Casey, Noam Chomsky, Chuck Clifton, Zoubin Ghahramani, Graeme Halford, John Hummel, Jay McClelland, Denis Mareschal, Randy O’Reilly, Steve Pinker, Zenon Pylyshyn, Erik Reichle, Ed Stein, Neil Stillings, Whitney Tabor, Zsofia Zvolen-szky, and several anonymous reviewers. For helpful discussion, I thank Andy Barto, Bob Berwick, Susan Carey, Gary Dell, Dan Dennett, Jerry Fodor, Lee Giles, Keith Holyoak, Ray Jackendoff, Robbie Jacobs, Art Markman, Mike McCloskey, Elissa Newport, Neal Pearlmut-ter, Steven Phillips, Terry Regier, Mike Tanenhaus, David Touretzky, and audiences at Birk-beck College, Johns Hopkins University, NYU, Oxford University, Rutgers University, UCLA, University of Essex, University of Massachusetts, University of Rochester, the April 1996 Edinburgh Conference on Evolution and Language, and the November 1996 Annual Meeting of the Psychonomics Society. This research was partially supported by a Faculty Research Grant from the University of Massachusetts. Address correspondence and reprint requests to Gary Marcus, Department of Psychology, New York University, 6 Washington Place, New York, NY 10003. E-mail: gary.marcus@nyu.edu. 243
PY - 1998/12
Y1 - 1998/12
N2 - Humans routinely generalize universal relationships to unfamiliar instances. If we are told "if glork then frum," and "glork," we can infer "frum"; any name that serves as the subject of a sentence can appear as the object of a sentence. These universals are pervasive in language and reasoning. One account of how they are generalized holds that humans possess mechanisms that manipulate symbols and variables; an alternative account holds that symbol-manipulation can be eliminated from scientific theories in favor of descriptions couched in terms of networks of interconnected nodes. Can these "eliminative" connectionist models offer a genuine alternative? This article shows that eliminative connectionist models cannot account for how we extend universals to arbitrary items. The argument runs as follows. First, if these models, as currently conceived, were to extend universals to arbitrary instances, they would have to generalize outside the space of training examples. Next, it is shown that the class of eliminative connectionist models that is currently popular cannot learn to extend universals outside the training space. This limitation might be avoided through the use of an architecture that implements symbol manipulation.
AB - Humans routinely generalize universal relationships to unfamiliar instances. If we are told "if glork then frum," and "glork," we can infer "frum"; any name that serves as the subject of a sentence can appear as the object of a sentence. These universals are pervasive in language and reasoning. One account of how they are generalized holds that humans possess mechanisms that manipulate symbols and variables; an alternative account holds that symbol-manipulation can be eliminated from scientific theories in favor of descriptions couched in terms of networks of interconnected nodes. Can these "eliminative" connectionist models offer a genuine alternative? This article shows that eliminative connectionist models cannot account for how we extend universals to arbitrary items. The argument runs as follows. First, if these models, as currently conceived, were to extend universals to arbitrary instances, they would have to generalize outside the space of training examples. Next, it is shown that the class of eliminative connectionist models that is currently popular cannot learn to extend universals outside the training space. This limitation might be avoided through the use of an architecture that implements symbol manipulation.
UR - http://www.scopus.com/inward/record.url?scp=0032247463&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=0032247463&partnerID=8YFLogxK
U2 - 10.1006/cogp.1998.0694
DO - 10.1006/cogp.1998.0694
M3 - Article
C2 - 9892549
AN - SCOPUS:0032247463
SN - 0010-0285
VL - 37
SP - 243
EP - 282
JO - Cognitive Psychology
JF - Cognitive Psychology
IS - 3
ER -