“During the past two years there has been more discussion of the foundations of cognitive science than in the 25 years preceding. The impetus for this reexamination has been a new approach to studying the mind, called “Con-nectionism”, “Parallel Distributed Processing”, or “Neural Networks”.
The assumptions behind this approach differ in substantial ways from the “central dogma” of cognitive science, that intelligence is the result of the manipulation of structured symbolic expressions. Instead, connectionists suggest that intelligence is to be understood as the result of the transmission of activation levels in large networks of densely interconnected simple units.
Connectionism has spawned an enormous amount of research activity in a short time. Much of the excitement surrounding the movement has been inspired by the rich possibilities inherent in ideas such as massive parallel processing, distributed representation, constraint satisfaction, neurally-realis-tic cognitive models, and subsymbolic or microfeatural analyses.
Models incorporating various combinations of these notions have been proposed for behavioral abilities as diverse as Pavlovian conditioning, visual recognition, and language acquisition.
Perhaps it is not surprising that in a burgeoning new field there have been few systematic attempts to analyze the core assumptions of the new approach in comparison with those of the approach it is trying to replace, and to juxtapose both sets of assumptions with the most salient facts about human cognition. Analyses of new scientific models have their place, but they are premature before substantial accomplishments in the new field have been reported and digested.
Now that many connectionist efforts are well known, it may be time for a careful teasing apart of what is truly new and what is just a relabeling of old notions; of the empirical generalizations that are sound and those that are likely to be false; of the proposals that naturally belong together and those that are logically independent.
This special issue of Cognition on Connectionism and Symbol Systems is intended to start such a discussion. Each of the papers in the issue attempts to analyze in careful detail the accomplishments and liabilities of connectio-nist models of cognition. The papers were independently and coincidentally submitted to the journal—a sign, perhaps, that the time is especially right for reflection on the status of connectionist theories. Though each makes different points, there are noteworthy common themes.
All the papers are highly critical of certain aspects of connectionist models, particularly as applied to language of the parts of cognition employing language-like operations. All of them try to pinpoint what it is about human cognition that supports the traditional physical symbol system hypothesis. Yet none of the papers is an outright dismissal—in each case, the authors discuss aspects of cognition for which connectionist models may yield critical insights.
Perhaps the most salient common theme in these papers is that many current connectionist proposals are not motivated purely by considerations of parallel processing, distributed representation, constraint satisfaction, or other computational issues, but seem to be tied more closely to an agenda of reviving associationism as a central doctrine of learning and mental functioning. As a result, discussions of connectionism involve a reexamination of debates about the strengths and weaknesses of associationist mechanisms that were a prominent part of cognitive theory 30 years ago and 300 years ago.
These papers comprise the first critical examination of connectionism as a scientific theory. The issues they raise go to the heart of our understanding of how the mind works. We hope that they begin a fruitful debate among scientists from different frameworks as to the respective roles of connectionist networks and physical symbol systems in explaining intelligence.”