Connectionism and the problem of systematicity: why Smolensky's solution doesn't work.

By Jerry A. Fodor, B. McLaughlin. 1990

Subfields: Cognitive Science & Psychology, Philosophy

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Cognitive Science & Psychology

In Philosophy

Citations in the corpus

Neural Logic Machines (2019, background): “Starting from Fodor & Pylyshyn (1988), however, there has been a debate over the problem of systematicity (such as understanding recursive systems) in connectionist models (Fodor & McLaughlin, 1990; Hadley, 1994; Jansen & Watter, 2012).”
Distributed representations for extended syntactic transformation (2000, background): “1 Whether or not the level of systematicity actually achieved in connectionist systems should be regarded to be a cognitively plausible demonstration of systematicity has been the matter of much debate (cf. Smolensky 1987, 1988, Fodor and McLaughlin 1990, van Gelder 1990, Blank et al .”
Learning to Reason with Third-Order Tensor Products (2018, background): “Similarly, the distributed representations f and r are assigned manually instead of being learned from data, yielding arguments against the TPR as a connectionist theory of cognition [30].”
How Limited Systematicity Emerges: A Computational Cognitive Neuroscience Approach (Author's Manuscript) (2014, background): “FP88 made the point that connectionist models of that time failed to exhibit these features, and thus were insufficient models of the full power of human cognition (Fodor & Pylyshyn, 1988; Fodor & McLaughlin, 1990; McLaughlin, 1993).”
Darwin's mistake: Explaining the discontinuity between human and nonhuman minds (2008, unknown): “But as Fodor and colleagues have repeatedly argued (e.g., Fodor 1997; Fodor & McLaughlin 1990), the kind of systematicity posited by the PSS hypothesis is not statistical or accidental or a by-product of domainspecific adaptations; rather, it arises as a matter of nomological necessity from the…”
The Unstoppable Rise of Computational Linguistics in Deep Learning (2020, background): “tures were not adequate to account for regularities which they characterised as systematicity (see also (Smolensky, 1990; Fodor and McLaughlin, 1990)).”
Strong systematicity through sensorimotor conceptual grounding: an unsupervised, developmental approach to connectionist sentence processing (2012, background): “Further, even if a single demonstration of systematicity in a connectionist system was developed, this would be insufficient – systematicity is a general property of cognition (Fodor and McLaughlin 1990 ) and should also be a broad property of any model of cognition.”