The DOI matches its Crossref record; 20 of the 24 references it cites were found in a registry or an index.
The symbol grounding problem
Open accessAbstract
There has been much discussion recently about the scope and limits of purely symbolic models of the mind and about the proper role of connectionism in cognitive modeling. This paper describes the "symbol grounding problem": How can the semantic interpretation of a formal symbol system be made intrinsic to the system, rather than just parasitic on the meanings in our heads? How can the meanings of the meaningless symbol tokens, manipulated solely on the basis of their (arbitrary) shapes, be grounded in anything but other meaningless symbols? The problem is analogous to trying to learn Chinese from a Chinese/Chinese dictionary alone. A candidate solution is sketched: Symbolic representations must be grounded bottom-up in nonsymbolic representations of two kinds: (1) "iconic representations" , which are analogs of the proximal sensory projections of distal objects and events, and (2) "categorical representations" , which are learned and innate feature-detectors that pick out the invariant features of object and event categories from their sensory projections. Elementary symbols are the names of these object and event categories, assigned on the basis of their (nonsymbolic) categorical representations. Higher-order (3) "symbolic representations" , grounded in these elementary symbols, consist of symbol strings describing category membership relations (e.g., "An X is a Y that is Z"). Connectionism is one natural candidate for the mechanism that learns the invariant features underl…
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“The question of whether a formal system can itself interpret machine tokens highlights the centrality of the "symbol grounding problem" (Harnad, 1990), which Harnad defined as the problem of how to make semantic interpretations intrinsic to the symbol system, rather than merely parasitic on the meanings assigned to it by human interpreters.”
From Are Large Language Models Intentional? The Limits of Referential Grounding (2026) · cites this paper as Harnad, 1990
In the citing paper
“The thought experiment invites a negative answer.”
From The Vector Grounding Problem (2026) · cites this paper as Harnad, 1990
In the citing paper
“Classical AI systems, in other words, are fundamentally limited by the Symbol Grounding Problem.”
From The Vector Grounding Problem (2026) · cites this paper as Harnad, 1990
In the citing paper
“We have argued that the Symbol Grounding Problem, as introduced by Harnad (1990), also applies to deep neural networks such as generative pre-trained models, albeit in a slightly different form, which we have called the Vector Grounding Problem.”
From The Vector Grounding Problem (2026) · cites this paper as Harnad (1990)
In the citing paper
“Threfore, these systems remain limited in their ability to develop genuinely situated perception or to adapt through active exploration of novel environments (Harnad, 1990; Chemero, 2009).”
From Toward Enactive Artificial Intelligence (2026) · cites this paper as Harnad, 1990
Citations
Cites
The magical number seven, plus or minus two: Some limits on our capacity for processing information.
Miller, G. A. (1956) · Psychological Review · doi:10.1037/h0043158 · Cited by 17,812 · cited 1×
“Psychology became more like an empirical science when, with the gradual advent of cognitivism [17] [25] [29], it became acceptable to make inferences about the unobservable processes underlying behavior.”
Searle, J. R. (1980) · Behavioral and Brain Sciences · doi:10.1017/s0140525x00005756 · Cited by 6,954 · cited 1×
“The first comes from Searle's (1980) celebrated "Chinese Room Argument," in which the symbol grounding problem is referred to as the problem of intrinsic meaning (or "intentionality"): Searle challenges the core assumption of symbolic AI that a symbol system able to generate behavior indistinguishable from that of a p…”
A FRAMEWORK FOR REPRESENTING KNOWLEDGE
Minsky, M. (1988) · Readings in Cognitive Science · doi:10.1016/b978-1-4832-1446-7.50018-2 · Cited by 4,536
Connectionism and cognitive architecture: A critical analysis
Fodor, J. A., & Pylyshyn, Z. W. (1988) · Cognition · doi:10.1016/0010-0277(88)90031-5 · Cited by 4,022
Chomsky, N. (1980) · Behavioral and Brain Sciences · doi:10.1017/s0140525x00001515 · Cited by 2,650
On the proper treatment of connectionism
Smolensky, P. (1988) · Behavioral and Brain Sciences · doi:10.1017/s0140525x00052432 · Cited by 2,085
Methodological solipsism considered as a research strategy in cognitive psychology
Fodor, J. A. (1980) · Behavioral and Brain Sciences · doi:10.1017/s0140525x00001771 · Cited by 1,485 · cited 1×
“…interpretability (meaningfulness), as we shall see, was one of the defining features of the most prominent contender vying to become the theoretical vocabulary of cognitivism, the "language of thought" [6], which became the prevailing view in cognitive theory for several decades in the form of the”
Newell, A. (1980) · Cognitive Science · doi:10.1207/s15516709cog0402_2 · Cited by 1,458 · cited 1×
“From Newell [28], Pylyshyn [33], Fodor [6] and the classical work by von Neumann, Turing, Grdel, Church, etc. (see ref.”
Computation and cognition: issues in the foundations of cognitive science
Pylyshyn, Z. W. (1980) · Behavioral and Brain Sciences · doi:10.1017/s0140525x00002053 · Cited by 1,217 · cited 5×
“According to Fodor and Pylyshyn, this is a severe limitation, because many of our behavioral capacities appear to be symbolic, and hence the most natural hypothesis about the underlying cognitive processes that generate them would be that they too must be symbolic.”
InfluentialIntentional systems in cognitive ethology: The “Panglossian paradigm” defended
Dennett, D. C. (1983) · Behavioral and Brain Sciences · doi:10.1017/s0140525x00016393 · Cited by 1,046
Research works printed but not linked: 3
- S. Harnad, Computational hermeneutics, Social Epistemology, in press.
- McCarthy, 1969, Some philosophical problems from the standpoint of artificial intelligence, Vol. 4
- McClelland, 1986, Vol. 1
Cited by
Whatever next? Predictive brains, situated agents, and the future of cognitive science
Clark, A. (2013) · Behavioral and Brain Sciences · doi:10.1017/s0140525x12000477 · Cited by 5,924
Barsalou, L. W. (2008) · Annual Review of Psychology · doi:10.1146/annurev.psych.59.103006.093639 · Cited by 5,936
Glenberg, A. M., & Kaschak, M. P. (2002) · Psychonomic Bulletin & Review · doi:10.3758/bf03196313 · Cited by 2,361
The neurobiology of semantic memory
Binder, J. R., & Desai, R. H. (2011) · Trends in Cognitive Sciences · doi:10.1016/j.tics.2011.10.001 · Cited by 2,114
Embodiment and Cognitive Science
Gibbs, Jr. (2005) · Cambridge University Press eBooks · doi:10.1017/cbo9780511805844 · Cited by 1,589
Metadata
- Authors
- Harnad, S.
- Affiliations
- Princeton University (US)
- Corresponding author
- Harnad, Stevan
- ORCID
- Harnad, Stevan
- Venue
- Physica D: Nonlinear Phenomena
- Publisher
- Elsevier BV
- Published
- 1990-06
- Volume
- 42
- Issue
- 1-3
- Pages
- 335-346
- ISSN
- 0167-2789 (ISSN-L)
- OpenAlex
- W2107019937
- Cited by
- 4,235
- References
- 24
- Citations by year
- 2026: 142 · 2025: 147 · 2024: 170 · 2023: 160 · 2022: 192 · 2021: 174 · 2020: 184 · 2019: 225 · 2018: 144 · 2017: 178 · 2016: 138 · 2015: 122 · 2014: 122 · 2013: 133 · 2012: 132
- FWCI
- 101.98
- Type
- journal article
- Language
- en
- Open access
- green
- arxiv.org
- Licence
- www.elsevier.com/tdm/userlicense/1.0/ (tdm)
- Locations
- Physica D Nonlinear Phenomena (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- ePrints Soton (University of Southampton) (submittedVersion)
- arXiv (Cornell University)
- Topics
- Social Sciences › Arts and Humanities › Philosophy › Philosophy and Theoretical Science
- Life Sciences › Neuroscience › Cognitive Neuroscience › Embodied and Extended Cognition
- Social Sciences › Psychology › Experimental and Cognitive Psychology › Categorization, perception, and language
- Keywords
- symbol grounding problem, connectionism, symbolic representation, iconic representation, categorical representation, feature detectors, category names, cognitive modeling
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: The symbol grounding problem. https://app.cochat.ai/papers/10.1016/0167-2789(90)90087-6
- The paper
- Harnad, S. (1990). The symbol grounding problem. Physica D: Nonlinear Phenomena. https://doi.org/10.1016/0167-2789(90)90087-6
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.