The DOI matches its Crossref record; 86 of the 86 references it cites were found in a registry or an index.
Rethinking Eliminative Connectionism
Open accessAbstract
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.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Learning representations by back-propagating errors
Rumelhart, D. E., Hinton, G. E., & Williams, R. J. (1986) · Nature · doi:10.1038/323533a0 · Cited by 31,892
Learning Internal Representations by Error Propagation
Rumelhart, D. E., Hinton, G. E., & Williams, R. J. (1985) · doi:10.21236/ada164453 · Cited by 16,172
Elman, J. L. (1990) · Cognitive Science · doi:10.1207/s15516709cog1402_1 · Cited by 11,212
Self-Organization and Associative Memory
Kohonen, T. (1989) · Springer Series in Information Sciences · doi:10.1007/978-3-642-88163-3 · Cited by 8,740
Anderson, J. R. (2013) · doi:10.4324/9781315799438 · Cited by 6,761
The Psychology of Learning and Motivation: Advances in Research and Theory
(2010) · Psychology of Learning and Motivation · doi:10.1016/c2009-0-62209-1 · Cited by 5,994
(1983) · Cited by 5,041
Fodor, J. A. (1975) · Medical Entomology and Zoology · Cited by 4,588
Madden, E. H., Goodman, N., & Melsen, A. G. V. (1955) · Philosophy and Phenomenological Research · doi:10.2307/2103789 · Cited by 4,377
(1991) · Choice Reviews Online · doi:10.5860/choice.28-5376 · Cited by 4,207
Cited by
Foundations of Language: Brain, Meaning, Grammar, Evolution
Jackendoff, R. (2002) · doi:10.1093/acprof:oso/9780198270126.001.0001 · Cited by 3,244
Building machines that learn and think like people
Lake, B. M., Ullman, T. D., Tenenbaum, J. B., & Gershman, S. J. (2017) · Behavioral and Brain Sciences · doi:10.1017/s0140525x16001837 · Cited by 2,550
Building Machines That Learn and Think Like People
Lake, B. M., Ullman, T. D., Tenenbaum, J. B., & Gershman, S. J. (2016) · arXiv · doi:10.48550/arxiv.1604.00289 · Cited by 2,550
Shortcut learning in deep neural networks
Geirhos, R., Jacobsen, J.-H., Michaelis, C., Zemel, R., Brendel, W., Bethge, M., & Wichmann, F. A. (2020) · Nature Machine Intelligence · doi:10.1038/s42256-020-00257-z · Cited by 2,224
Neuroscience-Inspired Artificial Intelligence
Hassabis, D., Kumaran, D., Summerfield, C., & Botvinick, M. (2017) · Neuron · doi:10.1016/j.neuron.2017.06.011 · Cited by 1,557
Chang, F., Dell, G. S., & Bock, K. (2006) · Psychological Review · doi:10.1037/0033-295x.113.2.234 · Cited by 984
Deep Learning: A Critical Appraisal
Marcus, G. (2018) · arXiv · doi:10.48550/arxiv.1801.00631 · Cited by 853
Self-citationA symbolic-connectionist theory of relational inference and generalization.
Hummel, J. E., & Holyoak, K. J. (2003) · Psychological Review · doi:10.1037/0033-295x.110.2.220 · Cited by 567
“First, algorithms such as back-propagation, which are based on representations that do not encode variable bindings, simply fail to generate human-like relational inferences, and fare poorly in tests of generalization to novel examples (see Hinton, 1986; Holyoak et al., 1994; Marcus, 1998).”
MethodJones, M., & Love, B. C. (2011) · Behavioral and Brain Sciences · doi:10.1017/s0140525x10003134 · Cited by 533
Infant artificial language learning and language acquisition
Gómez, R. L., & Gerken, L. (2000) · Trends in Cognitive Sciences · doi:10.1016/s1364-6613(00)01467-4 · Cited by 506
A Parallel Architecture perspective on language processing
Jackendoff, R. (2007) · Brain Research · doi:10.1016/j.brainres.2006.08.111 · Cited by 431
Symbolically speaking: a connectionist model of sentence production
Chang, F. (2002) · Cognitive Science · doi:10.1016/s0364-0213(02)00079-4 · Cited by 337
Exemplar-learning and schematization in a usage-based account of syntactic acquisition
Abbot-Smith, K., & Tomasello, M. (2006) · The Linguistic Review · doi:10.1515/tlr.2006.011 · Cited by 309
The Next Decade in AI: Four Steps Towards Robust Artificial Intelligence
Marcus, G. (2020) · arXiv · doi:10.48550/arxiv.2002.06177 · Cited by 297
“…trained on f(x)=x for only for even numbers, it will not extend the identity function to odd numbers, which lie outside the training distribution (Marcus, 1998) , To a human, it is obvious from a few examples that each output node, including the rightmost one, which represents the "1" bit…”
BackgroundMethodInfluentialSelf-citationTrading spaces: Computation, representation, and the limits of uninformed learning
Clark, A., & Thornton, C. (1997) · Behavioral and Brain Sciences · doi:10.1017/s0140525x97000022 · Cited by 297
Syntax and morphology in Williams syndrome
Clahsen, H. (1998) · Cognition · doi:10.1016/s0010-0277(98)00049-3 · Cited by 288
Susarla, A., Gopal, R., Thatcher, J. B., & Sarker, S. (2023) · Information Systems Research · doi:10.1287/isre.2023.ed.v34.n2 · Cited by 285
Inductive biases for deep learning of higher-level cognition
Goyal, A., & Bengio, Y. (2022) · Proceedings of the Royal Society A: Mathematical, Physical and Engineering Sciences · doi:10.1098/rspa.2021.0068 · Cited by 300
Empirical re-assessment of stimulus poverty arguments
Legate, J. A., & Yang, C. D. (2002) · The Linguistic Review · doi:10.1515/tlir.19.1-2.151 · Cited by 280
Mind Design and Minimal Syntax
Hinzen, W. (2006) · doi:10.1093/acprof:oso/9780199289257.001.0001 · Cited by 273
The architecture of grammar and the division of labor in exponence
Bermúdez-Otero, R. (2012) · The Morphology and Phonology of Exponence · doi:10.1093/acprof:oso/9780199573721.003.0002 · Cited by 269
Connectionist modelling in psychology: A localist manifesto
Page, M. (2000) · Behavioral and Brain Sciences · doi:10.1017/s0140525x00003356 · Cited by 267
Nature, Nurture And Universal Grammar
Crain, S., & Pietroski, P. (2001) · Linguistics and Philosophy · doi:10.1023/a:1005694100138 · Cited by 264
Deep problems with neural network models of human vision
Bowers, J. S., Malhotra, G., Dujmović, M., Llera Montero, M., Tsvetkov, C., Biscione, V., Puebla, G., Adolfi, F., Hummel, J. E., Heaton, R. F., et al. (2023) · Behavioral and Brain Sciences · doi:10.1017/s0140525x22002813 · Cited by 204
Indirection and symbol-like processing in the prefrontal cortex and basal ganglia
Kriete, T., Noelle, D. C., Cohen, J. D., & O’Reilly, R. C. (2013) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.1303547110 · Cited by 181
Rearranging the Familiar: Testing Compositional Generalization in Recurrent Networks
Loula, J., Baroni, M., & Lake, B. (2018) · Proceedings of the 2018 EMNLP Workshop BlackboxNLP: Analyzing and Interpreting Neural Networks for NLP · doi:10.18653/v1/w18-5413 · Cited by 136
McCoy, R. T., Yao, S., Friedman, D., Hardy, M. D., & Griffiths, T. L. (2024) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.2322420121 · Cited by 96
The problem of rapid variable creation
Hadley, R. F. (2009) · Neural Computation · doi:10.1162/neco.2008.07-07-572 · Cited by 23
Do Fine-tuned Commonsense Language Models Really Generalize?
Kejriwal, M., & Shen, K. (2020) · arXiv · doi:10.48550/arxiv.2011.09159 · Cited by 6
Metadata
- Authors
- Marcus, G. F.
- Venue
- Cognitive Psychology
- Publisher
- Elsevier BV
- Published
- 1998-12
- Volume
- 37
- Issue
- 3
- Pages
- 243-282
- ISSN
- 0010-0285 (ISSN-L)
- OpenAlex
- W1966678693
- Cited by
- 348
- References
- 86
- FWCI
- 25.49
- Type
- journal article
- Language
- en
- Open access
- hybrid
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
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.