Biologically Plausible, Human‐Scale Knowledge Representation
Open accessThe DOI matches its Crossref record; 11 of the 11 references it cites were found in a registry or an index.
Abstract
Several approaches to implementing symbol‐like representations in neurally plausible models have been proposed. These approaches include binding through synchrony (Shastri & Ajjanagadde,), “mesh” binding (van der Velde & de Kamps,), and conjunctive binding (Smolensky,). Recent theoretical work has suggested that most of these methods will not scale well, that is, that they cannot encode structured representations using any of the tens of thousands of terms in the adult lexicon without making implausible resource assumptions. Here, we empirically demonstrate that the biologically plausible structured representations employed in the Semantic Pointer Architecture (SPA) approach to modeling cognition (Eliasmith,) do scale appropriately. Specifically, we construct a spiking neural network of about 2.5 million neurons that employs semantic pointers to successfully encode and decode the main lexical relations in WordNet, which has over 100,000 terms. In addition, we show that the same representations can be employed to construct recursively structured sentences consisting of arbitrary WordNet concepts, while preserving the original lexical structure. We argue that these results suggest that semantic pointers are uniquely well‐suited to providing a biologically plausible account of the structured representations that underwrite human cognition.
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
ImageNet: A large-scale hierarchical image database
Deng, J., Dong, W., Socher, R., Li, L.-J., Li, K., & Fei-Fei, L. (2009) · 2009 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2009.5206848 · Cited by 65,333
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
How Can the Human Mind Occur in the Physical Universe?
Anderson, J. R. (2007) · doi:10.1093/acprof:oso/9780195324259.001.0001 · Cited by 1,483
Distributed representations, simple recurrent networks, and grammatical structure
Elman, J. L. (1991) · Machine Learning · doi:10.1007/bf00114844 · Cited by 1,354
Smolensky, P. (1990) · Artificial Intelligence · doi:10.1016/0004-3702(90)90007-m · Cited by 959
Jonas, P., Major, G., & Sakmann, B. (1993) · The Journal of Physiology · doi:10.1113/jphysiol.1993.sp019965 · Cited by 720
Holographic reduced representations
Plate, T. A. (1995) · IEEE Transactions on Neural Networks · doi:10.1109/72.377968 · Cited by 657 · cited 2×
“Here we employ a close relative of Holographic Reduced Representations (Plate, 2003), a type of VSA in which binding is implemented via circular convolution , superposition is implemented via vector addition and vectors representing symbols are randomly chosen from the D-dimensional unit sphere.”
MethodA 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 · cited 1×
“More recently, binding through synchrony has seen a revival in the LISA [20] and DORA [5] architectures, which focus on representing structures for analogical reasoning.”
BackgroundfMRI evidence for word association and situated simulation in conceptual processing
Simmons, W. K., Hamann, S. B., Harenski, C. L., Hu, X. P., & Barsalou, L. W. (2008) · Journal of Physiology-Paris · doi:10.1016/j.jphysparis.2008.03.014 · Cited by 197 · cited 1×
“Recent fMRI and behavioral experiments are supportive of this view (Simmons et al., 2008; Solomon & Barsalou, 2004).”
ResultIndirection 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
Cited by
40 years of cognitive architectures: core cognitive abilities and practical applications
Kotseruba, I., & Tsotsos, J. K. (2020) · Artificial Intelligence Review · doi:10.1007/s10462-018-9646-y · Cited by 539
Reconciling deep learning with symbolic artificial intelligence: representing objects and relations
Garnelo, M., & Shanahan, M. (2019) · Current Opinion in Behavioral Sciences · doi:10.1016/j.cobeha.2018.12.010 · Cited by 255
“Although various ways to incorporate variables and variable binding in neural networks have been proposed, some biologically inspired (e.g. [43,44]) and some less so (e.g. [45]), to date these have not been integrated with mechanisms for learning symbolic relational representations from raw data.”
BackgroundKleyko, D., Rachkovskij, D., Osipov, E., & Rahimi, A. (2023) · ACM Computing Surveys · doi:10.1145/3558000 · Cited by 141
Metadata
- Authors
- Crawford, E., Gingerich, M., & Eliasmith, C.
- Venue
- Cognitive Science
- Publisher
- Wiley
- Published
- 2015-07-14
- Volume
- 40
- Issue
- 4
- Pages
- 782-821
- ISSN
- 0364-0213 (ISSN-L)
- 1551-6709
- OpenAlex
- W1579683266
- Cited by
- 81
- References
- 11
- FWCI
- 5.32
- Type
- journal article
- Language
- en
- Open access
- bronze
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.