Neural representational geometry underlies few-shot concept learning
Open accessThe DOI matches its Crossref record; 70 of the 70 references it cites were found in a registry or an index.
Abstract
Understanding the neural basis of the remarkable human cognitive capacity to learn novel concepts from just one or a few sensory experiences constitutes a fundamental problem. We propose a simple, biologically plausible, mathematically tractable, and computationally powerful neural mechanism for few-shot learning of naturalistic concepts. We posit that the concepts that can be learned from few examples are defined by tightly circumscribed manifolds in the neural firing-rate space of higher-order sensory areas. We further posit that a single plastic downstream readout neuron learns to discriminate new concepts based on few examples using a simple plasticity rule. We demonstrate the computational power of our proposal by showing that it can achieve high few-shot learning accuracy on natural visual concepts using both macaque inferotemporal cortex representations and deep neural network (DNN) models of these representations and can even learn novel visual concepts specified only through linguistic descriptors. Moreover, we develop a mathematical theory of few-shot learning that links neurophysiology to predictions about behavioral outcomes by delineating several fundamental and measurable geometric properties of neural representations that can accurately predict the few-shot learning performance of naturalistic concepts across all our numerical simulations. This theory reveals, for instance, that high-dimensional manifolds enhance the ability to learn new concepts from few examples. Intriguingly, we observe striking mismatches between the geometry of manifolds in the primate visual pathway and in trained DNNs. We discuss testable predictions of our theory for psychophysics and neurophysiological experiments.
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
Figures








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.
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?
The source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“Furthermore, recent studies have found a striking representational alignment between a wide variety of ANNs and the human brain, despite their having different architectures, network initializations, learning objectives, and even different modalities such as language and vision [12,15–22]”
From The Umwelt Representation Hypothesis: rethinking Universality (2026) · cites this paper as [17]
Experimental — accuracy not yet measuredThe cited source says what the claim attributes to it.
In the citing paper
“Sorscher et al. (2022) show a setting in which word embeddings of visual concept names can be isometrically mapped to image embeddings for those same concepts.”
From The Platonic Representation Hypothesis (2024) · cites this paper as Sorscher et al. (2022)
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 · cited 1×
“A subset of 1,000 concepts comprises the standard ImageNet1k training set used in the ImageNet Large Scale Visual Recognition Challenge (68).”
MethodGlove: Global Vectors for Word Representation
Pennington, J., Socher, R., & Manning, C. (2014) · Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.3115/v1/d14-1162 · Cited by 34,071 · cited 2×
“To test this hypothesis, we obtain language representations for the names of the 1,000 familiar visual concepts used to train our DNN, from a standard word-vector embedding model (44) trained to produce a neural representation of all words in English based on cooccurrence statistics in a large corpus (Section P).”
MethodPyTorch: An Imperative Style, High-Performance Deep Learning Library
Paszke, A., Gross, S., Massa, F., Lerer, A., Bradbury, J., Chanan, G., Killeen, T., Lin, Z., Gimelshein, N., Antiga, L., et al. (2019) · arXiv · doi:10.48550/arxiv.1912.01703 · Cited by 31,473 · cited 1×
“All DNNs studied throughout this work are standard architectures available in the PyTorch library (69) and are pretrained on the ImageNet1k dataset.”
MethodLearning Transferable Visual Models From Natural Language Supervision
Radford, A., Kim, J. W., Hallacy, C., Ramesh, A., Goh, G., Agarwal, S., Sastry, G., Askell, A., Mishkin, P., Clark, J., et al. (2021) · arXiv · doi:10.48550/arxiv.2103.00020 · Cited by 15,293 · cited 2×
“, SimCLR (34) or CLIP (27)] manner also achieve high performance (Fig.”
BackgroundAdvances in Neural Information Processing Systems 25
Zhang, Y., Sutton, C. A., Storkey, A., & Zoubin Ghahramani, A. (2012) · Cited by 12,653
A training algorithm for optimal margin classifiers
Boser, B. E., Guyon, I. M., & Vapnik, V. N. (1992) · Proceedings of the fifth annual workshop on Computational learning theory · doi:10.1145/130385.130401 · Cited by 11,992 · cited 2×
“An intermediate model between prototype and exemplar learning is max-margin learning (50) (Fig.”
BackgroundA simple framework for contrastive learning of visual representations
Chen, T., Kornblith, S., Norouzi, M., & Hinton, G. (2020) · arXiv · doi:10.48550/arxiv.2002.05709 · Cited by 10,857 · cited 2×
“, SimCLR (34) or CLIP (27)] manner also achieve high performance (Fig.”
BackgroundFamily resemblances: Studies in the internal structure of categories
Rosch, E., & Mervis, C. B. (1975) · Cognitive Psychology · doi:10.1016/0010-0285(75)90024-9 · Cited by 5,933 · cited 1×
“Two such foundational theories include prototype learning, which posits that features of previously encountered examples are averaged into a set of “prototypical” features (14), and exemplar learning, which posits that the features of all previously encountered examples are simply stored in memory (8).”
BackgroundPrototypical Networks for Few-shot Learning
Snell, J., Swersky, K., & Zemel, R. S. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1703.05175 · Cited by 4,755 · cited 2×
“Drawing inspiration from previous works that have trained mappings between visual embeddings and word embeddings (33, 45) or between word embeddings in multiple languages (46), we seek to learn a simple mapping between the language and vision domains (Fig.”
BackgroundMethodHierarchical models of object recognition in cortex
Riesenhuber, M., & Poggio, T. (1999) · Nature Neuroscience · doi:10.1038/14819 · Cited by 3,309
Research works printed but not linked: 7
- S. Carey, E. Bartlett, Acquiring a single new word in Papers and reports on child language development (1978), vol. 15, pp. 17–29.
- G. L. Murphy, The Big Book of Concepts (MIT Press, Cambridge, MA, 2004).
- Aristotle, Categories (Princeton University Press, Princeton, NJ, 1984).
- 10.1037/0278-7393.14.1.54 · doi:10.1037/0278-7393.14.1.54 · Paper page
- 10.1037/0278-7393.7.4.241 · doi:10.1037/0278-7393.7.4.241 · Paper page
- 10.1037/0278-7393.24.6.1411 · doi:10.1037/0278-7393.24.6.1411 · Paper page
- 10.1037/0096-1523.21.1.128 · DOI
Cited by
Conwell, C., Prince, J. S., Kay, K. N., Alvarez, G. A., & Konkle, T. (2022) · doi:10.1101/2022.03.28.485868 · Cited by 160
“Importantly, however, we do not consider this a claim on the importance of similar model-agnostic metrics more generally: the intersection of manifold statistics and neural coding schemes is an emerging field (Cohen et al., 2020; Sorscher et al., 2022a; Yerxa et al., 2023), which we believe will be fruitful for the ne…”
BackgroundConwell, C., Prince, J. S., Kay, K. N., Alvarez, G. A., & Konkle, T. (2024) · Nature Communications · doi:10.1038/s41467-024-53147-y · Cited by 100
Goldstein, A., Grinstein-Dabush, A., Schain, M., Wang, H., Hong, Z., Aubrey, B., Nastase, S. A., Zada, Z., Ham, E., Feder, A., et al. (2024) · Nature Communications · doi:10.1038/s41467-024-46631-y · Cited by 64
Dimension of Activity in Random Neural Networks
Clark, D. G., Abbott, L. F., & Litwin-Kumar, A. (2023) · Physical Review Letters · doi:10.1103/physrevlett.131.118401 · Cited by 79
High-performing neural network models of visual cortex benefit from high latent dimensionality
Elmoznino, E., & Bonner, M. F. (2024) · PLOS Computational Biology · doi:10.1371/journal.pcbi.1011792 · Cited by 49
Metadata
- Authors
- Sorscher, B., Ganguli, S., & Sompolinsky, H.
- Affiliations
- Stanford University (US)
- Harvard University (US)
- Corresponding author
- Sompolinsky, Haim
- Venue
- Proceedings of the National Academy of Sciences
- Publisher
- National Academy of Sciences
- Published
- 2022-10-17
- Volume
- 119
- Issue
- 43
- Pages
- e2200800119-e2200800119
- ISSN
- 0027-8424 (ISSN-L)
- 1091-6490
- PMC
- PMC9618072
- OpenAlex
- W4306643150
- Cited by
- 78
- References
- 70
- Citations by year
- 2026: 12 · 2025: 31 · 2024: 20 · 2023: 13 · 2022: 2
- FWCI
- 5.43
- Type
- journal article
- Language
- en
- Open access
- hybrid
- doi.org
- Licence
- Locations
- Proceedings of the National Academy of Sciences (publishedVersion, cc-by-nc-nd)
- PubMed Central (publishedVersion, cc-by-nc-nd)
- PubMed (publishedVersion)
- Funders
- National Institute of Neurological Disorders and Stroke (U19NS104653)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Domain Adaptation and Few-Shot Learning
- Life Sciences › Neuroscience › Cognitive Neuroscience › Memory and Neural Mechanisms
- Life Sciences › Neuroscience › Cognitive Neuroscience › Visual perception and processing mechanisms
- Keywords
- few-shot learning, concept learning, neural manifolds, inferotemporal cortex, synaptic plasticity, high-dimensional manifolds
- MeSH terms
- Animals, Concept Formation, Humans, Learning, Macaca, Plastics, Primates, Visual Pathways, Neural Networks, Computer
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: Neural representational geometry underlies few-shot concept learning. https://app.cochat.ai/papers/10.1073/pnas.2200800119
- The paper
- Sorscher, B., Ganguli, S., & Sompolinsky, H. (2022). Neural representational geometry underlies few-shot concept learning. Proceedings of the National Academy of Sciences. https://doi.org/10.1073/pnas.2200800119
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.