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
Human-level concept learning through probabilistic program induction
Lake, B. M., Salakhutdinov, R., & Tenenbaum, J. B. (2015) · Science · doi:10.1126/science.aab3050 · Cited by 2,817
Smith, E. E., & Medin, D. L. (1981) · Harvard University Press eBooks · doi:10.4159/harvard.9780674866270 · Cited by 2,606
Performance-optimized hierarchical models predict neural responses in higher visual cortex
Yamins, D. L. K., Hong, H., Cadieu, C. F., Solomon, E. A., Seibert, D., & DiCarlo, J. J. (2014) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.1403112111 · Cited by 1,924 · cited 3×
“Previous approaches based on behavioral performance (19, 31, 64–66); neuron (54) or circuit (57) matching; linear regression between representations (28); or representational similarity analysis (30) reveal a reasonable match between the two.”
BackgroundMethodContext-dependent computation by recurrent dynamics in prefrontal cortex
Mante, V., Sussillo, D., Shenoy, K. V., & Newsome, W. T. (2013) · Nature · doi:10.1038/nature12742 · Cited by 1,847 · cited 1×
“Computational neuroscience has recently developed increasingly complex high-dimensional machine-learning-derived models of many brain regions, including the retina (54–57); V1, V4, and IT (28, 58); motor cortex (59); prefrontal cortex (60); and entorhinal cortex (61, 62).”
BackgroundHow to grow a mind: Statistics, structure, and abstraction
Tenenbaum, J. B., Kemp, C., Griffiths, T. L., & Goodman, N. D. (2011) · Science · doi:10.1126/science.1192788 · Cited by 1,815 · cited 2×
“Deviations from these predictions may suggest that humans leverage more sophisticated higher-order processing to learn new concepts, which may incorporate human biases and priors on object-like concepts (51).”
BackgroundHow does the brain solve visual object recognition?
DiCarlo, J. J., Zoccolan, D., & Rust, N. C. (2012) · Neuron · doi:10.1016/j.neuron.2012.01.010 · Cited by 1,790 · cited 1×
“Indeed, in the case of vision, decades of research have revealed a series of representations of visual stimuli in neural population responses along the ventral visual pathway, including V1, V2, and V4, culminating in a rich object representation in the inferotemporal (IT) cortex (20–22), allowing a putative downstream…”
BackgroundUsing goal-driven deep learning models to understand sensory cortex
Yamins, D. L. K., & DiCarlo, J. J. (2016) · Nature Neuroscience · doi:10.1038/nn.4244 · Cited by 1,621 · cited 1×
“Computational neuroscience has recently developed increasingly complex high-dimensional machine-learning-derived models of many brain regions, including the retina (54–57); V1, V4, and IT (28, 58); motor cortex (59); prefrontal cortex (60); and entorhinal cortex (61, 62).”
BackgroundMental imagery in associative learning and memory.
Paivio, A. (1969) · Psychological Review · doi:10.1037/h0027272 · Cited by 1,358 · cited 1×
“Broadly, our results add plausibility to the tenets of dual-coding theory in human cognition (53).”
ResultLogothetis, N. K., & Sheinberg, D. L. (1996) · Annual Review of Neuroscience · doi:10.1146/annurev.ne.19.030196.003045 · Cited by 1,351
Matching Categorical Object Representations in Inferior Temporal Cortex of Man and Monkey
Kriegeskorte, N., Mur, M., Ruff, D. A., Kiani, R., Bodurka, J., Esteky, H., Tanaka, K., & Bandettini, P. A. (2008) · Neuron · doi:10.1016/j.neuron.2008.10.043 · Cited by 1,344 · cited 2×
“Previous approaches based on behavioral performance (19, 31, 64–66); neuron (54) or circuit (57) matching; linear regression between representations (28); or representational similarity analysis (30) reveal a reasonable match between the two.”
MethodPattern recognition and categorization
Reed, S. K. (1972) · Cognitive Psychology · doi:10.1016/0010-0285(72)90014-x · Cited by 997 · cited 1×
“Our theory reveals that exemplar learning is superior to prototype learning given many examples of low-dimensional concepts, consistent with past laboratory experiments (15, 47, 48, 67), but is inferior to prototype learning given only a few examples of highdimensional concepts, like those in DNNs and in primate IT (F…”
ResultZero-Shot Learning Through Cross-Modal Transfer
Socher, R., Ganjoo, M., Sridhar, H., Bastani, O., Manning, C. D., & Ng, A. Y. (2013) · arXiv · doi:10.48550/arxiv.1301.3666 · Cited by 997 · cited 1×
“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.”
MethodRethinking Few-Shot Image Classification: A Good Embedding is All You Need?
Tian, Y., Wang, Y., Krishnan, D., Tenenbaum, J. B., & Isola, P. (2020) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-58568-6_16 · Cited by 952
An elementary proof of a theorem of Johnson and Lindenstrauss
Dasgupta, S., & Gupta, A. (2003) · Random Structures & Algorithms · doi:10.1002/rsa.10073 · Cited by 932
Proceedings of the 39th Annual Conference of the Cognitive Science Society
Motamedi, Y., Schouwstra, M., Culbertson, J., Smith, K., & Kirby, S. (2017) · Cited by 870
Object name Learning Provides On-the-Job Training for Attention
Smith, L. B., Jones, S. S., Landau, B., Gershkoff-Stowe, L., & Samuelson, L. (2002) · Psychological Science · doi:10.1111/1467-9280.00403 · Cited by 632
A neural network that finds a naturalistic solution for the production of muscle activity
Sussillo, D., Churchland, M. M., Kaufman, M. T., & Shenoy, K. V. (2015) · Nature Neuroscience · doi:10.1038/nn.4042 · Cited by 598 · cited 1×
“Computational neuroscience has recently developed increasingly complex high-dimensional machine-learning-derived models of many brain regions, including the retina (54–57); V1, V4, and IT (28, 58); motor cortex (59); prefrontal cortex (60); and entorhinal cortex (61, 62).”
BackgroundHigh-dimensional geometry of population responses in visual cortex
Stringer, C., Pachitariu, M., Steinmetz, N., Carandini, M., & Harris, K. D. (2019) · Nature · doi:10.1038/s41586-019-1346-5 · Cited by 594 · cited 1×
“Previous works have shown that low-dimensional manifolds have desirable properties for object recognition, allowing a greater number of familiar object to be perfectly classified (36, 37) and conferring robustness (38).”
BackgroundSimilarity, frequency, and category representations.
Nosofsky, R. M. (1988) · Journal of Experimental Psychology: Learning, Memory, and Cognition · doi:10.1037//0278-7393.14.1.54 · Cited by 552 · cited 2×
“Our theory reveals that exemplar learning is superior to prototype learning given many examples of low-dimensional concepts, consistent with past laboratory experiments (15, 47, 48, 67), but is inferior to prototype learning given only a few examples of highdimensional concepts, like those in DNNs and in primate IT (F…”
BackgroundResultA Baseline for Few-Shot Image ClassificationPreprint
Dhillon, G. S., Chaudhari, P., Ravichandran, A., & Soatto, S. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1909.02729 · Cited by 549
Quinn, P. C., Eimas, P. D., & Rosenkrantz, S. L. (1993) · Perception · doi:10.1068/p220463 · Cited by 509
Prototypes in the mist: The early epochs of category learning.
Smith, J. D., & Minda, J. P. (1998) · Journal of Experimental Psychology Learning Memory and Cognition · doi:10.1037//0278-7393.24.6.1411 · Cited by 484
Brain-Score: Which Artificial Neural Network for Object Recognition is most Brain-Like?
Schrimpf, M., Kubilius, J., Hong, H., Majaj, N. J., Rajalingham, R., Issa, E. B., Kar, K., Bashivan, P., Prescott-Roy, J., Geiger, F., et al. (2018) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/407007 · Cited by 458 · cited 4×
“In particular, while manifold dimensionality in DNNs undergoes a massive expansion in the early to intermediate layers, reaching its maximum in the layer most predictive of V4 (32), dimensionality in the visual hierarchy reaches its minimum in V4 (Fig.”
BackgroundMethodInfluentialA map of object space in primate inferotemporal cortex
Bao, P., She, L., McGill, M., & Tsao, D. Y. (2020) · Nature · doi:10.1038/s41586-020-2350-5 · Cited by 392
Rajalingham, R., Issa, E. B., Bashivan, P., Kar, K., Schmidt, K., & DiCarlo, J. J. (2018) · The Journal of Neuroscience · doi:10.1523/jneurosci.0388-18.2018 · Cited by 358 · cited 1×
“We test our theory using neurophysiological recordings in macaques, as well as representations extracted from DNN models of the primate visual hierarchy, which have been shown to predict neural population responses in V1, V4, and IT (28, 29), the similarity structure of object representations in IT (30), and human per…”
MethodA theory of multineuronal dimensionality, dynamics and measurement
Gao, P., Trautmann, E., Yu, B., Santhanam, G., Ryu, S., Shenoy, K., & Ganguli, S. (2017) · doi:10.1101/214262 · Cited by 332 · cited 2×
“Although we do not restrict the maximal number of available axes, which could be as large as the dimensionality of the ambient space, N, the number of directions along which there is significant variation is quantified by an effective dimensionality D = ( ∑N i=1 R 2 i ) (2)/ ∑N i=1 R 4 i , called the participation rat…”
BackgroundSelf-citationHebart, M. N., Zheng, C. Y., Pereira, F., & Baker, C. I. (2020) · Nature Human Behaviour · doi:10.1038/s41562-020-00951-3 · Cited by 297
Basic-level and superordinate-like categorical representations in early infancy
Behl-Chadha, G. (1996) · Cognition · doi:10.1016/0010-0277(96)00706-8 · Cited by 266
Ganguli, S., & Sompolinsky, H. (2012) · Annual Review of Neuroscience · doi:10.1146/annurev-neuro-062111-150410 · Cited by 256
Self-citationAccurate Estimation of Neural Population Dynamics without Spike Sorting
Trautmann, E. M., Stavisky, S. D., Lahiri, S., Ames, K. C., Kaufman, M. T., O’Shea, D. J., Vyas, S., Sun, X., Ryu, S. I., Ganguli, S., et al. (2019) · Neuron · doi:10.1016/j.neuron.2019.05.003 · Cited by 255
Self-citationDiscrimination Training Alters Object Representations in Human Extrastriate Cortex
Op de Beeck, H. P., Baker, C. I., DiCarlo, J. J., & Kanwisher, N. G. (2006) · The Journal of Neuroscience · doi:10.1523/jneurosci.2481-06.2006 · Cited by 250
Experience-Dependent Sharpening of Visual Shape Selectivity in Inferior Temporal Cortex
Freedman, D. J. (2005) · Cerebral Cortex · doi:10.1093/cercor/bhj100 · Cited by 217
Experience-Dependent Plasticity in Adult Visual Cortex
Karmarkar, U. R., & Dan, Y. (2006) · Neuron · doi:10.1016/j.neuron.2006.11.001 · Cited by 209
Majaj, N. J., Hong, H., Solomon, E. A., & DiCarlo, J. J. (2015) · The Journal of Neuroscience · doi:10.1523/jneurosci.5181-14.2015 · Cited by 204 · cited 6×
“We next turn to the primate visual hierarchy and investigate the geometry of concept manifolds obtained via recordings of macaque V4 and IT in response to 64 synthetic visual concepts, designed to mimic naturalistic stimuli (24).”
BackgroundMethodResultInfluentialSeparability and geometry of object manifolds in deep neural networks
Cohen, U., Chung, S., Lee, D. D., & Sompolinsky, H. (2020) · Nature Communications · doi:10.1038/s41467-020-14578-5 · Cited by 188 · cited 3×
“Previous works have shown that low-dimensional manifolds have desirable properties for object recognition, allowing a greater number of familiar object to be perfectly classified (36, 37) and conferring robustness (38).”
BackgroundMethodSelf-citationStrategies and classification learning.
Medin, D. L., & Smith, E. E. (1981) · Journal of Experimental Psychology: Human Learning & Memory · doi:10.1037//0278-7393.7.4.241 · Cited by 183 · cited 1×
“In laboratory experiments, these features are either constructed by hand by generating synthetic stimuli that vary along a predefined set of latent features (15, 16) or are indirectly inferred from human similarity judgements (17–19).”
BackgroundA unified theory for the computational and mechanistic origins of grid cells
Sorscher, B., Mel, G. C., Ocko, S. A., Giocomo, L. M., & Ganguli, S. (2022) · Neuron · doi:10.1016/j.neuron.2022.10.003 · Cited by 179
Self-citationInvestigations of exemplar and decision bound models in large, ill-defined category structures.
McKinley, S. C., & Nosofsky, R. M. (1995) · Journal of Experimental Psychology Human Perception & Performance · doi:10.1037//0096-1523.21.1.128 · Cited by 172
Intrinsic dimension of data representations in deep neural networks
Ansuini, A., Laio, A., Macke, J. H., & Zoccolan, D. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1905.12784 · Cited by 145 · cited 1×
“Nonmonotonicity of dimension has also been observed by using capacity-related measures of dimension (36) and nonlinear measure of intrinsic dimensionality (39, 40).”
MethodDeep Learning Models of the Retinal Response to Natural Scenes
McIntosh, L., Maheswaranathan, N., Nayebi, A., Ganguli, S., & Baccus, S. A. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1702.01825 · Cited by 139
Self-citationThe neural architecture of language: Integrative modeling converges on predictive processing
(2020) · doi:10.1101/2020.06.26.174482 · Cited by 129
Classification and Geometry of General Perceptual Manifolds
Chung, S., Lee, D. D., & Sompolinsky, H. (2018) · Physical Review X · doi:10.1103/physrevx.8.031003 · Cited by 128 · cited 2×
“Previous works have shown that low-dimensional manifolds have desirable properties for object recognition, allowing a greater number of familiar object to be perfectly classified (36, 37) and conferring robustness (38).”
BackgroundSelf-citationA neural network trained for prediction mimics diverse features of biological neurons and perception
Lotter, W., Kreiman, G., & Cox, D. (2020) · Nature Machine Intelligence · doi:10.1038/s42256-020-0170-9 · Cited by 128 · cited 1×
“We test our theory using neurophysiological recordings in macaques, as well as representations extracted from DNN models of the primate visual hierarchy, which have been shown to predict neural population responses in V1, V4, and IT (28, 29), the similarity structure of object representations in IT (30), and human per…”
MethodSimulating a Primary Visual Cortex at the Front of CNNs Improves Robustness to Image Perturbations
Dapello, J., Marques, T., Schrimpf, M., Geiger, F., Cox, D. D., & DiCarlo, J. J. (2020) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2020.06.16.154542 · Cited by 117 · cited 1×
“(70) To compare with trained DNNs, we pass the same set of stimuli into each DNN and obtain a NDNN × P response matrix XDNN, as described in Section N.”
MethodBongard-LOGO: A New Benchmark for Human-Level Concept Learning and ReasoningPreprint
Nie, W., Yu, Z., Mao, L., Patel, A., Zhu, Y., & Anandkumar, A. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2010.00763 · Cited by 110
Dimensionality compression and expansion in Deep Neural NetworksPreprint
Recanatesi, S., Farrell, M., Advani, M. S., Moore, T., Lajoie, G., & Shea-Brown, E. T. (2019) · arXiv.org · doi:10.48550/arxiv.1906.00443 · Cited by 86 · cited 1×
“Nonmonotonicity of dimension has also been observed by using capacity-related measures of dimension (36) and nonlinear measure of intrinsic dimensionality (39, 40).”
MethodLindsey, J., Ocko, S. A., Ganguli, S., & Deny, S. (2019) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/511535 · Cited by 77
Self-citationPalmeri, T. J., & Nosofsky, R. M. (2001) · The Quarterly Journal of Experimental Psychology Section A · doi:10.1080/02724980042000084 · Cited by 74
Bongard-HOI: Benchmarking Few-Shot Visual Reasoning for Human-Object Interactions
Jiang, H., Ma, X., Nie, W., Yu, Z., Zhu, Y., & Anandkumar, A. (2022) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52688.2022.01847 · Cited by 71
Capturing human categorization of natural images by combining deep networks and cognitive models
Battleday, R. M., Peterson, J. C., & Griffiths, T. L. (2020) · Nature Communications · doi:10.1038/s41467-020-18946-z · Cited by 62 · cited 1×
“These predictions are consistent with a recent demonstration that a prototype-based rule can match the performance of an exemplar model on categorization of familiar high-dimensional stimuli (66).”
ResultDeep neural networks predict category typicality ratings for images
Lake, B. M., Zaremba, W., Fergus, R., & Gureckis, T. M. (2015) · Cited by 59
Sanders, C. A., & Nosofsky, R. M. (2020) · Computational Brain & Behavior · doi:10.1007/s42113-020-00073-z · Cited by 59
The emergence of multiple retinal cell types through efficient coding of natural moviesPreprint
Ocko, S. A., Lindsey, J. W., Ganguli, S., & Deny, S. (2018) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/458737 · Cited by 55
Self-citationA unified theory for the origin of grid cells through the lens of pattern formation
Sorscher, B., Mel, G. C., Ganguli, S., & Ocko, S. A. (2019) · neural information processing systems · Cited by 47
Self-citationFrom deep learning to mechanistic understanding in neuroscience: the structure of retinal prediction
Tanaka, H., Nayebi, A., Maheswaranathan, N., McIntosh, L., Baccus, S. A., & Ganguli, S. (2019) · PubMed · doi:10.48550/arxiv.1912.06207 · Cited by 41 · cited 1×
“Previous approaches based on behavioral performance (19, 31, 64–66); neuron (54) or circuit (57) matching; linear regression between representations (28); or representational similarity analysis (30) reveal a reasonable match between the two.”
Self-citationUniversality and individuality in neural dynamics across large populations of recurrent networks
Maheswaranathan, N., Williams, A. H., Golub, M. D., Ganguli, S., & Sussillo, D. (2019) · PubMed · doi:10.48550/arxiv.1907.08549 · Cited by 36 · cited 1×
“Such increased model complexity raises foundational questions about the appropriate comparisons between brains and machine-based models (63).”
BackgroundSelf-citationA unified theory for the computational and mechanistic origins of grid cellsPreprint
Sorscher, B., Mel, G. C., Ocko, S. A., et al. (2020) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2020.12.29.424583 · Cited by 28 · cited 1×
“Computational neuroscience has recently developed increasingly complex high-dimensional machine-learning-derived models of many brain regions, including the retina (54–57); V1, V4, and IT (28, 58); motor cortex (59); prefrontal cortex (60); and entorhinal cortex (61, 62).”
BackgroundSelf-citationEnd-to-end Deep Prototype and Exemplar Models for Predicting Human BehaviorPreprint
Singh, P., Peterson, J. C., Battleday, R. M., & Griffiths, T. L. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2007.08723 · Cited by 27
Emerging Cross-lingual Structure in Pretrained Language ModelsPreprint
Wu, S., Conneau, A., Li, H., Zettlemoyer, L., & Stoyanov, V. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1911.01464 · Cited by 21 · cited 1×
“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.”
MethodSanders, C. A., & Nosofsky, R. M. (2018) · eScholarship (California Digital Library) · Cited by 18
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
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.