ArticleProceedings of the National Academy of Sciences of the United States of America2022
Neural representational geometry underlies few-shot concept learning.
Article in Proceedings of the National Academy of Sciences of the United States of America, 2022. The graph could read no effect estimate from its abstract, so it casts no vote on the map. Cited by 51 papers.
What it found
Each row is one number read from the abstract, on the scale the paper reported it, with its interval. Left of the dashed line favours the treatment, right favours the comparator. Under each row is the sentence it came from. New to these charts? A ten-minute tutorial.
The abstract states no effect estimate the extractor could read, or names no intervention and outcome on the map, so this paper lights no cell and moves no belief. It is still indexed, cited and linked below.
The trial behind it
Trials whose registry record cites this paper, or whose number appears in the abstract. A trial that started after this paper was published is citing it as background, not reporting it.
Neither the registry nor the abstract names a trial number. If this is a trial report, that itself is worth knowing.
Who cites it
51 citing papers in PubMed, 73 citations in OpenAlex.
- Review
- Article
- Initial organization and progressive expansion of the math-responsive brain network during the first school years.Proceedings of the National Academy of Sciences of the United States of America · 2026Article
- Photonic biosensors based on nanoparticle superstructures: from data analysis to artificial intelligence (AI) detection.Fundamental research · 2026Review
- Re-emergence of orientation coding in primate IT cortex and deep networks reveals functional hubs for visual processing.bioRxiv : the preprint server for biology · 2026Article
- Article
- Unraveling the geometry of visual relational reasoning.Scientific reports · 2026Article
- Hierarchical and non-hierarchical network flows generate complementary representational dynamics in human visual cortex.bioRxiv : the preprint server for biology · 2026Article
- Human brains construct individualized global rankings from identical few-shot learning input.PLoS biology · 2026Article
- Granule cells reorient cortical manifolds to separate contexts but preserve their geometry.bioRxiv : the preprint server for biology · 2026Article
- Neural population geometry and optimal coding of tasks with shared latent structure.Nature neuroscience · 2026Article
- Neural and computational mechanisms underlying one-shot perceptual learning in humans.Nature communications · 2026Article
- Leveraging insights from neuroscience to build adaptive artificial intelligence.Nature neuroscience · 2026Review
- Linguistic features of AI mis/disinformation and the detection limits of LLMs.Nature communications · 2025Article
- When predict can also explain: Few-shot prediction to select better neural latents.PLoS computational biology · 2025Article
- Revisiting the high-dimensional geometry of population responses in the visual cortex.Proceedings of the National Academy of Sciences of the United States of America · 2025Article
- Revealing emergent human-like conceptual representations from language prediction.Proceedings of the National Academy of Sciences of the United States of America · 2025Article
- From retinotopic to ordinal coding: Dissecting the cortical stages of visual word recognition.Proceedings of the National Academy of Sciences of the United States of America · 2025Article
- Variation in the geometry of concept manifolds across human visual cortex.PLoS computational biology · 2025Article
- Article
Corrections and comments
PubMed lists nothing against this paper. Absence here is not a guarantee, only a check that was made.
Authors and funding
3 authors at 2 institutions in 2 countries.
Funding
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.
Indexed as
Identifiers
What OpenQuestion holds
Registered trials
Read under generation 80e0d062 · epoch 390. Bibliography from PubMed, PubMed Central and OpenAlex; grants from NIH RePORTER; trial links from ClinicalTrials.gov; estimates, votes and beliefs from the OpenQuestion graph.