ArticleProceedings of the National Academy of Sciences of the United States of America2022
Curriculum learning for human compositional generalization.
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 21 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
21 citing papers in PubMed, 44 citations in OpenAlex.
- Mental bootstrapping enables human-level concept learning in self-supervised deep models.Science advances · 2026Article
- Learning shapes neural geometry in the primate prefrontal cortex.Nature neuroscience · 2026Article
- Representation Transfer via Invariant Input-driven Continuous Attractors for Fast Domain Adaptation.Communications biology · 2026Article
- Infinite hidden Markov models can dissect the complexities of learning.Nature neuroscience · 2026Article
- Curriculum Learning in Humans and Neural Networks.Open mind : discoveries in cognitive science · 2026Article
- Curriculum effects in multitask learning through the lens of contextual inference.Current opinion in neurobiology · 2025Review
- The effects of task similarity during representation learning in brains and neural networks.Nature communications · 2025Article
- Factorized embedding of goal and uncertainty in the lateral prefrontal cortex guides stably flexible learning.Nature communications · 2025Article
- Article
- The dynamic interplay between in-context and in-weight learning in humans and neural networks.ArXiv · 2025Article
- Parallel trade-offs in human cognition and neural networks: The dynamic interplay between in-context and in-weight learning.Proceedings of the National Academy of Sciences of the United States of America · 2025Article
- Neural evidence that humans reuse strategies to solve new tasks.PLoS biology · 2025Article
- Neurosymbolic AI as an antithesis to scaling laws.PNAS nexus · 2025Article
- Adaptive planning depth in human problem-solving.Royal Society open science · 2025Article
- Decomposing dynamical subprocesses for compositional generalization.Proceedings of the National Academy of Sciences of the United States of America · 2024Article
- Article
- Computational role of structure in neural activity and connectivity.Trends in cognitive sciences · 2024Review
- Identifying Transfer Learning in the Reshaping of Inductive Biases.Open mind : discoveries in cognitive science · 2024Article
- Article
- 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 1 institution in 1 country.
Funding
No grant is acknowledged in the PubMed record.
Abstract
Generalization (or transfer) is the ability to repurpose knowledge in novel settings. It is often asserted that generalization is an important ingredient of human intelligence, but its extent, nature, and determinants have proved controversial. Here, we examine this ability with a paradigm that formalizes the transfer learning problem as one of recomposing existing functions to solve unseen problems. We find that people can generalize compositionally in ways that are elusive for standard neural networks and that human generalization benefits from training regimes in which items are axis aligned and temporally correlated. We describe a neural network model based around a Hebbian gating process that can capture how human generalization benefits from different training curricula. We additionally find that adult humans tend to learn composable functions asynchronously, exhibiting discontinuities in learning that resemble those seen in child development.
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.