ArticleNature communications2023
Abstract representations emerge naturally in neural networks trained to perform multiple tasks.
Article in Nature communications, 2023. The graph could read no effect estimate from its abstract, so it casts no vote on the map. Cited by 46 papers, 1 of them a synthesis that pooled it.
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
46 citing papers in PubMed, 1 synthesis or guideline pooled it.
- The asymmetry of working memory training transfer: A systematic review and meta-analysis.Psychonomic bulletin & review · 2026Pooled it
- The compositionality continuum as a principle for studying the neural basis of intelligence.Nature neuroscience · 2026Review
- Article
- The representational geometry of emotional states in basolateral amygdala.Nature neuroscience · 2026Article
- Stable readout of visual representations mediates flexible generalization.Nature communications · 2026Article
- The Effect of Semantic Radical Deformation on Abstract Semantic Radical Identity Representations: A Comparative Study of L1 speakers and L2 Learners.Journal of psycholinguistic research · 2026Article
- Benchmarking criteria to determine latent linear dimensionality in neural data.Scientific reports · 2026Article
- A mathematical theory for understanding when abstract representations emerge in neural networks.ArXiv · 2026Article
- Neural geometry in the human hippocampus enables generalization across spatial position and gaze.ArXiv · 2026Article
- Article
- Neural population geometry and optimal coding of tasks with shared latent structure.Nature neuroscience · 2026Article
- Electroluminescent perovskite QD-based neural networks for energy-efficient and accelerate multitasking learning.Science advances · 2026Article
- Order parameters and phase transitions of continual learning in deep neural networks.Proceedings of the National Academy of Sciences of the United States of America · 2026Article
- Article
- Neural representations of beliefs in a multi-dimensional inference task.bioRxiv : the preprint server for biology · 2026Article
- Humans and neural networks show similar patterns of transfer and interference during continual learning.Nature human behaviour · 2026Article
- Mining the gaps: Deciphering Alzheimer's biology through AI-driven reconciliation.The journal of prevention of Alzheimer's disease · 2025Article
- DDGWizard: Integration of feature calculation resources for analysis and prediction of changes in protein thermostability upon point mutations.PLoS computational biology · 2025Article
- The effects of task similarity during representation learning in brains and neural networks.Nature communications · 2025Article
- A neural circuit framework for economic choice: from building blocks of valuation to compositionality in multitasking.bioRxiv : the preprint server for biology · 2025Article
Corrections and comments
- Commented on by
Authors and funding
2 authors.
Funding
Abstract
Humans and other animals demonstrate a remarkable ability to generalize knowledge across distinct contexts and objects during natural behavior. We posit that this ability to generalize arises from a specific representational geometry, that we call abstract and that is referred to as disentangled in machine learning. These abstract representations have been observed in recent neurophysiological studies. However, it is unknown how they emerge. Here, using feedforward neural networks, we demonstrate that the learning of multiple tasks causes abstract representations to emerge, using both supervised and reinforcement learning. We show that these abstract representations enable few-sample learning and reliable generalization on novel tasks. We conclude that abstract representations of sensory and cognitive variables may emerge from the multiple behaviors that animals exhibit in the natural world, and, as a consequence, could be pervasive in high-level brain regions. We also make several specific predictions about which variables will be represented abstractly.
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.