ArticleNature communications2020
Brain-inspired replay for continual learning with artificial neural networks.
Article in Nature communications, 2020. The graph could read no effect estimate from its abstract, so it casts no vote on the map. Cited by 62 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
62 citing papers in PubMed.
- A Brain-wide Neuronal Spiking and Behavioral Dataset for Working Memory-specific Activation and Reactivation in Mice.Neuroscience bulletin · 2026Article
- Drift-diffusion dynamics of hippocampal replay.PLoS computational biology · 2026Article
- The hippocampus as a generative model.Philosophical transactions of the Royal Society of London. Series B, Biological sciences · 2026Review
- Self-Powered Flexible Triboelectric-Gated Ion-Gel Transistor for Neuromorphic Tactile Sensing and Human Activity Recognition.Advanced materials (Deerfield Beach, Fla.) · 2026Article
- Prewired static visual receptive fields for environment-agnostic perception.Patterns (New York, N.Y.) · 2026Article
- Article
- Hybrid deep learning framework MedFusionNet assists multilabel biomedical risk stratification from imaging and tabular data.Communications medicine · 2026Article
- Review
- Review
- Hierarchical Replay of Multi-regional Sequential Spiking Associated with Working Memory.Neuroscience bulletin · 2025Article
- Sequence-to-sequence models with attention mechanistically map to the architecture of human memory search.Communications psychology · 2025Article
- Towards Predictive Communication: The Fusion of Large Language Models and Brain-Computer Interface.Sensors (Basel, Switzerland) · 2025Review
- CRoP: Context-wise Robust Static Human-Sensing Personalization.Proceedings of the ACM on interactive, mobile, wearable and ubiquitous technologies · 2025Article
- Anterograde interference in multitask perceptual learning.NPJ science of learning · 2025Article
- Exploring multi-granularity balance strategy for class incremental learning via three-way granular computing.Brain informatics · 2025Article
- Hybrid neural networks for continual learning inspired by corticohippocampal circuits.Nature communications · 2025Article
- Article
- A synapse-specific refractory period for plasticity at individual dendritic spines.Proceedings of the National Academy of Sciences of the United States of America · 2025Article
- Deep learning-enabled filter-free fluorescence microscope.Science advances · 2025Article
- Sleep microstructure organizes memory replay.Nature · 2025Article
2 more citing papers are in PubMed but not listed here.
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.
Funding
No grant is acknowledged in the PubMed record.
Abstract
Artificial neural networks suffer from catastrophic forgetting. Unlike humans, when these networks are trained on something new, they rapidly forget what was learned before. In the brain, a mechanism thought to be important for protecting memories is the reactivation of neuronal activity patterns representing those memories. In artificial neural networks, such memory replay can be implemented as 'generative replay', which can successfully - and surprisingly efficiently - prevent catastrophic forgetting on toy examples even in a class-incremental learning scenario. However, scaling up generative replay to complicated problems with many tasks or complex inputs is challenging. We propose a new, brain-inspired variant of replay in which internal or hidden representations are replayed that are generated by the network's own, context-modulated feedback connections. Our method achieves state-of-the-art performance on challenging continual learning benchmarks (e.g., class-incremental learning on CIFAR-100) without storing data, and it provides a novel model for replay in the brain.
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.