ArticleNature communications2021
Synaptic metaplasticity in binarized neural networks.
Article in Nature communications, 2021. The graph could read no effect estimate from its abstract, so it casts no vote on the map. Cited by 17 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
17 citing papers in PubMed.
- Wafer-scale SOT-MRAM for analog crossbar array applications.Science advances · 2026Article
- In Situ Quantization with Memory-Transistor Transfer Unit Based on Electrochemical Random-Access Memory for Edge Applications.Advanced science (Weinheim, Baden-Wurttemberg, Germany) · 2026Article
- Bayesian continual learning and forgetting in neural networks.Nature communications · 2025Article
- Anterograde interference in multitask perceptual learning.NPJ science of learning · 2025Article
- Electrochemical ohmic memristors for continual learning.Nature communications · 2025Article
- Hybrid neural networks for continual learning inspired by corticohippocampal circuits.Nature communications · 2025Article
- A ferroelectric-memristor memory for both training and inference.Nature electronics · 2025Article
- Probabilistic metaplasticity for continual learning with memristors in spiking networks.Scientific reports · 2024Article
- Neuromorphic neuromodulation: Towards the next generation of closed-loop neurostimulation.PNAS nexus · 2024Review
- Eight challenges in developing theory of intelligence.Frontiers in computational neuroscience · 2024Article
- Bio-inspired, task-free continual learning through activity regularization.Biological cybernetics · 2023Article
- Distinctive properties of biological neural networks and recent advances in bottom-up approaches toward a better biologically plausible neural network.Frontiers in computational neuroscience · 2023Review
- Metaplastic and energy-efficient biocompatible graphene artificial synaptic transistors for enhanced accuracy neuromorphic computing.Nature communications · 2022Article
- Palimpsest memories stored in memristive synapses.Science advances · 2022Article
- On-device synaptic memory consolidation using Fowler-Nordheim quantum-tunneling.Frontiers in neuroscience · 2022Article
- Bayesian continual learningFrontiers in computational neuroscience · 2022Article
- Synaptic metaplasticity in binarized neural networks.Nature communications · 2021Article
Corrections and comments
PubMed lists nothing against this paper. Absence here is not a guarantee, only a check that was made.
Authors and funding
4 authors.
Funding
No grant is acknowledged in the PubMed record.
Abstract
While deep neural networks have surpassed human performance in multiple situations, they are prone to catastrophic forgetting: upon training a new task, they rapidly forget previously learned ones. Neuroscience studies, based on idealized tasks, suggest that in the brain, synapses overcome this issue by adjusting their plasticity depending on their past history. However, such "metaplastic" behaviors do not transfer directly to mitigate catastrophic forgetting in deep neural networks. In this work, we interpret the hidden weights used by binarized neural networks, a low-precision version of deep neural networks, as metaplastic variables, and modify their training technique to alleviate forgetting. Building on this idea, we propose and demonstrate experimentally, in situations of multitask and stream learning, a training technique that reduces catastrophic forgetting without needing previously presented data, nor formal boundaries between datasets and with performance approaching more mainstream techniques with task boundaries. We support our approach with a theoretical analysis on a tractable task. This work bridges computational neuroscience and deep learning, and presents significant assets for future embedded and neuromorphic systems, especially when using novel nanodevices featuring physics analogous to metaplasticity.
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.