mlsanityData to 14 Oct 2026

Synaptic metaplasticity in binarized neural networks

arXiv 2101.07592 ↗First posted 19 Jan 2021cs.NEcited by 29

Not on the map. Why?

Abstract (arXiv)

Unlike the brain, artificial neural networks, including state-of-the-art deep neural networks for computer vision, are subject to "catastrophic forgetting": they rapidly forget the previous task when trained on a new one. Neuroscience suggests that biological synapses avoid this issue through the process of synaptic consolidation and metaplasticity: the plasticity itself changes upon repeated synaptic events. In this work, we show that this concept of metaplasticity can be transferred to a particular type of deep neural networks, binarized neural networks, to reduce catastrophic forgetting.

Key facts. Cited by 29 papers in the map (data through 14 Oct 2026). First posted on arXiv 19 Jan 2021.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 1; 2022: 6; 2023: 6; 2024: 7; 2025: 5; 2026: 4.

29 papers.

Sort:

By area:

  1. 2024Continual Learning and Catastrophic Forgettingcited by 77
  2. 2022Bayesian Continual Learning via Spiking Neural Networkscited by 13
  3. 2021Deep learning via message passing algorithms based on belief propagationcited by 12
  4. 2022Statistical mechanics of continual learning: variational principle and mean-field potentialcited by 9
  5. 2023Design Principles for Lifelong Learning AI Acceleratorscited by 9
  6. 2025Bayesian continual learning and forgetting in neural networkscited by 9
  7. 2022The fine line between dead neurons and sparsity in binarized spiking neural networkscited by 8
  8. 2024Hebbian Learning based Orthogonal Projection for Continual Learning of Spiking Neural Networkscited by 8
  9. 2022Bio-Inspired, Task-Free Continual Learning through Activity Regularizationcited by 7
  10. 2023Eight challenges in developing theory of intelligencecited by 6
  11. 2022Random Quantum Neural Networks (RQNN) for Noisy Image Recognitioncited by 4
  12. 2024Theories of synaptic memory consolidation and intelligent plasticity for continual learningcited by 3
17 more
  1. 2022On-device Synaptic Memory Consolidation using Fowler-Nordheim Quantum-tunnelingcited by 1
  2. 2023Synaptic metaplasticity with multi-level memristive devicescited by 1
  3. 2024TACOS: Task Agnostic Continual Learning in Spiking Neural Networkscited by 1
  4. 2025Stochastic Engrams for Efficient Continual Learningcited by 1
  5. 2023Convergence and scaling of Boolean-weight optimization for hardware reservoirscited by 0
  6. 2023Quantized Non-Volatile Nanomagnetic Synapse based Autoencoder for Efficient Unsupervised Network Anomaly Detectioncited by 0
  7. 2023Bayesian Metaplasticity from Synaptic Uncertaintycited by 0
  8. 2024Quantified Task Misalignment to Inform PEFT: An Exploration of Domain Generalization and Catastrophic Forgetting in CLIPcited by 0
  9. 2024Neuromimetic metaplasticity for adaptive continual learningcited by 0
  10. 2024Investigating Plausibility of Biologically Inspired Bayesian Learning in ANNscited by 0
  11. 2025Towards Experience Replay for Class-Incremental Learning in Fully-Binary Networkscited by 0
  12. 2025Generative Binary Memory: Pseudo-Replay Class-Incremental Learning on Binarized Embeddingscited by 0
  13. 2025What Neuroscience Can Teach AI About Learning in Continuously Changing Environmentscited by 0
  14. 2026Active Continual Learning with Metaplastic Binary Bayesian Neural Networkscited by 0
  15. 2026NeuroGuard: Neural Gradient Update Aware of Representation Damagecited by 0
  16. 2026Metaplasticity as adaptive gradient preconditioning for incremental learningcited by 0
  17. 2026Do Artificial Neural Networks Need Dendritic Nanotubes? Two Reasons for Shrinking Importance Estimates in Continual Learningcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024Active Dendrites Enable Efficient Continual Learning in Time-To-First-Spike Neural Networks
  2. 2023A Sparse Quantized Hopfield Network for Online-Continual Memory
  3. 2023In search of dispersed memories: Generative diffusion models are associative memory networks
  4. 2024Continual Learning with Neuromorphic Computing: Foundations, Methods, and Emerging Applications
  5. 2024Neuroplastic Expansion in Deep Reinforcement Learning
  6. 2024Disentangling the Causes of Plasticity Loss in Neural Networks
  7. 2025Mitigating Catastrophic Forgetting and Mode Collapse in Text-to-Image Diffusion via Latent Replay
  8. 2026Why the Brain Consolidates: Predictive Forgetting for Optimal Generalisation