mlsanityData to 7 Oct 2026

Fast On-Device Adaptation for Spiking Neural Networks via Online-Within-Online Meta-Learning

arXiv 2103.03901 ↗First posted 21 Feb 2021cs.NE cs.LG eess.SPcited by 6

Not on the map. Why?

Abstract (arXiv)

Spiking Neural Networks (SNNs) have recently gained popularity as machine learning models for on-device edge intelligence for applications such as mobile healthcare management and natural language processing due to their low power profile. In such highly personalized use cases, it is important for the model to be able to adapt to the unique features of an individual with only a minimal amount of training data. Meta-learning has been proposed as a way to train models that are geared towards quick adaptation to new tasks. The few existing meta-learning solutions for SNNs operate offline and require some form of backpropagation that is incompatible with the current neuromorphic edge-devices. In this paper, we propose an online-within-online meta-learning rule for SNNs termed OWOML-SNN, that enables lifelong learning on a stream of tasks, and relies on local, backprop-free, nested updates.

Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Builds on 22 of its 38 references that are in the map. First posted on arXiv 21 Feb 2021.

Builds on

22 of 38 references.

References · 22

  1. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,861
  2. 2016Matching Networks for One Shot Learningcited by 2,246
  3. 2018On First-Order Meta-Learning Algorithmscited by 1,003
  4. 2020Personalized Federated Learning: A Meta-Learning Approachcited by 309
  5. 2019Improving Federated Learning Personalization via Model Agnostic Meta Learningcited by 264
  6. 2018Meta-Learning: A Surveycited by 254
  7. 2018Long short-term memory and learning-to-learn in networks of spiking neuronscited by 179
  8. 2020Survey of Personalization Techniques for Federated Learningcited by 144
  9. 2020Predictive Coding Approximates Backprop along Arbitrary Computation Graphscited by 89
  10. 2018Differentiable plasticity: training plastic neural networks with backpropagationcited by 83
  11. 2017Meta-Learning by Adjusting Priors Based on Extended PAC-Bayes Theorycited by 76
  12. 2020Meta-Learning through Hebbian Plasticity in Random Networkscited by 47
10 more
  1. 2018Meta-Learning Update Rules for Unsupervised Representation Learningcited by 37
  2. 2020Information-Theoretic Generalization Bounds for Meta-Learning and Applicationscited by 32
  3. 2019An Introduction to Probabilistic Spiking Neural Networks: Probabilistic Models, Learning Rules, and Applicationscited by 25
  4. 2018Deep Meta-Learning: Learning to Learn in the Concept Spacecited by 22
  5. 2020Online Few-shot Gesture Learning on a Neuromorphic Processorcited by 18
  6. 2019Federated Neuromorphic Learning of Spiking Neural Networks for Low-Power Edge Intelligencecited by 16
  7. 2019Neuromorphic Hardware learns to learncited by 8
  8. 2019On-chip Few-shot Learning with Surrogate Gradient Descent on a Neuromorphic Processorcited by 8
  9. 2020VOWEL: A Local Online Learning Rule for Recurrent Networks of Probabilistic Spiking Winner-Take-All Circuitscited by 7
  10. 2019Supervised Learning in Spiking Neural Networks with Phase-Change Memory Synapsescited by 2

Built on by

Cited by year

Citing papers per year: 2021: 2; 2022: 1; 2023: 0; 2024: 2; 2025: 1.

6 papers.

  1. 2021Edge-Cloud Polarization and Collaboration: A Comprehensive Survey for AIcited by 38
  2. 2024Training Machine Learning models at the Edge: A Surveycited by 11
  3. 2022Meta-learning Spiking Neural Networks with Surrogate Gradient Descentcited by 9
  4. 2021Spiking Generative Adversarial Networks With a Neural Network Discriminator: Local Training, Bayesian Models, and Continual Meta-Learningcited by 8
  5. 2024Emulating Brain-like Rapid Learning in Neuromorphic Edge Computingcited by 0
  6. 2025Self-cross Feature based Spiking Neural Networks for Efficient Few-shot Learningcited by 0