mlsanityData to 14 Oct 2026

Learning to learn online with neuromodulated synaptic plasticity in spiking neural networks

arXiv 2206.12520 ↗First posted 25 Jun 2022cs.NE cs.LGcited by 2

Not on the map. Why?

Abstract (arXiv)

We propose that in order to harness our understanding of neuroscience toward machine learning, we must first have powerful tools for training brain-like models of learning. Although substantial progress has been made toward understanding the dynamics of learning in the brain, neuroscience-derived models of learning have yet to demonstrate the same performance capabilities as methods in deep learning such as gradient descent. Inspired by the successes of machine learning using gradient descent, we demonstrate that models of neuromodulated synaptic plasticity from neuroscience can be trained in Spiking Neural Networks (SNNs) with a framework of learning to learn through gradient descent to address challenging online learning problems. This framework opens a new path toward developing neuroscience inspired online learning algorithms.

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 36 of its 98 references that are in the map. First posted on arXiv 25 Jun 2022.

Builds on

36 of 98 references.

References · 36

  1. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,897
  2. 2016Overcoming catastrophic forgetting in neural networkscited by 4,787
  3. 2018DARTS: Differentiable Architecture Searchcited by 1,798
  4. 2016Neural Architecture Search with Reinforcement Learningcited by 1,499
  5. 2018Continual Lifelong Learning with Neural Networks: A Reviewcited by 1,330
  6. 2020Meta-Learning in Neural Networks: A Surveycited by 950
  7. 2018Regularized Evolution for Image Classifier Architecture Searchcited by 909
  8. 2019Surrogate Gradient Learning in Spiking Neural Networkscited by 626
  9. 2016Learning to learn by gradient descent by gradient descentcited by 620
  10. 2018SLAYER: Spike Layer Error Reassignment in Timecited by 266
  11. 2017Building machines that adapt and compute like brainscited by 99
  12. 2018ProMP: Proximal Meta-Policy Searchcited by 91
24 more
  1. 2018Evolved Policy Gradientscited by 88
  2. 2019AI-GAs: AI-generating algorithms, an alternate paradigm for producing general artificial intelligencecited by 86
  3. 2020Learning to Continually Learncited by 84
  4. 2017Neural Optimizer Search with Reinforcement Learningcited by 82
  5. 2019Weight Agnostic Neural Networkscited by 71
  6. 2018Eligibility Traces and Plasticity on Behavioral Time Scales: Experimental Support of neoHebbian Three-Factor Learning Rulescited by 67
  7. 2019Meta-Q-Learningcited by 62
  8. 2021Evolving Reinforcement Learning Algorithmscited by 49
  9. 2022The BrainScaleS-2 accelerated neuromorphic system with hybrid plasticitycited by 42
  10. 2020Backpropamine: training self-modifying neural networks with differentiable neuromodulated plasticitycited by 41
  11. 2022A Modern Self-Referential Weight Matrix That Learns to Modify Itselfcited by 41
  12. 2018Meta-Learning Update Rules for Unsupervised Representation Learningcited by 37
  13. 2019Low-Power Neuromorphic Hardware for Signal Processing Applicationscited by 21
  14. 2019Biologically inspired alternatives to backpropagation through time for learning in recurrent neural netscited by 20
  15. 2020Online Few-shot Gesture Learning on a Neuromorphic Processorcited by 18
  16. 2021Increasing Liquid State Machine Performance with Edge-of-Chaos Dynamics Organized by Astrocyte-modulated Plasticitycited by 12
  17. 2017Diffusion-based neuromodulation can eliminate catastrophic forgetting in simple neural networkscited by 10
  18. 2019Neuromorphic Hardware learns to learncited by 8
  19. 2020Formation of working memory in a spiking neuron network accompanied by astrocytescited by 5
  20. 2020Adaptive Reinforcement Learning through Evolving Self-Modifying Neural Networkscited by 4
  21. 2021SpikePropamine: Differentiable Plasticity in Spiking Neural Networkscited by 4
  22. 2017Acetylcholine-modulated plasticity in reward-driven navigation: a computational studycited by 3
  23. 2020Embodied Synaptic Plasticity with Online Reinforcement learningcited by 3
  24. 2021Stable Lifelong Learning: Spiking neurons as a solution to instability in plastic neural networkscited by 2

Built on by

Cited by year

Citing papers per year: 2022: 1; 2023: 1.

2 papers.

  1. 2023Synaptic motor adaptation: A three-factor learning rule for adaptive robotic control in spiking neural networkscited by 3
  2. 2022Biological connectomes as a representation for the architecture of artificial neural networkscited by 2