mlsanityData to 7 Oct 2026

Surrogate Gradient Learning in Spiking Neural Networks

arXiv 1901.09948 ↗First posted 28 Jan 2019cs.NE q-bio.NCcited by 604

Not on the map. Why?

Abstract (arXiv)

Spiking neural networks are nature's versatile solution to fault-tolerant and energy efficient signal processing. To translate these benefits into hardware, a growing number of neuromorphic spiking neural network processors attempt to emulate biological neural networks. These developments have created an imminent need for methods and tools to enable such systems to solve real-world signal processing problems. Like conventional neural networks, spiking neural networks can be trained on real, domain specific data. However, their training requires overcoming a number of challenges linked to their binary and dynamical nature. This article elucidates step-by-step the problems typically encountered when training spiking neural networks, and guides the reader through the key concepts of synaptic plasticity and data-driven learning in the spiking setting. To that end, it gives an overview of existing approaches and provides an introduction to surrogate gradient methods, specifically, as a particularly flexible and efficient method to overcome the aforementioned challenges.

Key facts. Cited by 604 papers in the map (data through 7 Oct 2026). First posted on arXiv 28 Jan 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 57; 2022: 62; 2023: 116; 2024: 118; 2025: 127; 2026: 124.

604 papers.

Sort:

By area:

  1. 2022Spikformer: When Spiking Neural Network Meets Transformercited by 263
  2. 2021Training Spiking Neural Networks Using Lessons From Deep Learningcited by 251
  3. 2022Temporal Efficient Training of Spiking Neural Network via Gradient Re-weightingcited by 192
  4. 2023SpikingJelly: An open-source machine learning infrastructure platform for spike-based intelligencecited by 163
  5. 2022Recurrent Vision Transformers for Object Detection with Event Camerascited by 158
  6. 2023Spike-driven Transformercited by 141
  7. 2021Accurate and efficient time-domain classification with adaptive spiking recurrent neural networkscited by 113
  8. 2021A Free Lunch From ANN: Towards Efficient, Accurate Spiking Neural Networks Calibrationcited by 111
  9. 2021Temporal-wise Attention Spiking Neural Networks for Event Streams Classificationcited by 106
  10. 2022Attention Spiking Neural Networkscited by 103
  11. 2021Self-Supervised Learning of Event-Based Optical Flow with Spiking Neural Networkscited by 99
  12. 2024Spike-driven Transformer V2: Meta Spiking Neural Network Architecture Inspiring the Design of Next-generation Neuromorphic Chipscited by 97
38 more
  1. 2022Training High-Performance Low-Latency Spiking Neural Networks by Differentiation on Spike Representationcited by 89
  2. 2023SpikeGPT: Generative Pre-trained Language Model with Spiking Neural Networkscited by 82
  3. 2022Object Detection with Spiking Neural Networks on Automotive Event Datacited by 79
  4. 2021Advancing Spiking Neural Networks towards Deep Residual Learningcited by 76
  5. 2023Deep Directly-Trained Spiking Neural Networks for Object Detectioncited by 76
  6. 2021Predictive Coding: a Theoretical and Experimental Reviewcited by 74
  7. 2021HIRE-SNN: Harnessing the Inherent Robustness of Energy-Efficient Deep Spiking Neural Networks by Training with Crafted Input Noisecited by 61
  8. 2022Event-based Video Reconstruction via Potential-assisted Spiking Neural Networkcited by 58
  9. 2024Scaling Spike-driven Transformer with Efficient Spike Firing Approximation Trainingcited by 57
  10. 2021Beyond Classification: Directly Training Spiking Neural Networks for Semantic Segmentationcited by 54
  11. 2022Neural Architecture Search for Spiking Neural Networkscited by 52
  12. 2023Speck: A Smart event-based Vision Sensor with a low latency 327K Neuron Convolutional Neuronal Network Processing Pipelinecited by 50
  13. 2022Online Training Through Time for Spiking Neural Networkscited by 48
  14. 2023Learning Delays in Spiking Neural Networks using Dilated Convolutions with Learnable Spacingscited by 48
  15. 2024QKFormer: Hierarchical Spiking Transformer using Q-K Attentioncited by 46
  16. 2021Pruning of Deep Spiking Neural Networks through Gradient Rewiringcited by 41
  17. 2021Sparse Spiking Gradient Descentcited by 41
  18. 2023Constructing Deep Spiking Neural Networks from Artificial Neural Networks with Knowledge Distillationcited by 41
  19. 2023Parallel Spiking Neurons with High Efficiency and Ability to Learn Long-term Dependenciescited by 41
  20. 2022AutoSNN: Towards Energy-Efficient Spiking Neural Networkscited by 40
  21. 2021Training Feedback Spiking Neural Networks by Implicit Differentiation on the Equilibrium Statecited by 39
  22. 2022Optimized Potential Initialization for Low-latency Spiking Neural Networkscited by 39
  23. 2023Reducing ANN-SNN Conversion Error through Residual Membrane Potentialcited by 39
  24. 2023Towards Memory- and Time-Efficient Backpropagation for Training Spiking Neural Networkscited by 37
  25. 2024OpenESS: Event-based Semantic Scene Understanding with Open Vocabulariescited by 37
  26. 2023Ternary Spike: Learning Ternary Spikes for Spiking Neural Networkscited by 36
  27. 2023Spiking PointNet: Spiking Neural Networks for Point Cloudscited by 34
  28. 2021Accurate online training of dynamical spiking neural networks through Forward Propagation Through Timecited by 33
  29. 2022TCJA-SNN: Temporal-Channel Joint Attention for Spiking Neural Networkscited by 33
  30. 2023Optical flow estimation from event-based cameras and spiking neural networkscited by 33
  31. 2021A Long Short-Term Memory for AI Applications in Spike-based Neuromorphic Hardwarecited by 32
  32. 2021Applications and Techniques for Fast Machine Learning in Sciencecited by 32
  33. 2023Direct Learning-Based Deep Spiking Neural Networks: A Reviewcited by 31
  34. 2024SpikeLM: Towards General Spike-Driven Language Modeling via Elastic Bi-Spiking Mechanismscited by 31
  35. 2023Fully neuromorphic vision and control for autonomous drone flightcited by 30
  36. 2023SpikePoint: An Efficient Point-based Spiking Neural Network for Event Cameras Action Recognitioncited by 30
  37. 2023Training an Ising Machine with Equilibrium Propagationcited by 29
  38. 2024SpikeLLM: Scaling up Spiking Neural Network to Large Language Models via Saliency-based Spikingcited by 29

50 most cited of 604 All 604 (JSON)