mlsanityData to 7 Oct 2026

Direct Learning-Based Deep Spiking Neural Networks: A Review

arXiv 2305.19725 ↗First posted 31 May 2023cs.CVcited by 31

Not on the map. Why?

Abstract (arXiv)

The spiking neural network (SNN), as a promising brain-inspired computational model with binary spike information transmission mechanism, rich spatially-temporal dynamics, and event-driven characteristics, has received extensive attention. However, its intricately discontinuous spike mechanism brings difficulty to the optimization of the deep SNN. Since the surrogate gradient method can greatly mitigate the optimization difficulty and shows great potential in directly training deep SNNs, a variety of direct learning-based deep SNN works have been proposed and achieved satisfying progress in recent years. In this paper, we present a comprehensive survey of these direct learning-based deep SNN works, mainly categorized into accuracy improvement methods, efficiency improvement methods, and temporal dynamics utilization methods. In addition, we also divide these categorizations into finer granularities further to better organize and introduce them. Finally, the challenges and trends that may be faced in future research are prospected.

Key facts. Cited by 31 papers in the map (data through 7 Oct 2026). Builds on 75 of its 125 references that are in the map. First posted on arXiv 31 May 2023.

Builds on

75 of 125 references.

References · 75

  1. 2019Surrogate Gradient Learning in Spiking Neural Networkscited by 604
  2. 2017Spatio-Temporal Backpropagation for Training High-performance Spiking Neural Networkscited by 399
  3. 2020Incorporating Learnable Membrane Time Constant to Enhance Learning of Spiking Neural Networkscited by 340
  4. 2021Deep Residual Learning in Spiking Neural Networkscited by 326
  5. 2020Going Deeper With Directly-Trained Larger Spiking Neural Networkscited by 268
  6. 2022Spikformer: When Spiking Neural Network Meets Transformercited by 263
  7. 2018Deep Learning in Spiking Neural Networkscited by 258
  8. 2018Direct Training for Spiking Neural Networks: Faster, Larger, Bettercited by 222
  9. 2022Temporal Efficient Training of Spiking Neural Network via Gradient Re-weightingcited by 192
  10. 2018Long short-term memory and learning-to-learn in networks of spiking neuronscited by 179
  11. 2017SuperSpike: Supervised learning in multi-layer spiking neural networkscited by 178
  12. 2019Spiking-YOLO: Spiking Neural Network for Energy-Efficient Object Detectioncited by 174
38 more
  1. 2023Optimal ANN-SNN Conversion for High-accuracy and Ultra-low-latency Spiking Neural Networkscited by 116
  2. 2021Accurate and efficient time-domain classification with adaptive spiking recurrent neural networkscited by 113
  3. 2021A Free Lunch From ANN: Towards Efficient, Accurate Spiking Neural Networks Calibrationcited by 111
  4. 2021Temporal-wise Attention Spiking Neural Networks for Event Streams Classificationcited by 106
  5. 2021Self-Supervised Learning of Event-Based Optical Flow with Spiking Neural Networkscited by 99
  6. 2020Temporal Spike Sequence Learning via Backpropagation for Deep Spiking Neural Networkscited by 98
  7. 2022Training High-Performance Low-Latency Spiking Neural Networks by Differentiation on Spike Representationcited by 89
  8. 2022Object Detection with Spiking Neural Networks on Automotive Event Datacited by 79
  9. 2020Revisiting Batch Normalization for Training Low-latency Deep Spiking Neural Networks from Scratchcited by 76
  10. 2020DIET-SNN: Direct Input Encoding With Leakage and Threshold Optimization in Deep Spiking Neural Networkscited by 70
  11. 2022GLIF: A Unified Gated Leaky Integrate-and-Fire Neuron for Spiking Neural Networkscited by 63
  12. 2022Event-based Video Reconstruction via Potential-assisted Spiking Neural Networkcited by 58
  13. 2022Neural Architecture Search for Spiking Neural Networkscited by 52
  14. 2020Progressive Tandem Learning for Pattern Recognition with Deep Spiking Neural Networkscited by 46
  15. 2019Temporal-Coded Deep Spiking Neural Network with Easy Training and Robust Performancecited by 45
  16. 2020Effective and Efficient Computation with Multiple-timescale Spiking Recurrent Neural Networkscited by 43
  17. 2021Pruning of Deep Spiking Neural Networks through Gradient Rewiringcited by 41
  18. 2023Constructing Deep Spiking Neural Networks from Artificial Neural Networks with Knowledge Distillationcited by 41
  19. 2022AutoSNN: Towards Energy-Efficient Spiking Neural Networkscited by 40
  20. 2022Optimized Potential Initialization for Low-latency Spiking Neural Networkscited by 39
  21. 2018A Biologically Plausible Supervised Learning Method for Spiking Neural Networks Using the Symmetric STDP Rulecited by 36
  22. 2023Joint A-SNN: Joint Training of Artificial and Spiking Neural Networks via Self-Distillation and Weight Factorizationcited by 34
  23. 2022TCJA-SNN: Temporal-Channel Joint Attention for Spiking Neural Networkscited by 33
  24. 2022Efficient and Accurate Conversion of Spiking Neural Network with Burst Spikescited by 30
  25. 2021SpikeMS: Deep Spiking Neural Network for Motion Segmentationcited by 29
  26. 2019Deep Spiking Neural Networks for Large Vocabulary Automatic Speech Recognitioncited by 27
  27. 2021A Spiking Neural Network for Image Segmentationcited by 27
  28. 2021Spiking Neural Networks with Improved Inherent Recurrence Dynamics for Sequential Learningcited by 27
  29. 2022Exploring Lottery Ticket Hypothesis in Spiking Neural Networkscited by 25
  30. 2020Distilling Spikes: Knowledge Distillation in Spiking Neural Networkscited by 24
  31. 2022HALSIE: Hybrid Approach to Learning Segmentation by Simultaneously Exploiting Image and Event Modalitiescited by 24
  32. 2022Training Spiking Neural Networks with Local Tandem Learningcited by 22
  33. 2022Real Spike: Learning Real-valued Spikes for Spiking Neural Networkscited by 22
  34. 2021StereoSpike: Depth Learning with a Spiking Neural Networkcited by 21
  35. 2022Multi-Level Firing with Spiking DS-ResNet: Enabling Better and Deeper Directly-Trained Spiking Neural Networkscited by 21
  36. 2022STSC-SNN: Spatio-Temporal Synaptic Connection with Temporal Convolution and Attention for Spiking Neural Networkscited by 20
  37. 2020Low-activity supervised convolutional spiking neural networks applied to speech commands recognitioncited by 19
  38. 2022Adaptive-SpikeNet: Event-based Optical Flow Estimation using Spiking Neural Networks with Learnable Neuronal Dynamicscited by 19

50 most cited of 75 All 75 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 6; 2024: 11; 2025: 10; 2026: 4.

31 papers.

Sort:

  1. 2023Membrane Potential Batch Normalization for Spiking Neural Networkscited by 35
  2. 2023Spiking PointNet: Spiking Neural Networks for Point Cloudscited by 34
  3. 2024SpikeLM: Towards General Spike-Driven Language Modeling via Elastic Bi-Spiking Mechanismscited by 31
  4. 2023RMP-Loss: Regularizing Membrane Potential Distribution for Spiking Neural Networkscited by 27
  5. 2024Take A Shortcut Back: Mitigating the Gradient Vanishing for Training Spiking Neural Networkscited by 14
  6. 2024Q-SNNs: Quantized Spiking Neural Networkscited by 10
  7. 2024Towards Efficient Deep Spiking Neural Networks Construction with Spiking Activity based Pruningcited by 9
  8. 2025Towards Effective and Sparse Adversarial Attack on Spiking Neural Networks via Breaking Invisible Surrogate Gradientscited by 9
  9. 2024Advancing Training Efficiency of Deep Spiking Neural Networks through Rate-based Backpropagationcited by 8
  10. 2024Toward Large-scale Spiking Neural Networks: A Comprehensive Survey and Future Directionscited by 6
  11. 2024Sorbet: A Neuromorphic Hardware-Compatible Transformer-Based Spiking Language Modelcited by 6
  12. 2023NeuroCLIP: Neuromorphic Data Understanding by CLIP and SNNcited by 4
19 more
  1. 2023Brain-Inspired Spiking Neural Networks for Industrial Fault Diagnosis: A Survey, Challenges, and Opportunitiescited by 4
  2. 2025Time to Spike? Understanding the Representational Power of Spiking Neural Networks in Discrete Timecited by 4
  3. 2024SVFormer: A Direct Training Spiking Transformer for Efficient Video Action Recognitioncited by 3
  4. 2024Exploring the Limitations of Layer Synchronization in Spiking Neural Networkscited by 3
  5. 2025ReverB-SNN: Reversing Bit of the Weight and Activation for Spiking Neural Networkscited by 3
  6. 2025Efficient Logit-based Knowledge Distillation of Deep Spiking Neural Networks for Full-Range Timestep Deploymentcited by 2
  7. 2024Functional Classification of Spiking Signal Data Using Artificial Intelligence Techniques: A Reviewcited by 1
  8. 2025SpikingRTNH: Spiking Neural Network for 4D Radar Object Detectioncited by 1
  9. 2025PASCAL: Precise and Efficient ANN- SNN Conversion using Spike Accumulation and Adaptive Layerwise Activationcited by 1
  10. 2025Sparse by Rule: Probability-Based N:M Pruning for Spiking Neural Networkscited by 1
  11. 2026BitFair: A 12-nm Bit-Serial CNN Accelerator with Learnable Early Termination and Adaptive Bit Ordering for Ultra-Low-Power XR Visioncited by 1
  12. 2023InfLoR-SNN: Reducing Information Loss for Spiking Neural Networkscited by 0
  13. 2024Multiscale fusion enhanced spiking neural network for invasive BCI neural signal decodingcited by 0
  14. 2025Optimization of Low-Latency Spiking Neural Networks Utilizing Historical Dynamics of Refractory Periodscited by 0
  15. 2025SPACT18: Spiking Human Action Recognition Benchmark Dataset with Complementary RGB and Thermal Modalitiescited by 0
  16. 2025Stabilizing Direct Training of Spiking Neural Networks: Membrane Potential Initialization and Threshold-robust Surrogate Gradientcited by 0
  17. 2026Signal-Adaptive Trust Regions for Gradient-Free Optimization of Recurrent Spiking Neural Networkscited by 0
  18. 2026Sensor Generalization for Adaptive Sensing in Event-based Object Detection via Joint Distribution Trainingcited by 0
  19. 2026NeuroTrain: Surveying Local Learning Rules for Spiking Neural Networks with an Open Benchmarking Frameworkcited by 0