mlsanityData to 7 Oct 2026

BSNN: Towards Faster and Better Conversion of Artificial Neural Networks to Spiking Neural Networks with Bistable Neurons

arXiv 2105.12917 ↗First posted 27 May 2021cs.NE cs.AIcited by 12

Not on the map. Why?

Abstract (arXiv)

The spiking neural network (SNN) computes and communicates information through discrete binary events. It is considered more biologically plausible and more energy-efficient than artificial neural networks (ANN) in emerging neuromorphic hardware. However, due to the discontinuous and non-differentiable characteristics, training SNN is a relatively challenging task. Recent work has achieved essential progress on an excellent performance by converting ANN to SNN. Due to the difference in information processing, the converted deep SNN usually suffers serious performance loss and large time delay. In this paper, we analyze the reasons for the performance loss and propose a novel bistable spiking neural network (BSNN) that addresses the problem of spikes of inactivated neurons (SIN) caused by the phase lead and phase lag. Also, when ResNet structure-based ANNs are converted, the information of output neurons is incomplete due to the rapid transmission of the shortcut path. We design synchronous neurons (SN) to help efficiently improve performance. Experimental results show that the proposed method only needs 1/4-1/10 of the time steps compared to previous work to achieve nearly lossless conversion. We demonstrate state-of-the-art ANN-SNN conversion for VGG16, ResNet20, and ResNet34 on challenging datasets including CIFAR-10 (95.16% top-1), CIFAR-100 (78.12% top-1), and ImageNet (72.64% top-1).

Key facts. Cited by 12 papers in the map (data through 7 Oct 2026). Builds on 31 of its 77 references that are in the map. First posted on arXiv 27 May 2021.

Builds on

31 of 77 references.

References · 31

  1. 2017Attention Is All You Needcited by 59,932
  2. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  3. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  4. 2015You Only Look Once: Unified, Real-Time Object Detectioncited by 4,829
  5. 2014Neural Machine Translation by Jointly Learning to Align and Translatecited by 4,530
  6. 2015SSD: Single Shot MultiBox Detectorcited by 3,125
  7. 2015Fast R-CNNcited by 2,930
  8. 2019Energy and Policy Considerations for Deep Learning in NLPcited by 1,242
  9. 2014Deep Neural Networks are Easily Fooled: High Confidence Predictions for Unrecognizable Imagescited by 774
  10. 2017Measuring Catastrophic Forgetting in Neural Networkscited by 359
  11. 2020Incorporating Learnable Membrane Time Constant to Enhance Learning of Spiking Neural Networkscited by 340
  12. 2021Deep Residual Learning in Spiking Neural Networkscited by 326
19 more
  1. 2018Deep Learning in Spiking Neural Networkscited by 258
  2. 2018SLAYER: Spike Layer Error Reassignment in Timecited by 257
  3. 2018Going Deeper in Spiking Neural Networks: VGG and Residual Architecturescited by 236
  4. 2018Direct Training for Spiking Neural Networks: Faster, Larger, Bettercited by 222
  5. 2015Quantized Convolutional Neural Networks for Mobile Devicescited by 212
  6. 2020Enabling Deep Spiking Neural Networks with Hybrid Conversion and Spike Timing Dependent Backpropagationcited by 142
  7. 2020RMP-SNN: Residual Membrane Potential Neuron for Enabling Deeper High-Accuracy and Low-Latency Spiking Neural Networkcited by 141
  8. 2020Improved Noisy Student Training for Automatic Speech Recognitioncited by 139
  9. 2021Optimal Conversion of Conventional Artificial Neural Networks to Spiking Neural Networkscited by 134
  10. 2019Enabling Spike-based Backpropagation for Training Deep Neural Network Architecturescited by 119
  11. 2020Temporal Spike Sequence Learning via Backpropagation for Deep Spiking Neural Networkscited by 98
  12. 2019Spiking Neural Networks and Online Learning: An Overview and Perspectivescited by 41
  13. 2018A Biologically Plausible Supervised Learning Method for Spiking Neural Networks Using the Symmetric STDP Rulecited by 36
  14. 2018Fast and Efficient Information Transmission with Burst Spikes in Deep Spiking Neural Networkscited by 34
  15. 2019Biologically plausible deep learning -- but how far can we go with shallow networks?cited by 25
  16. 2019An Introduction to Probabilistic Spiking Neural Networks: Probabilistic Models, Learning Rules, and Applicationscited by 25
  17. 2018Spiking Deep Residual Networkcited by 18
  18. 2015STDP as presynaptic activity times rate of change of postsynaptic activitycited by 8
  19. 2020Compiling Spiking Neural Networks to Neuromorphic Hardwarecited by 4

Built on by

Cited by year

Citing papers per year: 2021: 2; 2022: 4; 2023: 2; 2024: 1; 2025: 3.

12 papers.

  1. 2022Efficient and Accurate Conversion of Spiking Neural Network with Burst Spikescited by 30
  2. 2021Backpropagation with Biologically Plausible Spatio-Temporal Adjustment For Training Deep Spiking Neural Networkscited by 22
  3. 2022Spike Calibration: Fast and Accurate Conversion of Spiking Neural Network for Object Detection and Segmentationcited by 15
  4. 2024Sign Gradient Descent-based Neuronal Dynamics: ANN-to-SNN Conversion Beyond ReLU Networkcited by 5
  5. 2023Exploiting High Performance Spiking Neural Networks with Efficient Spiking Patternscited by 3
  6. 2023MSAT: Biologically Inspired Multi-Stage Adaptive Threshold for Conversion of Spiking Neural Networkscited by 3
  7. 2025SPARTA: Advancing Sparse Attention in Spiking Neural Networks via Spike-Timing-Based Prioritizationcited by 2
  8. 2022S3NN: Time Step Reduction of Spiking Surrogate Gradients for Training Energy Efficient Single-Step Spiking Neural Networkscited by 1
  9. 2022DPSNN: A Differentially Private Spiking Neural Network with Temporal Enhanced Poolingcited by 1
  10. 2021N-Omniglot, a large-scale neuromorphic dataset for spatio-temporal sparse few-shot learningcited by 0
  11. 2025Temporal Misalignment in ANN-SNN Conversion and Its Mitigation via Probabilistic Spiking Neuronscited by 0
  12. 2025Optimization of Low-Latency Spiking Neural Networks Utilizing Historical Dynamics of Refractory Periodscited by 0