/must-read-papers-on-snn

Collect important papers about snn

must-read-papers-on-snn

Collect important papers about snn

Content

1. Survey
2. Supervised learning
 2.1 Synaptic plasticity  2.2 Surrogate gradient
3. Conversion
4. Unsupervised learning

Survey papers

  1. Deep learning in spiking neural networks. Neural Networks 2019. paper

    Tavanaei A, Ghodrati M, Kheradpisheh S R, et al.

  2. 脉冲神经网络研究进展综述. 控制与决策 2021. paper

    Hu Yifan, Li Guoqi, Wu Yujie, Deng Lei

  3. Rethinking the performance comparison between SNNS and ANNS. Neural Networks 2020. paper

    Deng L, Wu Y, Hu X, et al.

Supervised learning

Synaptic plasticity

  1. The tempotron: a neuron that learns spike timing–based decisions. Nature neuroscience 2006. paper

    Gütig R, Sompolinsky H.

  2. Supervised learning in spiking neural networks with ReSuMe: sequence learning, classification, and spike shifting. Neural computation 2010. paper

    Ponulak F, Kasiński A.

  3. Learning Real-World Stimuli by Single-Spike Coding and Tempotron Rule. IJCNN 2012. paper

    Tang H, Yu Q, Tan K C.

  4. A review of learning in biologically plausible spiking neural networks. Neural Networks 2020. paper

    Taherkhani A, Belatreche A, Li Y, et al.

Surrogate gradient

  1. Training deep spiking neural networks using backpropagation. Frontiers in neuroscience 2016. paper

    Lee J H, Delbruck T, Pfeiffer M.

  2. Spatio-temporal backpropagation for training high-performance spiking neural networks. Frontiers in neuroscience 2018. paper

    Wu Y, Deng L, Li G, et al.

  3. Surrogate gradient learning in spiking neural networks. IEEE Signal Processing Magazine 2019. paper

    Neftci E O, Mostafa H, Zenke F.

  4. Direct training for spiking neural networks: Faster, larger, better. AAAI 2019. paper

    Wu Y, Deng L, Li G, et al.

  5. Slayer: Spike layer error reassignment in time. NIPS 2018. paper

    Shrestha S B, Orchard G.

  6. Incorporating Learnable Membrane Time Constant to Enhance Learning of Spiking Neural Networks. arXiv 2020. paper

    Wei Fang, Zhaofei Yu, Yanqi Chen, et al.

  7. Temporal spike sequence learning via backpropagation for deep spiking neural networks. NIPS 2020. paper

    Zhang W, Li P.

  8. Brain-inspired global-local hybrid learning towards human-like intelligence. arXiv 2020. paper

    Wu Y, Zhao R, Zhu J, et al.

  9. Convolutional Spiking Neural Networks for Spatio-Temporal Feature Extraction. arXiv 2020. paper

    Samadzadeh A, Far F S T, Javadi A, et al.

  10. Going Deeper With Directly-Trained Larger Spiking Neural Networks. AAAI 2021. paper

    Zheng H, Wu Y, Deng L, et al.

Conversion

  1. Spiking deep convolutional neural networks for energy-efficient object recognition. IJCV 2015. paper

    Y Cao, Y Chen, D Khosla.

  2. Fast-classifying, high-accuracy spiking deep networks through weight and threshold balancing. IJCNN 2015. paper

    Diehl P U, Neil D, Binas J, et al.

  3. Conversion of continuous-valued deep networks to efficient event-driven networks for image classification. Frontiers in neuroscience 2017. paper

    Rueckauer B, Lungu I A, Hu Y, et al.

  4. Going deeper in spiking neural networks: VGG and residual architectures. Frontiers in neuroscience 2019. paper

    Sengupta A, Ye Y, Wang R, et al.

  5. Rmp-snn: Residual membrane potential neuron for enabling deeper high-accuracy and low-latency spiking neural network. CVPR 2020.paper

    Han B, Srinivasan G, Roy K.

  6. Deep spiking neural network: Energy efficiency through time based coding. ECCV 2020. paper

    Han B, Roy K.

  7. Enabling deep spiking neural networks with hybrid conversion and spike timing dependent backpropagation. ICLR 2020. paper

    Rathi N, Srinivasan G, Panda P, et al.

  8. Exploring the connection between binary and spiking neural networks. Frontiers in Neuroscience 2020. paper

    Lu S, Sengupta A.

  9. TCL: an ANN-to-SNN Conversion with Trainable Clipping Layers. arXiv 2020. paper

    Ho N D, Chang I J.

  10. DIET-SNN: A Low-Latency Spiking Neural Network with Direct Input Encoding & Leakage and Threshold Optimization. Openreview 2020. paper

    N Rathi, K Roy.

  11. Optimal Conversion of Conventional Artificial Neural Networks to Spiking Neural Networks. ICLR 2021. paper

    Deng S, Gu S.

  12. A Free Lunch From ANN: Towards Efficient, Accurate Spiking Neural Networks Calibration. ICML 2021. paper

    Li Y, Deng S, Dong X, et al.

Unsupervised learning

  1. Learning temporally encoded patterns in networks of spiking neurons. Neural Processing Letters 1997. paper

    Ruf B, Schmitt M.

  2. Unsupervised regenerative learning of hierarchical features in spiking deep networks for object recognition. IJCNN 2016. paper

    Panda P, Roy K.

  3. STDP-based spiking deep convolutional neural networks for object recognition. Neural Networks 2018. paper

    Kheradpisheh S R, Ganjtabesh M, Thorpe S J, et al.

  4. A biologically plausible supervised learning method for spiking neural networks using the symmetric STDP rule. Neural Networks 2020. paper

    Hao Y, Huang X, Dong M, et al.

  5. Training deep spiking neural networks for energy-efficient neuromorphic computing. ICASSP 2020. paper

    Srinivasan G, Lee C, Sengupta A, et al.