mlsanityData to 7 Oct 2026

Spiking Neural Networks and Bio-Inspired Supervised Deep Learning: A Survey

arXiv 2307.16235 ↗First posted 30 Jul 2023cs.NE cs.AI cs.CVcited by 8

Not on the map. Why?

Abstract (arXiv)

For a long time, biology and neuroscience fields have been a great source of inspiration for computer scientists, towards the development of Artificial Intelligence (AI) technologies. This survey aims at providing a comprehensive review of recent biologically-inspired approaches for AI. After introducing the main principles of computation and synaptic plasticity in biological neurons, we provide a thorough presentation of Spiking Neural Network (SNN) models, and we highlight the main challenges related to SNN training, where traditional backprop-based optimization is not directly applicable. Therefore, we discuss recent bio-inspired training methods, which pose themselves as alternatives to backprop, both for traditional and spiking networks. Bio-Inspired Deep Learning (BIDL) approaches towards advancing the computational capabilities and biological plausibility of current models.

Key facts. Cited by 8 papers in the map (data through 7 Oct 2026). Builds on 79 of its 228 references that are in the map. First posted on arXiv 30 Jul 2023.

Builds on

79 of 228 references.

References · 79

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  3. 2014Going Deeper with Convolutionscited by 4,231
  4. 2016Deep Variational Information Bottleneckcited by 915
  5. 2019Surrogate Gradient Learning in Spiking Neural Networkscited by 604
  6. 2017Spatio-Temporal Backpropagation for Training High-performance Spiking Neural Networkscited by 399
  7. 2014Deeply-Supervised Netscited by 364
  8. 2020Going Deeper With Directly-Trained Larger Spiking Neural Networkscited by 268
  9. 2022The Forward-Forward Algorithm: Some Preliminary Investigationscited by 262
  10. 2018Deep Learning in Spiking Neural Networkscited by 258
  11. 2016Equilibrium Propagation: Bridging the Gap Between Energy-Based Models and Backpropagationcited by 251
  12. 2021Training Spiking Neural Networks Using Lessons From Deep Learningcited by 251
38 more
  1. 2018Going Deeper in Spiking Neural Networks: VGG and Residual Architecturescited by 236
  2. 2018Direct Training for Spiking Neural Networks: Faster, Larger, Bettercited by 222
  3. 2016Training Deep Spiking Neural Networks using Backpropagationcited by 203
  4. 2017SuperSpike: Supervised learning in multi-layer spiking neural networkscited by 178
  5. 2020Enabling Deep Spiking Neural Networks with Hybrid Conversion and Spike Timing Dependent Backpropagationcited by 142
  6. 2019Training Neural Networks with Local Error Signalscited by 135
  7. 2019Enabling Spike-based Backpropagation for Training Deep Neural Network Architecturescited by 119
  8. 2018Greedy Layerwise Learning Can Scale to ImageNetcited by 113
  9. 2019Overcoming Catastrophic Forgetting with Unlabeled Data in the Wildcited by 111
  10. 2018Dendritic cortical microcircuits approximate the backpropagation algorithmcited by 96
  11. 2020Predictive Coding Approximates Backprop along Arbitrary Computation Graphscited by 89
  12. 2018Differentiable plasticity: training plastic neural networks with backpropagationcited by 83
  13. 2018Unsupervised Learning via Meta-Learningcited by 81
  14. 2016Towards an integration of deep learning and neurosciencecited by 77
  15. 2019The HSIC Bottleneck: Deep Learning without Back-Propagationcited by 77
  16. 2016Towards deep learning with segregated dendritescited by 71
  17. 2020Why should we add early exits to neural networks?cited by 70
  18. 2018Eligibility Traces and Plasticity on Behavioral Time Scales: Experimental Support of neoHebbian Three-Factor Learning Rulescited by 64
  19. 2022Hebbian Deep Learning Without Feedbackcited by 61
  20. 2019Fast and energy-efficient neuromorphic deep learning with first-spike timescited by 52
  21. 2014Random feedback weights support learning in deep neural networkscited by 47
  22. 2020Meta-Learning through Hebbian Plasticity in Random Networkscited by 47
  23. 2019Temporal-Coded Deep Spiking Neural Network with Easy Training and Robust Performancecited by 45
  24. 2020T2FSNN: Deep Spiking Neural Networks with Time-to-first-spike Codingcited by 45
  25. 2018Unsupervised Learning by Competing Hidden Unitscited by 44
  26. 2018BindsNET: A machine learning-oriented spiking neural networks library in Pythoncited by 42
  27. 2018Meta-Learning Update Rules for Unsupervised Representation Learningcited by 37
  28. 2015Training Deeper Convolutional Networks with Deep Supervisioncited by 36
  29. 2021SoftHebb: Bayesian Inference in Unsupervised Hebbian Soft Winner-Take-All Networkscited by 29
  30. 2018Deep Predictive Coding Network with Local Recurrent Processing for Object Recognitioncited by 25
  31. 2019Biologically plausible deep learning -- but how far can we go with shallow networks?cited by 25
  32. 2020Kernelized information bottleneck leads to biologically plausible 3-factor Hebbian learning in deep networkscited by 25
  33. 2022Signal Propagation: A Framework for Learning and Inference In a Forward Passcited by 24
  34. 2017BP-STDP: Approximating Backpropagation using Spike Timing Dependent Plasticitycited by 23
  35. 2018Deep Predictive Coding Network for Object Recognitioncited by 23
  36. 2019People infer recursive visual concepts from just a few examplescited by 23
  37. 2017Deep Echo State Network (DeepESN): A Brief Surveycited by 21
  38. 2017First-spike based visual categorization using reward-modulated STDPcited by 19

50 most cited of 79 All 79 (JSON)

Built on by

Cited by year

Citing papers per year: 2024: 2; 2025: 6.

8 papers.

  1. 2025STAA-SNN: Spatial-Temporal Attention Aggregator for Spiking Neural Networkscited by 11
  2. 2024Degree-Conscious Spiking Graph for Cross-Domain Adaptationcited by 5
  3. 2024Optimal Gradient Checkpointing for Sparse and Recurrent Architectures using Off-Chip Memorycited by 3
  4. 2025From Neurons to Computation: Biological Reservoir Computing for Pattern Recognitioncited by 2
  5. 2025Spiking Neural Networks: The Future of Brain-Inspired Computingcited by 2
  6. 2025From Neural Activity to Computation: Biological Reservoirs for Pattern Recognition in Digit Classificationcited by 1
  7. 2025CA3D: Convolutional-Attentional 3D Nets for Efficient Video Activity Recognition on the Edgecited by 0
  8. 2025Learning Internal Biological Neuron Parameters and Complexity-Based Encoding for Improved Spiking Neural Networks Performancecited by 0