pith. machine review for the scientific record. sign in

arxiv: 2605.15058 · v1 · submitted 2026-05-14 · 💻 cs.NE · cs.AI

Recognition: 2 theorem links

· Lean Theorem

NeuroTrain: Surveying Local Learning Rules for Spiking Neural Networks with an Open Benchmarking Framework

Alessio Caviglia , Filippo Marostica , Roberta Bardini , Alessandro Savino , Stefano Di Carlo
Authors on Pith no claims yet

Pith reviewed 2026-05-15 03:05 UTC · model grok-4.3

classification 💻 cs.NE cs.AI
keywords spiking neural networkstraining algorithmstaxonomylocal learning rulesbenchmarking frameworksurrogate gradientplasticity mechanismsANN-to-SNN conversion
0
0 comments X

The pith

A single taxonomy sorts spiking neural network training methods by their signals and locality while a shared code base lets researchers test them together.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

The paper sorts the growing set of ways to train spiking neural networks into groups based on whether they rely on surrogate gradients, purely local updates, three-factor rules, biological plasticity, conversion from ordinary networks, or other optimizers. It examines each group for the kind of learning signal it uses and how local that signal stays. A reader would care because this map makes it easier to see which methods share the same foundations and which stand apart, cutting down on repeated effort across papers. The authors back the taxonomy with NeuroTrain, an open framework built on snnTorch that runs representative algorithms under identical conditions on the same datasets and models. This setup turns scattered individual results into comparable numbers and surfaces the practical limits that still block wider use of spiking networks.

Core claim

SNN training algorithms can be organized by their computational principles, learning signals, and degree of locality into a fine-grained taxonomy that covers surrogate-gradient backpropagation, local and three-factor rules, biologically inspired plasticity, ANN-to-SNN conversion, and non-standard optimization; the NeuroTrain framework implements a representative subset of each class in one modular code base so that performance, hardware fit, and scaling behavior can be measured on equal terms.

What carries the argument

The taxonomy that groups algorithms according to how they generate and propagate learning signals together with the modular NeuroTrain framework that places representative implementations of each group inside the same code structure for direct comparison.

If this is right

  • Researchers can run head-to-head tests of local-rule methods against surrogate-gradient ones on the same architectures and data sets.
  • Patterns that cut across multiple algorithm classes become visible, showing which limits are shared rather than method-specific.
  • New algorithms can be dropped into the framework and measured against the existing set without rewriting the evaluation pipeline.
  • Hardware choices can be guided by which classes of rules actually run efficiently once placed on the same footing.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

  • If the taxonomy proves stable, hybrid training schemes that borrow locality from one class and scaling from another could be designed more deliberately.
  • The benchmark may show that current local rules still trail surrogate methods on large tasks, directing attention toward specific fixes in signal generation or weight update rules.
  • Consistent numbers across methods could make it clearer which open challenges, such as online learning on edge devices, are truly unsolved rather than just under-tested.

Load-bearing premise

The algorithms picked for NeuroTrain capture the main ideas and performance traits of the wider literature without leaving out key variants or adding hidden coding differences.

What would settle it

A new training method that reaches strong accuracy on standard SNN benchmarks yet cannot be placed in any existing taxonomy category or produces markedly different results when re-coded inside the NeuroTrain framework.

Figures

Figures reproduced from arXiv: 2605.15058 by Alessandro Savino, Alessio Caviglia, Filippo Marostica, Roberta Bardini, Stefano Di Carlo.

Figure 1
Figure 1. Figure 1: Biological neuron behavior. Spatiotemporal integration and action [PITH_FULL_IMAGE:figures/full_fig_p002_1.png] view at source ↗
Figure 2
Figure 2. Figure 2: Two complementary taxonomies for SNN training algorithms. (A) [PITH_FULL_IMAGE:figures/full_fig_p006_2.png] view at source ↗
Figure 3
Figure 3. Figure 3: NeuroTrain framework and benchmarking workflow. The framework organizes SNN training experiments around modular trainers, models, and datasets, [PITH_FULL_IMAGE:figures/full_fig_p016_3.png] view at source ↗
Figure 4
Figure 4. Figure 4: Example of benchmarking results generated by NeuroTrain. Three architectures are benchmarked in variants tailored to the dataset. In the order MNIST, [PITH_FULL_IMAGE:figures/full_fig_p017_4.png] view at source ↗
read the original abstract

The rapid expansion of spiking neural networks (SNNs) has led to a proliferation of training algorithms that differ widely in biological inspiration, computational structure, and hardware suitability. Despite this progress, the field lacks a unified, fine-grained taxonomy that systematically organizes these approaches and clarifies their conceptual relationships. This survey provides a comprehensive taxonomy of SNN training algorithms, spanning surrogate-gradient backpropagation, local and three-factor learning rules, biologically inspired plasticity mechanisms, ANN-to-SNN conversion pipelines, and non-standard optimization strategies. We analyze each class in terms of its computational principles, learning signals, and locality properties. To support reproducible research, we release NeuroTrain, an open-source snnTorch-based framework that implements a representative set of these algorithms within a unified, modular, and extendable framework, enabling consistent benchmarking across datasets, architectures, and training regimes. By consolidating fragmented literature and providing a reusable benchmarking framework, this survey identifies common patterns, highlights open challenges, and outlines promising directions for future work on scalable, efficient SNN training.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Referee Report

1 major / 0 minor

Summary. The manuscript surveys training algorithms for spiking neural networks (SNNs), offering a taxonomy that spans surrogate-gradient backpropagation, local and three-factor learning rules, biologically inspired plasticity mechanisms, ANN-to-SNN conversion pipelines, and non-standard optimization strategies. Each class is analyzed with respect to computational principles, learning signals, and locality properties. The work releases NeuroTrain, an open-source snnTorch-based framework that implements a representative subset of these algorithms to enable consistent, reproducible benchmarking across datasets, architectures, and training regimes.

Significance. If the taxonomy is complete and the NeuroTrain implementations faithfully reproduce the core properties of each class without unstated approximations, the paper would consolidate a fragmented literature and supply a reusable tool for fair comparisons, directly addressing the lack of standardized evaluation in SNN training research.

major comments (1)
  1. [Abstract] Abstract: the claim that NeuroTrain implements 'a representative set' of algorithms is load-bearing for both the taxonomy analysis and the benchmarking contribution, yet no explicit inclusion criteria, coverage audit, or justification for the chosen representatives (particularly within the three-factor and biologically inspired classes) is provided; without this, it is impossible to assess whether major variants with distinct eligibility traces or convergence behaviors have been omitted or distorted by the snnTorch re-implementations.

Simulated Author's Rebuttal

1 responses · 0 unresolved

We thank the referee for their constructive feedback on our survey and the NeuroTrain framework. We address the single major comment below and have prepared revisions to strengthen the manuscript's clarity on algorithm selection and coverage.

read point-by-point responses

  1. Referee: [Abstract] Abstract: the claim that NeuroTrain implements 'a representative set' of algorithms is load-bearing for both the taxonomy analysis and the benchmarking contribution, yet no explicit inclusion criteria, coverage audit, or justification for the chosen representatives (particularly within the three-factor and biologically inspired classes) is provided; without this, it is impossible to assess whether major variants with distinct eligibility traces or convergence behaviors have been omitted or distorted by the snnTorch re-implementations.

    Authors: We agree that the abstract claim requires explicit support. In the revised manuscript we will add a new subsection (Section 4.1) that states the inclusion criteria: algorithms were selected to (i) cover every major class in the taxonomy, (ii) include at least one canonical implementation per class with documented differences in eligibility traces or convergence properties, and (iii) be re-implementable within the snnTorch modular interface without altering core mathematical formulations. We will also insert a coverage-audit table that lists each taxonomy category, the representative algorithm(s) chosen, the key variants deliberately omitted (with citations), and any snnTorch-specific approximations (e.g., fixed time-step discretization). This addition will allow readers to evaluate scope and fidelity directly. revision: yes

Circularity Check

0 steps flagged

No significant circularity in survey and framework release

full rationale

This paper is a literature survey that organizes existing SNN training methods into a taxonomy (surrogate-gradient, local/three-factor rules, biologically inspired plasticity, ANN-to-SNN conversion, non-standard optimization) and releases the NeuroTrain snnTorch-based benchmarking framework. The provided text contains no equations, derivations, fitted parameters, predictions of new quantities, or self-citations used to justify uniqueness theorems or ansatzes. The central claims rest on consolidation of prior work and tool release rather than any internal reduction to inputs by construction. The selection of representative algorithms is presented as a practical choice for the framework, not as a derived or predicted result.

Axiom & Free-Parameter Ledger

0 free parameters · 0 axioms · 0 invented entities

No free parameters, axioms, or invented entities are introduced; the work rests entirely on existing literature and the snnTorch library.

pith-pipeline@v0.9.0 · 5493 in / 1043 out tokens · 36599 ms · 2026-05-15T03:05:56.906634+00:00 · methodology

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Lean theorems connected to this paper

Citations machine-checked in the Pith Canon. Every link opens the source theorem in the public Lean library.

What do these tags mean?
matches
The paper's claim is directly supported by a theorem in the formal canon.
supports
The theorem supports part of the paper's argument, but the paper may add assumptions or extra steps.
extends
The paper goes beyond the formal theorem; the theorem is a base layer rather than the whole result.
uses
The paper appears to rely on the theorem as machinery.
contradicts
The paper's claim conflicts with a theorem or certificate in the canon.
unclear
Pith found a possible connection, but the passage is too broad, indirect, or ambiguous to say the theorem truly supports the claim.

Reference graph

Works this paper leans on

191 extracted references · 191 canonical work pages · 1 internal anchor

  1. [1]

    Maass, Networks of spiking neurons: The third generation of neural network models, Neural Net- works 10 (9) (1997) 1659–1671.doi:10.1016/ S0893-6080(97)00011-7

    W. Maass, Networks of spiking neurons: The third generation of neural network models, Neural Net- works 10 (9) (1997) 1659–1671.doi:10.1016/ S0893-6080(97)00011-7

    work page 1997

  2. [2]

    Davies, N

    M. Davies, N. Srinivasa, T.-H. Lin, G. Chinya, Y . Cao, S. H. Choday, G. Dimou, P. Joshi, N. Imam, S. Jain, Y . Liao, C.-K. Lin, A. Lines, R. Liu, D. Mathaikutty, S. McCoy, A. Paul, J. Tse, G. Venkataramanan, Y .-H. Weng, A. Wild, Y . Yang, H. Wang, Loihi: A Neuromor- phic Manycore Processor with On-Chip Learning, IEEE Micro 38 (1) (2018) 82–99.doi:10.110...

    work page doi:10.1109/mm.2018 2018

  3. [3]

    B. Huo, F. Li, S. Peng, H. Chen, S. Xin, H. Wang, Research on SNN Learning Algorithms and Networks Based on Biological Plausibility, IEEE Access 13 (2025) 95243–95256.doi:10.1109/ACCESS.2025.3566717

    work page doi:10.1109/access.2025.3566717 2025

  4. [4]

    Lansky, S

    P. Lansky, S. Ditlevsen, A review of the methods for signal estimation in stochastic diffusion leaky integrate- and-fire neuronal models, Biological cybernetics 99 (4) (2008) 253–262.doi:10.1007/s00422-008-0237-x

    work page doi:10.1007/s00422-008-0237-x 2008

  5. [6]

    Mészáros, J

    B. Mészáros, J. C. Knight, T. Nowotny, Efficient event- based delay learning in spiking neural networks, Nature Communications 16 (1) (2025) 10422.doi:10.1038/ s41467-025-65394-8

    work page 2025

  6. [8]

    Bi, Spatiotemporal specificity of synaptic plas- ticity: cellular rules and mechanisms, Biological cy- bernetics 87 (5) (2002) 319–332.doi:10.1007/ s00422-002-0349-7

    G.-Q. Bi, Spatiotemporal specificity of synaptic plas- ticity: cellular rules and mechanisms, Biological cy- bernetics 87 (5) (2002) 319–332.doi:10.1007/ s00422-002-0349-7

    work page 2002

  7. [9]

    C. Zha, W. S. Sossin, The molecular diversity of plas- ticity mechanisms underlying memory: An evolutionary perspective, Journal of neurochemistry 163 (6) (2022) 444–460.doi:10.1111/jnc.15717

    work page doi:10.1111/jnc.15717 2022

  8. [10]

    J. D. Sweatt, Neural plasticity and behavior–sixty years of conceptual advances, Journal of neurochemistry 139 (2016) 179–199.doi:10.1111/jnc.13580

    work page doi:10.1111/jnc.13580 2016

  9. [11]

    A. R. McFarlan, C. Y . Chou, A. Watanabe, N. Cherepacha, M. Haddad, H. Owens, P. J. Sjöström, The plasticitome of cortical interneurons, Nature Reviews Neuroscience 24 (2) (2023) 80–97. doi:10.1038/s41583-022-00663-9

    work page doi:10.1038/s41583-022-00663-9 2023

  10. [12]

    Ivanov, A

    D. Ivanov, A. Chezhegov, M. Kiselev, A. Grunin, D. Larionov, Neuromorphic artificial intelligence sys- tems, Frontiers in Neuroscience 16 (Sep. 2022).doi: 10.3389/fnins.2022.959626

    work page doi:10.3389/fnins.2022.959626 2022

  11. [13]

    Caviglia, F

    A. Caviglia, F. Marostica, A. Carpegna, A. Savino, S. Di Carlo, Sfatti: Spiking fpga accelerator for tem- poral task-driven inference - a case study on mnist, in: 2025 IEEE International Conference on Image Process- ing Workshops (ICIPW), 2025, pp. 59–64.doi:10. 1109/ICIPW68931.2025.11385983

    work page arXiv 2025

  12. [14]

    J. Pedersen, et al., Spinnaker 2: A 10 million core pro- cessor system for brain simulation and machine learning, Communicating Process Architectures 2017 & 2018: WoTUG-39 & WoTUG-40 70 (2019) 277.doi:10. 3233/978-1-61499-949-2-277

    work page 2017

  13. [15]

    Carpegna, A

    A. Carpegna, A. Savino, S. D. Carlo, Spiker+: A frame- work for the generation of efficient spiking neural net- works fpga accelerators for inference at the edge, IEEE Transactions on Emerging Topics in Computing 13 (3) (2025) 784–798.doi:10.1109/TETC.2024.3511676

    work page doi:10.1109/tetc.2024.3511676 2025

  14. [16]

    B., Manohar, R., Risk, W

    F. Akopyan, J. Sawada, A. Cassidy, R. Alvarez-Icaza, J. Arthur, P. Merolla, N. Imam, Y . Nakamura, P. Datta, G.-J. Nam, B. Taba, M. Beakes, B. Brezzo, J. B. Kuang, R. Manohar, W. P. Risk, B. Jackson, D. S. Modha, TrueNorth: Design and Tool Flow of a 65 mW 1 Mil- lion Neuron Programmable Neurosynaptic Chip, IEEE Transactions on Computer-Aided Design of Int...

    work page doi:10.1109/tcad.2015.2474396 2015

  15. [17]

    B. V . Benjamin, P. Gao, E. McQuinn, S. Choudhary, A. R. Chandrasekaran, J.-M. Bussat, R. Alvarez-Icaza, J. V . Arthur, P. A. Merolla, K. Boahen, Neurogrid: A Mixed-Analog-Digital Multichip System for Large- Scale Neural Simulations, Proceedings of the IEEE 102 (5) (2014) 699–716.doi:10.1109/JPROC.2014. 2313565

    work page doi:10.1109/jproc.2014 2014

  16. [18]

    Marostica, A

    F. Marostica, A. Carpegna, A. Savino, S. D. Carlo, Energy-efficient digital design: A comparative study of event-driven and clock-driven spiking neurons, in: 2025 IEEE Computer Society Annual Symposium on VLSI (ISVLSI), V ol. 1, 2025, pp. 1–6.doi:10.1109/ ISVLSI65124.2025.11130320

    work page arXiv 2025

  17. [19]

    Ponulak, A

    F. Ponulak, A. Kasinski, Introduction to spiking neural networks: Information processing, learning and applica- tions, Acta Neurobiologiae Experimentalis 71 (4) (2011) 409–433.doi:10.55782/ane-2011-1862

    work page doi:10.55782/ane-2011-1862 2011

  18. [20]

    Ponulak, A

    F. Ponulak, A. Kasi ´nski, Supervised Learning in Spik- ing Neural Networks with ReSuMe: Sequence Learning, Classification, and Spike Shifting, Neural Computation 22 (2) (2010) 467–510.doi:10.1162/neco.2009. 11-08-901

    work page doi:10.1162/neco.2009 2010

  19. [21]

    S. M. Bohte, J. N. Kok, H. La Poutré, Error- backpropagation in temporally encoded networks of spiking neurons, Neurocomputing 48 (1) (2002) 17–37. doi:10.1016/S0925-2312(01)00658-0

    work page doi:10.1016/s0925-2312(01)00658-0 2002

  20. [22]

    Pfeiffer, T

    M. Pfeiffer, T. Pfeil, Deep Learning With Spiking Neu- rons: Opportunities and Challenges, Frontiers in Neuro- science 12 (Oct. 2018).doi:10.3389/fnins.2018. 00774

    work page doi:10.3389/fnins.2018 2018

  21. [23]

    Tavanaei, M

    A. Tavanaei, M. Ghodrati, S. R. Kheradpisheh, T. Masquelier, A. Maida, Deep learning in spiking neu- ral networks, Neural Networks 111 (2019) 47–63.doi: 10.1016/j.neunet.2018.12.002

    work page doi:10.1016/j.neunet.2018.12.002 2019

  22. [24]

    X. Wang, X. Lin, X. Dang, Supervised learning in spik- ing neural networks: A review of algorithms and eval- uations, Neural Networks 125 (2020) 258–280.doi: 10.1016/j.neunet.2020.02.011

    work page doi:10.1016/j.neunet.2020.02.011 2020

  23. [25]

    Vigneron, J

    A. Vigneron, J. Martinet, A critical survey of STDP in Spiking Neural Networks for Pattern Recognition, in: 2020 International Joint Conference on Neural Networks (IJCNN), 2020, pp. 1–9.doi:10.1109/IJCNN48605. 2020.9207239

    work page doi:10.1109/ijcnn48605 2020

  24. [26]

    Taherkhani, A

    A. Taherkhani, A. Belatreche, Y . Li, G. Cosma, L. P. Maguire, T. M. McGinnity, A review of learning in bio- logically plausible spiking neural networks, Neural Net- works 122 (2020) 253–272.doi:10.1016/j.neunet. 2019.09.036

    work page doi:10.1016/j.neunet 2020

  25. [27]

    K. Roy, A. Jaiswal, P. Panda, Towards spike-based ma- chine intelligence with neuromorphic computing, Na- ture 575 (7784) (2019) 607–617.doi:10.1038/ s41586-019-1677-2

    work page 2019

  26. [28]

    S. Dora, N. Kasabov, Spiking Neural Networks for Com- putational Intelligence: An Overview, Big Data and Cognitive Computing 5 (4) (2021) 67.doi:10.3390/ bdcc5040067

    work page 2021

  27. [29]

    Nguyen, X.-T

    D.-A. Nguyen, X.-T. Tran, F. Iacopi, A Review of Al- gorithms and Hardware Implementations for Spiking Neural Networks, Journal of Low Power Electronics and Applications 11 (2) (2021) 23.doi:10.3390/ jlpea11020023

    work page 2021

  28. [30]

    D. V . Christensen, R. Dittmann, B. Linares-Barranco, A. Sebastian, M. Le Gallo, A. Redaelli, S. Slesazeck, T. Mikolajick, S. Spiga, S. Menzel, I. Valov, G. Mi- lano, C. Ricciardi, S.-J. Liang, F. Miao, M. Lanza, T. J. Quill, S. T. Keene, A. Salleo, J. Grollier, D. Markovi ´c, A. Mizrahi, P. Yao, J. J. Yang, G. Indiveri, J. P. Strachan, S. Datta, E. Viane...

    work page 2022

  29. [31]

    J. D. Nunes, M. Carvalho, D. Carneiro, J. S. Cardoso, Spiking Neural Networks: A Survey, IEEE Access 10 60738–60764.doi:10.1109/ACCESS.2022.3179968

    work page doi:10.1109/access.2022.3179968 2022

  30. [32]

    C. D. Schuman, S. R. Kulkarni, M. Parsa, J. P. Mitchell, P. Date, B. Kay, Opportunities for neuromorphic com- puting algorithms and applications, Nature Computa- tional Science 2 (1) (2022) 10–19.doi:10.1038/ s43588-021-00184-y

    work page 2022

  31. [33]

    Shrestha, H

    A. Shrestha, H. Fang, Z. Mei, D. P. Rider, Q. Wu, Q. Qiu, A survey on neuromorphic computing: Models and hardware, IEEE Circuits and Systems Magazine 22 (2) (2022) 6–35.doi:10.1109/MCAS.2022.3166331

    work page doi:10.1109/mcas.2022.3166331 2022

  32. [34]

    Yamazaki, V .-K

    K. Yamazaki, V .-K. V o-Ho, D. Bulsara, N. Le, Spik- ing Neural Networks and Their Applications: A Re- view, Brain Sciences 12 (7) (2022) 863.doi:10.3390/ brainsci12070863

    work page 2022

  33. [35]

    Khacef, P

    L. Khacef, P. Klein, M. Cartiglia, A. Rubino, G. Indi- veri, E. Chicca, Spike-based local synaptic plasticity: a survey of computational models and neuromorphic cir- cuits, Neuromorphic Computing and Engineering 3 (4) (2023) 042001.doi:10.1088/2634-4386/ad05da

    work page doi:10.1088/2634-4386/ad05da 2023

  34. [36]

    Pietrzak, S

    P. Pietrzak, S. Szczesny, D. Huderek, L. Przyborowski, Overview of Spiking Neural Network Learning Ap- proaches and Their Computational Complexities, Sen- sors 23 (6) (2023) 3037.doi:10.3390/s23063037. 19

    work page doi:10.3390/s23063037 2023

  35. [37]

    Rathi, I

    N. Rathi, I. Chakraborty, A. Kosta, A. Sengupta, A. Ankit, P. Panda, K. Roy, Exploring Neuromorphic Computing Based on Spiking Neural Networks: Algo- rithms to Hardware, ACM Comput. Surv. 55 (12) (2023) 243:1–243:49.doi:10.1145/3571155

    work page doi:10.1145/3571155 2023

  36. [38]

    Al Abdul Wahid, A

    S. Al Abdul Wahid, A. Asad, F. Mohammadi, A Sur- vey on Neuromorphic Architectures for Running Artifi- cial Intelligence Algorithms, Electronics 13 (15) (2024) 2963.doi:10.3390/electronics13152963

    work page doi:10.3390/electronics13152963 2024

  37. [39]

    Frenkel, D

    C. Frenkel, D. Bol, G. Indiveri, Bottom-Up and Top- Down Approaches for the Design of Neuromorphic Pro- cessing Systems: Tradeoffs and Synergies Between Nat- ural and Artificial Intelligence, Proceedings of the IEEE 111 (6) (2023) 623–652.doi:10.1109/JPROC.2023. 3273520

    work page doi:10.1109/jproc.2023 2023

  38. [40]

    Z. Yi, J. Lian, Q. Liu, H. Zhu, D. Liang, J. Liu, Learning rules in spiking neural networks: A survey, Neurocom- puting 531 (2023) 163–179.doi:https://doi.org/ 10.1016/j.neucom.2023.02.026

    work page doi:10.1016/j.neucom.2023.02.026 2023

  39. [41]

    Dampfhoffer, T

    M. Dampfhoffer, T. Mesquida, A. Valentian, L. Anghel, Backpropagation-Based Learning Techniques for Deep Spiking Neural Networks: A Survey, IEEE Transactions on Neural Networks and Learning Systems 35 (9) (2024) 11906–11921.doi:10.1109/TNNLS.2023.3263008

    work page doi:10.1109/tnnls.2023.3263008 2024

  40. [42]

    A. H. Khan, X. Cao, C. Luo, S. Zhang, W. Guo, V . N. Katsikis, S. Li, Spiking Neural Networks: A Com- prehensive Survey of Training Methodologies, Hard- ware Implementations and Applications, Artificial Intel- ligence Science and Engineering 1 (3) (2025) 175–207. doi:10.23919/AISE.2025.000013

    work page doi:10.23919/aise.2025.000013 2025

  41. [43]

    Ayasi, C

    B. Ayasi, C. J. Carmona, M. Saleh, A. M. García-Vico, A Practical Tutorial on Spiking Neural Networks: Compre- hensive Review, Models, Experiments, Software Tools, and Implementation Guidelines, Eng 6 (11) (2025) 304. doi:10.3390/eng6110304

    work page doi:10.3390/eng6110304 2025

  42. [44]

    J. Wu, Y . Wang, Z. Li, L. Lu, Q. Li, A Review of Computing with Spiking Neural Networks, Computers, Materials & Continua 78 (3) (2024) 2909–2939.doi: 10.32604/cmc.2024.047240

    work page doi:10.32604/cmc.2024.047240 2024

  43. [45]

    Y . Hu, Q. Zheng, G. Li, H. Tang, G. Pan, Toward Large-scale Spiking Neural Networks: A Comprehen- sive Survey and Future Directions, preprint on arXiv (Aug. 2024).doi:10.48550/arXiv.2409.02111

    work page doi:10.48550/arxiv.2409.02111 2024

  44. [46]

    C. Zhou, H. Zhang, L. Yu, Y . Ye, Z. Zhou, L. Huang, Z. Ma, X. Fan, H. Zhou, Y . Tian, Direct training high- performance deep spiking neural networks: a review of theories and methods, Frontiers in Neuroscience 18 (Jul. 2024).doi:10.3389/fnins.2024.1383844

    work page doi:10.3389/fnins.2024.1383844 2024

  45. [47]

    174197995.54372833

    Progress and Challenges in Large Scale Spiking Neural Networks for AI and Neuroscience, preprint on TechRxiv (2025).doi:10.36227/techrxiv. 174197995.54372833

    work page doi:10.36227/techrxiv 2025

  46. [48]

    Fatima Minhas, R

    M. Fatima Minhas, R. Vidya Wicaksana Putra, F. Awwad, O. Hasan, M. Shafique, Continual Learn- ing With Neuromorphic Computing: Foundations, Meth- ods, and Emerging Applications, IEEE Access 13 (2025) 124824–124873.doi:10.1109/ACCESS.2025. 3588665

    work page doi:10.1109/access.2025 2025

  47. [49]

    Mishra, M

    R. Mishra, M. Suri, A survey and perspective on neuro- morphic continual learning systems, Frontiers in Neuro- science 17 (May 2023).doi:10.3389/fnins.2023. 1149410

    work page doi:10.3389/fnins.2023 2023

  48. [50]

    S. Shen, R. Zhang, C. Wang, R. Huang, A. Tuer- hong, Q. Guo, Z. Lu, J. Zhang, L. Leng, Evolution- ary spiking neural networks: a survey, Journal of Mem- brane Computing 6 (4) (2024) 335–346.doi:10.1007/ s41965-024-00156-x

    work page 2024

  49. [51]

    Karamimanesh, E

    M. Karamimanesh, E. Abiri, M. Shahsavari, K. Hassanli, A. van Schaik, J. Eshraghian, Spiking neural networks on FPGA: A survey of methodologies and recent ad- vancements, Neural Networks 186 (2025) 107256.doi: 10.1016/j.neunet.2025.107256

    work page doi:10.1016/j.neunet.2025.107256 2025

  50. [52]

    Mazurek, J

    S. Mazurek, J. Caputa, J. K. Argasi ´nski, M. Wielgosz, Three-factor learning in spiking neural networks: An overview of methods and trends from a machine learn- ing perspective, Patterns 6 (12) (2025) 101414. URLhttps://www.sciencedirect.com/science/ article/pii/S2666389925002624

    work page 2025

  51. [53]

    J. Lin, S. Lu, M. Bal, A. Sengupta, Benchmarking Spik- ing Neural Network Learning Methods With Varying Lo- cality, IEEE Access 13 (2025) 113606–113617.doi: 10.1109/ACCESS.2025.3582564

    work page doi:10.1109/access.2025.3582564 2025

  52. [54]

    J. K. Eshraghian, M. Ward, E. O. Neftci, X. Wang, G. Lenz, G. Dwivedi, M. Bennamoun, D. S. Jeong, W. D. Lu, Training Spiking Neural Networks Using Lessons From Deep Learning, Proceedings of the IEEE 111 (9) (2023) 1016–1054.doi:10.1109/JPROC. 2023.3308088

    work page doi:10.1109/jproc 2023

  53. [56]

    Werbos, Backpropagation through time: what it does and how to do it, Proceedings of the IEEE 78 (10) (1990) 1550–1560.doi:10.1109/5.58337

    P. Werbos, Backpropagation through time: what it does and how to do it, Proceedings of the IEEE 78 (10) (1990) 1550–1560.doi:10.1109/5.58337

    work page doi:10.1109/5.58337 1990

  54. [57]

    Frémaux, W

    N. Frémaux, W. Gerstner, Neuromodulated Spike- Timing-Dependent Plasticity, and Theory of Three- Factor Learning Rules, Frontiers in Neural Circuits 9 (Jan. 2016).doi:10.3389/fncir.2015.00085. 20

    work page doi:10.3389/fncir.2015.00085 2016

  55. [58]

    Nø kland, Direct Feedback Alignment Provides Learning in Deep Neural Networks, in: Advances in Neural Information Processing Systems, V ol

    A. Nø kland, Direct Feedback Alignment Provides Learning in Deep Neural Networks, in: Advances in Neural Information Processing Systems, V ol. 29, Curran Associates, Inc., 2016. URLhttps://proceedings. neurips.cc/paper/2016/hash/ d490d7b4576290fa60eb31b5fc917ad1-Abstract. html

    work page 2016

  56. [59]

    Frenkel, M

    C. Frenkel, M. Lefebvre, D. Bol, Learning Without Feedback: Fixed Random Learning Signals Allow for Feedforward Training of Deep Neural Networks, Fron- tiers in Neuroscience 15 (Feb. 2021).doi:10.3389/ fnins.2021.629892

    work page arXiv 2021

  57. [60]

    Schrauwen, J

    B. Schrauwen, J. Van Campenhout, Extending spike- prop, in: 2004 IEEE International Joint Conference on Neural Networks (IEEE Cat. No.04CH37541), V ol. 1, 2004, pp. 471–475.doi:10.1109/IJCNN.2004. 1379954

    work page doi:10.1109/ijcnn.2004 2004

  58. [61]

    McKennoch, D

    S. McKennoch, D. Liu, L. Bushnell, Fast Modifications of the SpikeProp Algorithm, in: The 2006 IEEE In- ternational Joint Conference on Neural Network Pro- ceedings, 2006, pp. 3970–3977.doi:10.1109/IJCNN. 2006.246918

    work page doi:10.1109/ijcnn 2006

  59. [62]

    Sporea, A

    I. Sporea, A. Grüning, Supervised Learning in Mul- tilayer Spiking Neural Networks, Neural Computation 25 (2) (2013) 473–509.doi:10.1162/NECO_a_00396

    work page doi:10.1162/neco_a_00396 2013

  60. [63]

    Mohemmed, S

    A. Mohemmed, S. Schliebs, S. Matsuda, N. Kasabov, Span: spike pattern association neuron for learning spatio-temporal spike patterns, International Journal of Neural Systems 22 (04) (2012) 1250012.doi:10. 1142/S0129065712500128

    work page 2012

  61. [64]

    R. V . Florian, The Chronotron: A Neuron That Learns to Fire Temporally Precise Spike Patterns, PLOS ONE 7 (8) (2012) e40233.doi:10.1371/journal.pone. 0040233

    work page doi:10.1371/journal.pone 2012

  62. [65]

    Gütig, H

    R. Gütig, H. Sompolinsky, The tempotron: a neuron that learns spike timing-based decisions, Nature Neuro- science 9 (3) (2006) 420–428.doi:10.1038/nn1643

    work page doi:10.1038/nn1643 2006

  63. [66]

    J. J. Wade, L. J. McDaid, J. A. Santos, H. M. Sayers, SW AT: A Spiking Neural Network Training Algorithm for Classification Problems, IEEE Transactions on Neu- ral Networks 21 (11) (2010) 1817–1830.doi:10.1109/ TNN.2010.2074212

    work page arXiv 2010

  64. [68]

    Y . Wu, L. Deng, G. Li, J. Zhu, L. Shi, Spatio-Temporal Backpropagation for Training High-Performance Spik- ing Neural Networks, Frontiers in Neuroscience 12 (May 2018).doi:10.3389/fnins.2018.00331

    work page doi:10.3389/fnins.2018.00331 2018

  65. [69]

    E. O. Neftci, H. Mostafa, F. Zenke, Surrogate Gradi- ent Learning in Spiking Neural Networks: Bringing the Power of Gradient-Based Optimization to Spiking Neu- ral Networks, IEEE Signal Processing Magazine 36 (6) (2019) 51–63.doi:10.1109/MSP.2019.2931595

    work page doi:10.1109/msp.2019.2931595 2019

  66. [70]

    Zenke, S

    F. Zenke, S. Ganguli, SuperSpike: Supervised Learning in Multilayer Spiking Neural Networks, Neural Compu- tation 30 (6) (2018) 1514–1541.doi:10.1162/neco_ a_01086

    work page doi:10.1162/neco_ 2018

  67. [71]

    S. B. Shrestha, G. Orchard, SLAYER: Spike Layer Error Reassignment in Time, in: Advances in Neural Infor- mation Processing Systems, V ol. 31, Curran Associates, Inc., 2018. URLhttps://proceedings.neurips. cc/paper_files/paper/2018/hash/ 82f2b308c3b01637c607ce05f52a2fed-Abstract. html

    work page 2018

  68. [72]

    A. Amir, B. Taba, D. Berg, T. Melano, J. McKinstry, C. Di Nolfo, T. Nayak, A. Andreopoulos, G. Gar- reau, M. Mendoza, J. Kusnitz, M. Debole, S. Esser, T. Delbruck, M. Flickner, D. Modha, A Low Power, Fully Event-Based Gesture Recognition System, in: 2017 IEEE Conference on Computer Vision and Pat- tern Recognition (CVPR), IEEE, Honolulu, HI, 2017, pp. 738...

    work page doi:10.1109/cvpr.2017.781 2017

  69. [73]

    F. C. Bauer, G. Lenz, S. Haghighatshoar, S. Sheik, EXO- DUS: Stable and efficient training of spiking neural net- works, Frontiers in Neuroscience 17 (Feb. 2023).doi: 10.3389/fnins.2023.1110444

    work page doi:10.3389/fnins.2023.1110444 2023

  70. [74]

    Zenke, T

    F. Zenke, T. P. V ogels, The Remarkable Robustness of Surrogate Gradient Learning for Instilling Complex Function in Spiking Neural Networks, Neural Compu- tation 33 (4) (2021) 899–925.doi:10.1162/neco_a_ 01367

    work page doi:10.1162/neco_a_ 2021

  71. [75]

    W. Fang, Z. Yu, Y . Chen, T. Masquelier, T. Huang, Y . Tian, Incorporating Learnable Membrane Time Con- stant To Enhance Learning of Spiking Neural Networks, 2021, pp. 2661–2671. URLhttps://openaccess.thecvf.com/ content/ICCV2021/html/Fang_Incorporating_ Learnable_Membrane_Time_Constant_To_ Enhance_Learning_of_Spiking_ICCV_2021_ paper.html

    work page 2021

  72. [76]

    X. Yao, F. Li, Z. Mo, J. Cheng, GLIF: A Unified Gated Leaky Integrate-and-Fire Neuron for Spiking Neural Networks, Advances in Neural Information Processing Systems 35 (2022) 32160–32171. URLhttps://proceedings.neurips. cc/paper_files/paper/2022/hash/ cfa8440d500a6a6867157dfd4eaff66e-Abstract-Conference. html 21

    work page 2022

  73. [77]

    Zheng, Y

    H. Zheng, Y . Wu, L. Deng, Y . Hu, G. Li, Going Deeper With Directly-Trained Larger Spiking Neural Networks, Proceedings of the AAAI Conference on Artificial Intel- ligence 35 (12) (2021) 11062–11070.doi:10.1609/ aaai.v35i12.17320

    work page 2021

  74. [78]

    Y . Kim, P. Panda, Revisiting Batch Normalization for Training Low-Latency Deep Spiking Neural Networks From Scratch, Frontiers in Neuroscience 15 (Dec. 2021). doi:10.3389/fnins.2021.773954

    work page doi:10.3389/fnins.2021.773954 2021

  75. [79]

    C. Duan, J. Ding, S. Chen, Z. Yu, T. Huang, Tempo- ral Effective Batch Normalization in Spiking Neural Networks, Advances in Neural Information Processing Systems 35 (2022) 34377–34390. URLhttps://proceedings.neurips. cc/paper_files/paper/2022/hash/ de2ad3ed44ee4e675b3be42aa0b615d0-Abstract-Conference. html

    work page 2022

  76. [80]

    Y . Guo, Y . Zhang, Y . Chen, W. Peng, X. Liu, L. Zhang, X. Huang, Z. Ma, Membrane Potential Batch Nor- malization for Spiking Neural Networks, 2023, pp. 19420–19430. URLhttps://openaccess.thecvf.com/content/ ICCV2023/html/Guo_Membrane_Potential_ Batch_Normalization_for_Spiking_Neural_ Networks_ICCV_2023_paper.html

    work page 2023

  77. [81]

    S. Deng, Y . Li, S. Zhang, S. Gu, Temporal efficient training of spiking neural network via gradient re- weighting, in: International Conference on Learning Representations, 2022. URLhttps://openreview.net/forum?id= _XNtisL32jv

    work page 2022

  78. [82]

    Y . Guo, X. Tong, Y . Chen, L. Zhang, X. Liu, Z. Ma, X. Huang, RecDis-SNN: Rectifying Membrane Poten- tial Distribution for Directly Training Spiking Neural Networks, 2022, pp. 326–335. URLhttps://openaccess.thecvf.com/content/ CVPR2022/html/Guo_RecDis-SNN_Rectifying_ Membrane_Potential_Distribution_for_ Directly_Training_Spiking_Neural_CVPR_ 2022_paper.html

    work page 2022

  79. [83]

    Y . Guo, Y . Chen, L. Zhang, X. Liu, Y . Wang, X. Huang, Z. Ma, IM-Loss: Information Maximization Loss for Spiking Neural Networks, Advances in Neural Informa- tion Processing Systems 35 (2022) 156–166. URLhttps://proceedings.neurips. cc/paper_files/paper/2022/hash/ 010c5ba0cafc743fece8be02e7adb8dd-Abstract-Conference. html

    work page 2022

  80. [84]

    Q. Meng, M. Xiao, S. Yan, Y . Wang, Z. Lin, Z.-Q. Luo, Training High-Performance Low-Latency Spiking Neural Networks by Differentiation on Spike Represen- tation, 2022, pp. 12444–12453. URLhttps://openaccess.thecvf.com/ content/CVPR2022/html/Meng_Training_ High-Performance_Low-Latency_Spiking_ Neural_Networks_by_Differentiation_on_ Spike_CVPR_2022_paper.html

    work page 2022

Showing first 80 references.