Spiking Neural Networks: A Survey
Open accessThe DOI matches its Crossref record; 28 of the 28 references it cites were found in a registry or an index.
Abstract
The field of Deep Learning (DL) has seen a remarkable series of developments with increasingly accurate and robust algorithms. However, the increase in performance has been accompanied by an increase in the parameters, complexity, and training and inference time of the models, which means that we are rapidly reaching a point where DL may no longer be feasible. On the other hand, some specific applications need to be carefully considered when developing DL models due to hardware limitations or power requirements. In this context, there is a growing interest in efficient DL algorithms, with Spiking Neural Networks (SNNs) being one of the most promising paradigms. Due to the inherent asynchrony and sparseness of spike trains, these types of networks have the potential to reduce power consumption while maintaining relatively good performance. This is attractive for efficient DL and if successful, could replace traditional Artificial Neural Networks (ANNs) in many applications. However, despite significant progress, the performance of SNNs on benchmark datasets is often lower than that of traditional ANNs. Moreover, due to the non-differentiable nature of their activation functions, it is difficult to train SNNs with direct backpropagation, so appropriate training strategies must be found. Nevertheless, significant efforts have been made to develop competitive models. This survey covers the main ideas behind SNNs and reviews recent trends in learning rules and network architectures, with a particular focus on biologically inspired strategies. It also provides some practical considerations of state-of-the-art SNNs and discusses relevant research opportunities.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.90 · Cited by 235,474
LeCun, Y., Bengio, Y., & Hinton, G. (2015) · Nature · doi:10.1038/nature14539 · Cited by 84,126
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2018) · arXiv · doi:10.48550/arxiv.1810.04805 · Cited by 73,173
ImageNet: A large-scale hierarchical image database
Deng, J., Dong, W., Socher, R., Li, L.-J., Li, K., & Fei-Fei, L. (2009) · 2009 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2009.5206848 · Cited by 65,333
Gradient-based learning applied to document recognition
Lecun, Y., Bottou, L., Bengio, Y., & Haffner, P. (1998) · Proceedings of the IEEE · doi:10.1109/5.726791 · Cited by 58,805 · cited 10×
“Although a simple solution, the proposed strategy was demonstrated to achieve competitive performance on the MNIST [11] and CALTECH face/motorbike datasets.”
BackgroundMethodInfluentialLearning representations by back-propagating errors
Rumelhart, D. E., Hinton, G. E., & Williams, R. J. (1986) · Nature · doi:10.1038/323533a0 · Cited by 31,892
PyTorch: An Imperative Style, High-Performance Deep Learning Library
Paszke, A., Gross, S., Massa, F., Lerer, A., Bradbury, J., Chanan, G., Killeen, T., Lin, Z., Gimelshein, N., Antiga, L., et al. (2019) · arXiv · doi:10.48550/arxiv.1912.01703 · Cited by 31,473
Language Models are Few-Shot Learners
Brown, T. B., Mann, B., Ryder, N., Subbiah, M., Kaplan, J., Dhariwal, P., Neelakantan, A., Shyam, P., Sastry, G., Askell, A., et al. (2020) · arXiv · doi:10.48550/arxiv.2005.14165 · Cited by 23,372
A fast learning algorithm for deep belief nets
Hinton, G. E., Osindero, S., & Teh, Y.-W. (2006) · Neural Computation · doi:10.1162/neco.2006.18.7.1527 · Cited by 16,336 · cited 1×
“In the 1990’s it was thought that learning useful representations from raw data was not feasible but later, in 2006, a team of researchers demonstrated that BP works remarkably well to train deep ANNs for classification and recognition tasks [99, 100, 101, 102].”
BackgroundSelf-organized formation of topologically correct feature maps
Kohonen, T. (1982) · Biological Cybernetics · doi:10.1007/bf00337288 · Cited by 9,529
Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms
Xiao, H., Rasul, K., & Vollgraf, R. (2017) · arXiv · doi:10.48550/arxiv.1708.07747 · Cited by 6,108
Greedy layer-wise training of deep networks
Bengio, Y., Lamblin, P., Popovici, D., & Larochelle, H. (2007) · Advances in Neural Information Processing Systems 19 · doi:10.7551/mitpress/7503.003.0024 · Cited by 4,841 · cited 1×
“In the 1990’s it was thought that learning useful representations from raw data was not feasible but later, in 2006, a team of researchers demonstrated that BP works remarkably well to train deep ANNs for classification and recognition tasks [99, 100, 101, 102].”
BackgroundSimple model of spiking neurons
Izhikevich, E. M. (2003) · IEEE Transactions on Neural Networks · doi:10.1109/tnn.2003.820440 · Cited by 4,828
Bi, G.-Q., & Poo, M.-M. (1998) · The Journal of Neuroscience · doi:10.1523/jneurosci.18-24-10464.1998 · Cited by 4,744
Speed of processing in the human visual system
Thorpe, S., Fize, D., & Marlot, C. (1996) · Nature · doi:10.1038/381520a0 · Cited by 3,538
Dopamine, learning and motivation.
Wise, R. A. (2004) · Nature Reviews Neuroscience · doi:10.1038/nrn1406 · Cited by 3,379 · cited 1×
“For example, it was demonstrated that dopamine acts as a reward signal, affecting synaptic plasticity [151, 152, 153].”
BackgroundNeuronal Dynamics: From Single Neurons to Networks and Models of Cognition
Gerstner, W., Kistler, W. M., Naud, R., & Paninski, L. (2014) · doi:10.1017/cbo9781107447615 · Cited by 1,515 · cited 1×
“Nonetheless, averaging a neuron’s response over simulations allows the smoothing of intrinsic and network-related noise spikes that occur both in vivo and in simulated neurons [82].”
BackgroundGPipe: Efficient Training of Giant Neural Networks using Pipeline Parallelism
Huang, Y., Cheng, Y., Bapna, A., Firat, O., Chen, M. X., Chen, D., Lee, H., Ngiam, J., Le, Q. V., Wu, Y., et al. (2018) · arXiv · doi:10.48550/arxiv.1811.06965 · Cited by 1,180
Efficient Learning of Sparse Representations with an Energy-Based Model
Ranzato, M., Poultney, C., Chopra, S., & LeCun, Y. (2007) · Advances in Neural Information Processing Systems 19 · doi:10.7551/mitpress/7503.003.0147 · Cited by 1,106
A selective role for dopamine in stimulus-reward learning
Flagel, S. B., Clark, J. J., Robinson, T. E., Mayo, L., Czuj, A., Willuhn, I., Akers, C. A., Clinton, S. M., Phillips, P. E. M., & Akil, H. (2011) · Nature · doi:10.1038/nature09588 · Cited by 1,026 · cited 1×
“For example, it was demonstrated that dopamine acts as a reward signal, affecting synaptic plasticity [151, 152, 153].”
BackgroundA Low Power, Fully Event-Based Gesture Recognition System
Amir, A., Taba, B., Berg, D., Melano, T., McKinstry, J., Di Nolfo, C., Nayak, T., Andreopoulos, A., Garreau, G., Mendoza, M., et al. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.781 · Cited by 1,017
Population coding of shape in area V4
Pasupathy, A., & Connor, C. E. (2002) · Nature Neuroscience · doi:10.1038/972 · Cited by 552 · cited 1×
“Some evidence shows the presence of population rate coding in both macaque and mouse visual systems [85, 86].”
BackgroundCarbon Emissions and Large Neural Network Training
Patterson, D., Gonzalez, J., Le, Q., Liang, C., Munguia, L.-M., Rothchild, D., So, D., Texier, M., & Dean, J. (2021) · arXiv · doi:10.48550/arxiv.2104.10350 · Cited by 486 · cited 1×
“…improvements of model capabilities have been correlated with an increase in models’ parameters, complexity, prediction latency, training time, etc. Nowadays, training a single top-performing model requires many hardware and energy resources, which results in a large carbon footprint [7].”
BackgroundArchitectures of neuronal circuits
Luo, L. (2021) · Science · doi:10.1126/science.abg7285 · Cited by 390 · cited 3×
“For example, it is believed to occur at the retina, where active photoreceptors, through horizontal cells, will inhibit neighbouring photoreceptors [37].”
BackgroundInfluentialInstructed learning in the auditory localization pathway of the barn owl
Knudsen, E. I. (2002) · Nature · doi:10.1038/417322a · Cited by 320
Nessler, B., Pfeiffer, M., Buesing, L., & Maass, W. (2013) · PLoS Computational Biology · doi:10.1371/journal.pcbi.1003037 · Cited by 281 · cited 1×
“On one hand, they added an exponential weight dependence to the previous strategy of synaptic traces [119, 120] (see Equation 10).”
BackgroundTasks for inhibitory interneurons in intact brain circuits
Roux, L., & Buzsáki, G. (2015) · Neuropharmacology · doi:10.1016/j.neuropharm.2014.09.011 · Cited by 218 · cited 2×
“These include: controlling of synchronous or oscillatory spiking activity, regulation of neuron sensitivity to input stimuli, through the promotion of a fast response, and preventing quiescence or saturation of postsynaptic firing rates [38, 39, 40, 41, 42].”
BackgroundBliss, T. V. P., & Lømo, T. (1973) · The Journal of Physiology · doi:10.1113/jphysiol.1973.sp010273 · Cited by 135
Metadata
- Authors
- Nunes, J. D., Carvalho, M., Carneiro, D., & Cardoso, J. S.
- Venue
- IEEE Access
- Published
- 2022
- Volume
- 10
- Pages
- 60738-60764
- ISSN
- 2169-3536 (ISSN-L)
- OpenAlex
- W4285247025
- Cited by
- 215
- References
- 28
- FWCI
- 10.31
- Type
- journal article
- Language
- en
- Open access
- gold
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.