The DOI matches its Crossref record; 35 of the 35 references it cites were found in a registry or an index.
Surrogate Gradient Learning in Spiking Neural Networks: Bringing the Power of Gradient-Based Optimization to Spiking Neural Networks
Abstract
Spiking neural networks (SNNs) are nature's versatile solution to fault-tolerant, energy-efficient signal processing. To translate these benefits into hardware, a growing number of neuromorphic spiking NN processors have attempted to emulate biological NNs. These developments have created an imminent need for methods and tools that enable such systems to solve real-world signal processing problems. Like conventional NNs, SNNs can be trained on real, domain-specific data; however, their training requires the overcoming of a number of challenges linked to their binary and dynamical nature. This article elucidates step-by-step the problems typically encountered when training SNNs and guides the reader through the key concepts of synaptic plasticity and data-driven learning in the spiking setting. Accordingly, it gives an overview of existing approaches and provides an introduction to surrogate gradient (SG) methods, specifically, as a particularly flexible and efficient method to overcome the aforementioned challenges.
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
A Learning Algorithm for Continually Running Fully Recurrent Neural Networks
Williams, R. J., & Zipser, D. (1989) · Neural Computation · doi:10.1162/neco.1989.1.2.270 · Cited by 4,369 · cited 2×
“2) The forward method: In some situations, it is beneficial to propagate all necessary information for gradient computation forward in time [14].”
MethodResultA learning algorithm for Boltzmann machines
Ackley, D. H., Hinton, G. E., & Sejnowski, T. J. (1985) · Cognitive Science · doi:10.1207/s15516709cog0901_7 · Cited by 3,402
Courbariaux, M., Hubara, I., Soudry, D., El-Yaniv, R., & Bengio, Y. (2016) · arXiv · doi:10.48550/arxiv.1602.02830 · Cited by 2,106
Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation
Bengio, Y., Léonard, N., & Courville, A. (2013) · arXiv · doi:10.48550/arxiv.1308.3432 · Cited by 1,910
Neuronal 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
Deep learning in spiking neural networks
Tavanaei, A., Ghodrati, M., Kheradpisheh, S. R., Masquelier, T., & Maida, A. (2019) · Neural Networks · doi:10.1016/j.neunet.2018.12.002 · Cited by 1,386
Error-backpropagation in temporally encoded networks of spiking neurons
Bohte, S. M., Kok, J. N., & La Poutré, H. (2002) · Neurocomputing · doi:10.1016/s0925-2312(01)00658-0 · Cited by 1,021
Training Deep Spiking Neural Networks Using Backpropagation
Lee, J. H., Delbruck, T., & Pfeiffer, M. (2016) · Frontiers in Neuroscience · doi:10.3389/fnins.2016.00508 · Cited by 976
Random synaptic feedback weights support error backpropagation for deep learning
Lillicrap, T. P., Cownden, D., Tweed, D. B., & Akerman, C. J. (2016) · Nature Communications · doi:10.1038/ncomms13276 · Cited by 812
Convolutional networks for fast, energy-efficient neuromorphic computing
Esser, S. K., Merolla, P. A., Arthur, J. V., Cassidy, A. S., Appuswamy, R., Andreopoulos, A., Berg, D. J., McKinstry, J. L., Melano, T., Barch, D. R., et al. (2016) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.1604850113 · Cited by 781
SuperSpike: Supervised Learning in Multilayer Spiking Neural Networks
Zenke, F., & Ganguli, S. (2018) · Neural Computation · doi:10.1162/neco_a_01086 · Cited by 515
Self-citationSLAYER: Spike Layer Error Reassignment in Time
Shrestha, S. B., & Orchard, G. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1810.08646 · Cited by 444
Towards deep learning with segregated dendrites
Guerguiev, J., Lillicrap, T. P., & Richards, B. A. (2017) · eLife · doi:10.7554/elife.22901 · Cited by 371
Supervised Learning Based on Temporal Coding in Spiking Neural Networks
Mostafa, H. (2017) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2017.2726060 · Cited by 331
Self-citationDirect Feedback Alignment Provides Learning in Deep Neural Networks
Nøkland, A. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1609.01596 · Cited by 275
Optimal Spike-Timing-Dependent Plasticity for Precise Action Potential Firing in Supervised Learning
Pfister, J.-P., Toyoizumi, T., Barber, D., & Gerstner, W. (2006) · Neural Computation · doi:10.1162/neco.2006.18.6.1318 · Cited by 245
Event-Driven Random Back-Propagation: Enabling Neuromorphic Deep Learning Machines
Neftci, E. O., Augustine, C., Paul, S., & Detorakis, G. (2017) · Frontiers in Neuroscience · doi:10.3389/fnins.2017.00324 · Cited by 237
Self-citationSupervised learning in spiking neural networks with FORCE training
Nicola, W., & Clopath, C. (2017) · Nature Communications · doi:10.1038/s41467-017-01827-3 · Cited by 211
Building functional networks of spiking model neurons
Abbott, L. F., DePasquale, B., & Memmesheimer, R.-M. (2016) · Nature Neuroscience · doi:10.1038/nn.4241 · Cited by 204
Spiking Deep Networks with LIF Neurons
Hunsberger, E., & Eliasmith, C. (2015) · arXiv (Cornell University) · doi:10.48550/arxiv.1510.08829 · Cited by 203
Deep Supervised Learning Using Local Errors
Mostafa, H., Ramesh, V., & Cauwenberghs, G. (2018) · Frontiers in Neuroscience · doi:10.3389/fnins.2018.00608 · Cited by 147
Self-citationLearning Precisely Timed Spikes
Memmesheimer, R.-M., Rubin, R., Ölveczky, B. P., & Sompolinsky, H. (2014) · Neuron · doi:10.1016/j.neuron.2014.03.026 · Cited by 145
Matching Recall and Storage in Sequence Learning with Spiking Neural Networks
Brea, J. M., Senn, W., & Pfister, J.-P. (2013) · Journal of Neuroscience · doi:10.1523/jneurosci.4098-12.2013 · Cited by 132
Event-driven random backpropagation: Enabling neuromorphic deep learning machines
Neftci, E. O., Augustine, C., Paul, S., & Detorakis, G. (2017) · IEEE International Symposium on Circuits and Systems proceedings · doi:10.1109/iscas.2017.8050529 · Cited by 118
Self-citationBellec, G., Scherr, F., Hajek, E., Salaj, D., Legenstein, R., & Maass, W. (2019) · TUGraz OPEN Library (Graz University of Technology) · doi:10.12751/nncn.bc2019.0013 · Cited by 115
Boahen, K. A. (2017) · Computing in Science & Engineering · doi:10.1109/mcse.2017.33 · Cited by 104
Predicting non-linear dynamics by stable local learning in a recurrent spiking neural network
Gilra, A., & Wulfram Gerstner, B. (2017) · eLife · doi:10.7554/elife.28295 · Cited by 100
Gütig, R. (2014) · Current Opinion in Neurobiology · doi:10.1016/j.conb.2014.01.004 · Cited by 93
A theory of local learning, the learning channel, and the optimality of backpropagation
Baldi, P., & Sadowski, P. (2016) · Neural Networks · doi:10.1016/j.neunet.2016.07.006 · Cited by 84
Stochastic variational learning in recurrent spiking networks
Rezende, D. J., & Wulfram Gerstner, B. (2014) · Frontiers in Computational Neuroscience · doi:10.3389/fncom.2014.00038 · Cited by 78
NormAD - Normalized Approximate Descent based supervised learning rule for spiking neurons
Anwani, N., & Rajendran, B. (2015) · doi:10.1109/ijcnn.2015.7280618 · Cited by 52
Error-Backpropagation in Networks of Fractionally Predictive Spiking Neurons
Bohté, S. M. (2011) · Lecture notes in computer science · doi:10.1007/978-3-642-21735-7_8 · Cited by 50
Learning Spatiotemporally Encoded Pattern Transformations in Structured Spiking Neural Networks
Brian, G., Sporea, I., & Grüning, A. (2015) · Neural Computation · doi:10.1162/neco_a_00790 · Cited by 49
A Learning Framework for Winner-Take-All Networks with Stochastic Synapses
Mostafa, H., & Cauwenberghs, G. (2018) · Neural Computation · doi:10.1162/neco_a_01080 · Cited by 14
Self-citationTemporally Efficient Deep Learning with SpikesPreprint
O'Connor, P., Gavves, E., & Welling, M. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1706.04159 · Cited by 13
Cited by
Opportunities for neuromorphic computing algorithms and applications
Schuman, C. D., Kulkarni, S. R., Parsa, M., Mitchell, J. P., Date, P., & Kay, B. (2022) · Nature Computational Science · doi:10.1038/s43588-021-00184-y · Cited by 1,117
“Some of the approaches that adapt deep learning-style training include using a surrogate gradient and having a smoothed activation function to compute the error gradients while performing weight adjustments in each of the successive layers 19,21 .”
MethodTraining Spiking Neural Networks Using Lessons From Deep Learning
Eshraghian, J. K., Ward, M., Neftci, E. O., Wang, X., Lenz, G., Dwivedi, G., Bennamoun, M., Jeong, D. S., & Lu, W. D. (2023) · Proceedings of the IEEE · doi:10.1109/jproc.2023.3308088 · Cited by 782
Self-citationAdvancing Neuromorphic Computing With Loihi: A Survey of Results and Outlook
Davies, M., Wild, A., Orchard, G., Sandamirskaya, Y., Guerra, G. A. F., Joshi, P., Plank, P., & Risbud, S. R. (2021) · Proceedings of the IEEE · doi:10.1109/jproc.2021.3067593 · Cited by 688
Embedded Devices for Neuromorphic Time-Series Assessment
Mazumder, A. N., Hosseini, M., & Mohsenin, T. (2022) · Research Explorer (The University of Manchester) · doi:10.13016/m2ksy0-wxr3 · Cited by 652
Incorporating Learnable Membrane Time Constant to Enhance Learning of Spiking Neural Networks
Fang, W., Yu, Z., Chen, Y., Masquelier, T., Huang, T., & Tian, Y. (2021) · 2021 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.00266 · Cited by 605
Metadata
- Authors
- Neftci, E. O., Mostafa, H., & Zenke, F.
- Venue
- IEEE Signal Processing Magazine
- Published
- 2019-11
- Volume
- 36
- Issue
- 6
- Pages
- 51-63
- ISSN
- 1053-5888 (ISSN-L)
- 1558-0792
- OpenAlex
- W2984844508
- Cited by
- 1,538
- References
- 35
- FWCI
- 28.90
- Type
- journal article
- Language
- en
- Open access
- closed
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.