An Introduction to Probabilistic Spiking Neural Networks: Probabilistic Models, Learning Rules, and Applications
Open accessThe DOI matches its Crossref record; 38 of the 38 references it cites were found in a registry or an index.
Abstract
Spiking neural networks (SNNs) are distributed trainable systems whose computing elements, or neurons, are characterized by internal analog dynamics and by digital and sparse synaptic communications. The sparsity of the synaptic spiking inputs and the corresponding event-driven nature of neural processing can be leveraged by energy-efficient hardware implementations, which can offer significant energy reductions as compared to conventional artificial neural networks (ANNs). The design of training algorithms for SNNs, however, lags behind hardware implementations: most existing training algorithms for SNNs have been designed either for biological plausibility or through conversion from pretrained ANNs via rate encoding.
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.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“Inspired by the dynamic spiking neurons in the human brain, the energy consumption and latency of edge AI can be significantly reduced by processing the learning tasks in an event-driven manner [62], [63].”
From Edge artificial intelligence for 6g: vision, enabling technologies, and applications (2022) · cites this paper as [62]
Experimental — accuracy not yet measured
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
Auto-Encoding Variational Bayes
Kingma, D. P., & Welling, M. (2013) · arXiv · doi:10.48550/arxiv.1312.6114 · Cited by 20,067 · cited 2×
“In terms of algorithms, the doubly stochastic SGD approach reviewed here for ML training can be extended and improved by leveraging an alternative estimator of the ELBO and its gradients with respect to the variational parameters that is known as the reparameterization trick [28].”
MethodLoihi: A Neuromorphic Manycore Processor with On-Chip Learning
Davies, M., Srinivasa, N., Lin, T.-H., Chinya, G., Cao, Y., Choday, S. H., Dimou, G., Joshi, P., Imam, N., Jain, S., et al. (2018) · IEEE Micro · doi:10.1109/mm.2018.112130359 · Cited by 3,897 · cited 11×
“The design of training algorithms for SNNs, however, lags behind hardware implementations: most existing training algorithms for SNNs have been designed either for biological plausibility or through conversion from pretrained ANNs via rate encoding.”
BackgroundInfluentialNetworks of spiking neurons: The third generation of neural network models
Maass, W. (1997) · Neural Networks · doi:10.1016/s0893-6080(97)00011-7 · Cited by 3,481 · cited 1×
“Inspired by this observation, as illustrated in Figure 1, SNNs have been introduced in the theoretical neuroscience literature as networks of dynamic spiking neurons [3].”
MethodSpiking Neuron Models: Single Neurons, Populations, Plasticity
Gerstner, W., & Kistler, W. M. (2002) · Cambridge University Press eBooks · doi:10.1017/cbo9780511815706 · Cited by 3,080
Bienenstock, E., Cooper, L., & Munro, P. (1982) · The Journal of Neuroscience · doi:10.1523/jneurosci.02-01-00032.1982 · Cited by 2,896 · cited 1×
“This update can be related to the standard spike-timingdependent plasticity (STDP) rule [10], [16], [25].”
BackgroundA database for handwritten text recognition research
Hull, J. J. (1994) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/34.291440 · Cited by 2,244 · cited 1×
“Batch learning examples As an example of batch learning, we consider the standard handwritten digit classification task on the USPS data set [35].”
MethodNeftci, E. O., Mostafa, H., & Zenke, F. (2019) · IEEE Signal Processing Magazine · doi:10.1109/msp.2019.2931595 · Cited by 1,538 · cited 1×
“When including loops, deterministic SNNs can also implement recurrent neural networks (RNNs) [20].”
BackgroundSpatio-temporal correlations and visual signalling in a complete neuronal population
Pillow, J. W., Shlens, J., Paninski, L., Sher, A., Litke, A. M., Chichilnisky, E. J., & Simoncelli, E. P. (2008) · Nature · doi:10.1038/nature07140 · Cited by 1,311 · cited 2×
“Examples of feedforward/feedback kernels: (a) an exponentially decaying feedforward kernel , at (b) an exponentially decaying feedback kernel , bt (c) raised cosine basis functions a , k t in [14], and (d) spike-timing-dependent plasticity basis functions a , k t for long-term potentiation (LTP) and longterm depressio…”
BackgroundSpatio-Temporal Backpropagation for Training High-Performance Spiking Neural Networks
Wu, Y., Deng, L., Li, G., Zhu, J., & Shi, L. (2018) · Frontiers in Neuroscience · doi:10.3389/fnins.2018.00331 · Cited by 1,196 · cited 1×
“To obviate this problem, a number of existing learning rules approximate the derivative by smoothing out the membrane potential as a function of the weights [7]–[9].”
BackgroundTraining 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 · cited 1×
“To obviate this problem, a number of existing learning rules approximate the derivative by smoothing out the membrane potential as a function of the weights [7]–[9].”
Background
Research works printed but not linked: 7
- dau, 2018, The UCR time series classification archive
- jang, 2019, An introduction to spiking neural networks Probabilistic models learning rules and applications [supplementary material]
- dayan, 2001, Theoretical Neuroscience Computational and Mathematical Modeling of Neural Systems
- eliasmith, 2004, Neural Engineering Computation Representation and Dynamics in Neurobiological Systems
- sutton, 2018, Reinforcement Learning An Introduction
- welling, 2018, Intelligence per kilowatt-hour
- goodfellow, 2016, Deep Learning
Cited by
Edge artificial intelligence for 6g: vision, enabling technologies, and applications
Letaief, K. B., Shi, Y., Lu, J., & Lu, J. (2022) · IEEE Journal on Selected Areas in Communications · doi:10.1109/jsac.2021.3126076 · Cited by 829
“Inspired by the dynamic spiking neurons in the human brain, the energy consumption and latency of edge AI can be significantly reduced by processing the learning tasks in an event-5 driven manner [62], [63].”
MethodAdvancing 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
“Applying methods from probabilistic signal processing, stochastic SNNs can be designed to tackle a variety of inference and learning problems that optimally leverage their time-coding capabilities [99].”
MethodMehonic, A., Sebastian, A., Rajendran, B., Simeone, O., Vasilaki, E., & Kenyon, A. J. (2020) · Advanced Intelligent Systems · doi:10.1002/aisy.202000085 · Cited by 331
Self-citationThe Heidelberg Spiking Data Sets for the Systematic Evaluation of Spiking Neural Networks
Cramer, B., Stradmann, Y., Schemmel, J., & Zenke, F. (2022) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2020.3044364 · Cited by 288
Green Edge AI: A Contemporary Survey
Mao, Y., Yu, X., Huang, K., Zhang, Y. A., & Zhang, J. (2024) · Proceedings of the IEEE · doi:10.1109/jproc.2024.3437365 · Cited by 184
“They differ from the conventional DNNs by encoding input as time series and using discrete spikes to transfer information between spiking neurons, each of which can fire a spike with sufficient input strength called membrane potential [298].”
BackgroundBrain-inspired global-local learning incorporated with neuromorphic computing
Wu, Y., Zhao, R. J., Zhu, J., Chen, F., Xu, M., Li, G., Song, S., Deng, L., Wang, G., Zheng, H., et al. (2022) · Nature Communications · doi:10.1038/s41467-021-27653-2 · Cited by 151
“Some works explored the three-factor learning rules in a spiking probabilistic framework to approximate bio-plausible inference and learning solutions 14-17 .”
BackgroundA Survey on Collaborative DNN Inference for Edge Intelligence
Ren, W., Qu, Y., Dong, C., Jing, Y., Sun, H., Wu, Q., & Guo, S. (2023) · Machine Intelligence Research · doi:10.1007/s11633-022-1391-7 · Cited by 137
“In a nutshell, compared to singlenode inference, multi-node collaborative inference can bring many potential benefits to the landing of EI, including lower latency and bandwidth pressure, broader application scenarios, lower energy consumption and equipment rental cost, and agile task scheduling strategies and resourc…”
BackgroundBrain-Inspired Learning on Neuromorphic Substrates
Zenke, F., & Neftci, E. (2021) · Proceedings of the IEEE · doi:10.1109/jproc.2020.3045625 · Cited by 135
“n-differential nature of spiking neurons [20, 66–68]. The most commonly used gradient-based SNN learning paradigms are network translation [69– 72], variational learning with stochastic neuron models [13, 23, 73, 74], and surrogate gradients in combination with deterministic Linear Integrate and Fire (LIF) neurons [15…”
MethodA surrogate gradient spiking baseline for speech command recognition
Bittar, A., & Garner, P. N. (2022) · Frontiers in Neuroscience · doi:10.3389/fnins.2022.865897 · Cited by 135
Learning rules in spiking neural networks: A survey
Yi, Z., Lian, J., Liu, Q., Zhu, H., Liang, D., & Liu, J. (2023) · Neurocomputing · doi:10.1016/j.neucom.2023.02.026 · Cited by 125
Advancements in Algorithms and Neuromorphic Hardware for Spiking Neural Networks
Javanshir, A., Nguyen, T. T., Mahmud, M. A. P., & Kouzani, A. Z. (2022) · Neural Computation · doi:10.1162/neco_a_01499 · Cited by 116
“For this reason, the inference performance of the SNNs is typically lower than that of the original ANNs (Pfeiffer & Pfeil, 2018).”
MethodInfluentialWang, C., Li, Y., Wang, Y., Xu, X., Fu, M., Liu, Y., Lin, Z., Ling, H., Gkoupidenis, P., Yi, M., et al. (2021) · Journal of Materials Chemistry C · doi:10.1039/d1tc01660a · Cited by 80
Neuromorphic Wireless Cognition: Event-Driven Semantic Communications for Remote Inference
Chen, J., Skatchkovsky, N., & Simeone, O. (2023) · IEEE Transactions on Cognitive Communications and Networking · doi:10.1109/tccn.2023.3236940 · Cited by 80
“Spiking neurons communicate and process with the timings of spikes [14].”
BackgroundSelf-citationBrain-Inspired Computing: Models and Architectures
Parhi, K. K., & Unnikrishnan, N. K. (2020) · IEEE Open Journal of Circuits and Systems · doi:10.1109/ojcas.2020.3032092 · Cited by 65
“(12) representing a spike response model (SRM) [57], [58] in the discreet time-space.”
BackgroundExploiting noise as a resource for computation and learning in spiking neural networks
Ma, G., Yan, R., & Tang, H. (2023) · Patterns · doi:10.1016/j.patter.2023.100831 · Cited by 59
Neuromorphic Integrated Sensing and Communications
Chen, J., Skatchkovsky, N., & Simeone, O. (2022) · IEEE Wireless Communications Letters · doi:10.1109/lwc.2022.3231388 · Cited by 56
“We refer to [18], [19] for further details.”
BackgroundSelf-citationFederated Neuromorphic Learning of Spiking Neural Networks for Low-Power Edge Intelligence
Skatchkovsky, N., Jang, H., & Simeone, O. (2020) · ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) · doi:10.1109/icassp40776.2020.9053861 · Cited by 35
“When summed over the available data set, the logloss can be optimized as a learning criterion via SGD [5].”
BackgroundMethodInfluentialSelf-citationLearning with Limited Samples: Meta-Learning and Applications to Communication Systems
Chen, L., Jose, S. T., Nikoloska, I., Park, S., Chen, T., & Simeone, O. (2023) · Foundations and Trends® in Signal Processing · doi:10.1561/2000000115 · Cited by 46
Self-citationBayesian continual learning via spiking neural networks
Skatchkovsky, N., Jang, H., & Simeone, O. (2022) · Frontiers in Computational Neuroscience · doi:10.3389/fncom.2022.1037976 · Cited by 44
“An alternative approach, reviewed in Jang et al. (2019), is to view the SNN as a probabilistic model whose likelihood can be directly differentiated.”
BackgroundSelf-citationLi, Y., Zhao, D., & Zeng, Y. (2022) · Frontiers in Neuroscience · doi:10.3389/fnins.2022.991851 · Cited by 40
“Therefore, the spiking neural network, known as the third-generation artificial neural network (Maass, 1997), has received more and more attention (Bing et al., 2018; Illing et al., 2019; Jang et al., 2019; Tavanaei et al., 2019; Wang et al., 2020).”
BackgroundElucidating the Theoretical Underpinnings of Surrogate Gradient Learning in Spiking Neural Networks
Gygax, J., & Zenke, F. (2025) · Neural Computation · doi:10.1162/neco_a_01752 · Cited by 34
End-to-End Learning of Neuromorphic Wireless Systems for Low-Power Edge Artificial Intelligence
Skatchkovsky, N., Jang, H., & Simeone, O. (2020) · Asilomar Conference on Signals, Systems and Computers (ACSSC) · doi:10.1109/ieeeconf51394.2020.9443351 · Cited by 34
“Furthermore, in order to overcome the difficulties due to the non-differentiability of the activation function of deterministic SNN models [17], we focus on a probabilistic implementation of SNNs [11].”
BackgroundMethodSelf-citationNeuromorphic Sentiment Analysis Using Spiking Neural Networks
Chunduri, R. K., & Perera, D. G. (2023) · Sensors · doi:10.3390/s23187701 · Cited by 33
“Unlike traditional neural networks that rely on continuous-valued signals, the SNNs work in continuous time [8].”
BackgroundA hierarchical taxonomic survey of spiking neural networks
Wang, S., Cheng, T. H., & Lim, M. H. (2022) · Memetic Computing · doi:10.1007/s12293-022-00373-w · Cited by 31
“In this respect, SNN neurons are different from those in ANN since they are dynamic rather than non-linearly static [31].”
BackgroundZecchin, M., Park, S., & Simeone, O. (2024) · IEEE Journal on Selected Areas in Information Theory · doi:10.1109/jsait.2024.3368229 · Cited by 31
“Examples include time-GANs [57], diffusion models [58], recurrent neural networks with a probabilistic interpretation of the output [59], and probabilistic spiking neural networks [60], [61].”
BackgroundSelf-citationA Survey of Artificial Neural Network Computing Systems
Foukalas, F. T. (2024) · Cognitive Computation · doi:10.1007/s12559-024-10383-0 · Cited by 30
“TheideabehindthisisthatneuronsinSNNsdonotfireateach propagation cycle (like in other ANN categories), but rather only when a membrane potential reaches a specific threshold value [36].”
Spiking Neural Networks—Part II: Detecting Spatio-Temporal Patterns
Skatchkovsky, N., Jang, H., & Simeone, O. (2021) · IEEE Communications Letters · doi:10.1109/lcomm.2021.3050242 · Cited by 29
“As a remark, in GLMs, it is common to associate each synapse with multiple spike responses and corresponding weights, allowing to learn distinct temporal receptive fields across the spiking neurons [11], [13].”
BackgroundSelf-citationRosenfeld, B., Simeone, O., & Rajendran, B. (2022) · IEEE Transactions on Computers · doi:10.1109/tc.2022.3191738 · Cited by 28
“The gradient of the log likelihood of neuron outputs is central to the optimization and is derived as in [4]”
BackgroundMethodInfluentialSelf-citationBiSNN: Training Spiking Neural Networks with Binary Weights via Bayesian Learning
Jang, H., Skatchkovsky, N., & Simeone, O. (2021) · IEEE Data Science Workshop (DSW) · doi:10.1109/dslw51110.2021.9523415 · Cited by 26
Self-citationNeuromorphic Split Computing With Wake-Up Radios: Architecture and Design via Digital Twinning
Chen, J., Park, S., Popovski, P., Poor, H. V., & Simeone, O. (2024) · IEEE Transactions on Signal Processing · doi:10.1109/tsp.2024.3463210 · Cited by 24
“N EUROMORPHIC processing units (NPUs), such as Intel’s Loihi or BrainChip’s Akida, leverage the sparsity of temporal data to reduce processing energy by activating a small subset of neurons and synapses at each time step [1], [2].”
MethodSelf-citationEfficient asynchronous federated neuromorphic learning of spiking neural networks
Wang, Y., Duan, S., & Chen, F. (2023) · Neurocomputing · doi:10.1016/j.neucom.2023.126686 · Cited by 23
Neuromorphic Accelerator for Spiking Neural Network Using SOT-MRAM Crossbar Array
Verma, G., Nisar, A., Dhull, S., & Kaushik, B. K. (2023) · IEEE Transactions on Electron Devices · doi:10.1109/ted.2023.3317357 · Cited by 23
“The computational ability in terms of area and energy efficiency of the biological brain arises from the use of highly parallel and sparse spike-based real-time information processing [1].”
BackgroundKnowing When to Stop: Delay-Adaptive Spiking Neural Network Classifiers With Reliability Guarantees
Chen, J., Park, S., & Simeone, O. (2024) · IEEE Journal of Selected Topics in Signal Processing · doi:10.1109/jstsp.2024.3431996 · Cited by 22
“Another approach that targets the direct training of SNNs is based on modelling the spiking mechanism as a stochastic process, which enables the use of likelihood-based methods [13], as well as of Bayesian rules [14].”
Self-citationAntiferromagnet-Based Neuromorphics Using Dynamics of Topological Charges
Zhang, S., & Tserkovnyak, Y. (2020) · Physical Review Letters · doi:10.1103/physrevlett.125.207202 · Cited by 22
Multisample Online Learning for Probabilistic Spiking Neural Networks
Jang, H., & Simeone, O. (2022) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2022.3144296 · Cited by 21
Self-citationFederated Learning with Spiking Neural Networks in Heterogeneous Systems
Tumpa, S. A., Singh, S., Khan, M. F. F., Kandemir, M. T., Narayanan, V., & Das, C. R. (2023) · IEEE Computer Society Annual Symposium on VLSI · doi:10.1109/isvlsi59464.2023.10238618 · Cited by 19
“the single-SNN learning rule in [15] for probabilistic SNNs.”
BackgroundJang, H., Skatchkovsky, N., & Simeone, O. (2021) · Proceedings - International Conference on Pattern Recognition/Proceedings/International Conference on Pattern Recognition · doi:10.1109/icpr48806.2021.9413206 · Cited by 18
“In this section, we introduce the operational principles of SNNs and the key definitions, and review the online local variational training rules derived in [16], [17], [18] for conventional SNNs (not including WTA circuits).”
BackgroundMethodInfluentialSelf-citationA Survey on Spiking Neural Networks
Han, C. S., & Lee, K. M. (2021) · International Journal of Fuzzy Logic and Intelligent Systems · doi:10.5391/ijfis.2021.21.4.317 · Cited by 18
Anti-interference of a small-world spiking neural network against pulse noise
Guo, L., Song, Y., Wu, Y., & Xu, G. (2022) · Applied Intelligence · doi:10.1007/s10489-022-03804-w · Cited by 18
“The SNN has been necessary theory and model foundation of computational neuroscience since it can reflect the electrophysiological activity of nerves [4–7].”
MethodLearning to Time-Decode in Spiking Neural Networks Through the Information BottleneckPreprint
Skatchkovsky, N., Simeone, O., & Jang, H. (2021) · Research Portal (King's College London) · doi:10.48550/arxiv.2106.01177 · Cited by 18
“For the readout neurons, this can be directly done as [4] ∇we ij log pwe i (yi,t = 1|ui,t) = ( αt ∗ zj,t )( yi,t − σ(ui,t) ) = eij,t, (19) where we recall that zj,t is the spiking signal of pre-synaptic neuron j.”
BackgroundMethodInfluentialSelf-citationTowards efficient and reliable artificial intelligence through neuromorphic principles
Rajendran, B., Simeone, O., & Al‐Hashimi, B. M. (2026) · Philosophical Transactions of the Royal Society A Mathematical Physical and Engineering Sciences · doi:10.1098/rsta.2024.0522 · Cited by 17
Self-citationSpiking Neural Networks—Part III: Neuromorphic Communications
Skatchkovsky, N., Jang, H., & Simeone, O. (2021) · IEEE Communications Letters · doi:10.1109/lcomm.2021.3050212 · Cited by 14
“Mathematically, in a manner similar to FL-SNN, NeuroJSCC tackles the problem of minimizing the training log-loss [20] ≤ T produced by the hidden neurons of encoder and decoder, as well as the channel’s inputs and outputs x ≤ T and y ≤ T as To address problem (8), as in the derivation of the…”
MethodSelf-citationA neuromorphic approach to obstacle avoidance in robot manipulation
Abdelrahman, A. F., Valdenegro-Toro, M., Bennewitz, M., & Plöger, P. G. (2024) · The International Journal of Robotics Research · doi:10.1177/02783649241284058 · Cited by 14
“…of neuronal dynamics have been employed in SNN research to produce a variety of neuron models, including the Hodgkin-and-Huxley model (Hodgkin and Huxley, 1952), Spike Response Model (SRM) (Gerstner, 1995), Izhikevich model (Izhikevich, 2003), and various probabilistic models (Jang et al., 2019).”
Neuromorphic Event-Driven Semantic Communication in Microgrids
Diao, X., Song, Y., Sahoo, S., & Li, Y. (2024) · IEEE Transactions on Smart Grid · doi:10.1109/tsg.2024.3370822 · Cited by 14
“Unlike the next generation artificial neural networks (ANN), which always utilizes real valued samples for learning and inferences, SNN simply compute using binary spikes to excite a change in its corresponding weights by governing local dynamics [18].”
BackgroundTraining Spiking Neural Networks with Metaheuristic Algorithms
Javanshir, A., Nguyen, T. T., Mahmud, M. A. P., & Kouzani, A. Z. (2023) · Applied Sciences · doi:10.3390/app13084809 · Cited by 13
Fast On-Device Adaptation for Spiking Neural Networks Via Online-Within-Online Meta-Learning
Rosenfeld, B., Rajendran, B., & Simeone, O. (2021) · IEEE Data Science Workshop (DSW) · doi:10.1109/dslw51110.2021.9523405 · Cited by 12
Self-citationA Construction Kit for Efficient Low Power Neural Network Accelerator Designs
Jokic, P., Azarkhish, E., Bonetti, A., Pons, M., Emery, S., & Benini, L. (2022) · ACM Transactions on Embedded Computing Systems · doi:10.1145/3520127 · Cited by 11
A Reversible-Logic based Architecture for Artificial Neural Network
Dey, B., Khalil, K., Kumar, A., & Bayoumi, M. (2020) · IEEE International Midwest Symposium on Circuits and Systems (MWSCAS) · doi:10.1109/mwscas48704.2020.9184662 · Cited by 11
A Review of Recent Advances and Application for Spiking Neural Networks
Liu, H., Chai, H., Sun, Q., Yun, X., & Li, X. (2023) · Strategic Study of CAE · doi:10.15302/j-sscae-2023.06.011 · Cited by 10
Ren, P., Wang, Y., Wang, Z., Peng, D., Liu, C., & Han, T. (2025) · Advanced Engineering Informatics · doi:10.1016/j.aei.2025.103273 · Cited by 9
Bayesian Inference on Binary Spiking Networks Leveraging Nanoscale Device Stochasticity
Katti, P., Skatchkovsky, N., Simeone, O., Rajendran, B., & Al‐Hashimi, B. M. (2023) · IEEE International Symposium on Circuits and Systems proceedings · doi:10.1109/iscas46773.2023.10181438 · Cited by 9
“Spiking Neural Networks (SNNs) [13] have been widely investigated for their energy efficiency, with hardware implementations ranging from digital to mixed-signal IMC plat-”
BackgroundSelf-citationSupervised Learning With First-to-Spike Decoding in Multilayer Spiking Neural Networks
Brian, G., & Grüning, A. (2021) · Frontiers in Computational Neuroscience · doi:10.3389/fncom.2021.617862 · Cited by 9
“A variational, online learning rule for training recurrent SNNs has also recently been proposed in Jang et al. (2020); a detailed review of probabilistic learning methods can be found in Jang et al. (2019).”
BackgroundA Brief Review on Spiking Neural Network - A Biological InspirationPreprint
Rafi, T. H. (2021) · Preprints.org · doi:10.20944/preprints202104.0202.v1 · Cited by 9
“However, it can process the encoded data according to the event of time [6].”
BackgroundMotion feature extraction using magnocellular-inspired spiking neural networks for drone detection
Zheng, J., Wan, Y., Yang, X. P. O., Hua, Z., Du, M., & Wang, G. (2025) · Frontiers in Computational Neuroscience · doi:10.3389/fncom.2025.1452203 · Cited by 8
Azmine, M. F., Li, R., Sharma, G., & Yi, Y. (2025) · IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems · doi:10.1109/tcad.2025.3543439 · Cited by 8
Advances in Neuromorphic Spin-Based Spiking Neural Networks: A review
Verma, G., Bindal, N., Nisar, A., Dhull, S., & Kaushik, B. K. (2021) · IEEE Nanotechnology Magazine · doi:10.1109/mnano.2021.3098219 · Cited by 8
Fono, A., Singh, M., Araya, E., Petersen, P., Boche, H., & Kutyniok, G. (2026) · IEEE Signal Processing Magazine · doi:10.1109/msp.2025.3597033 · Cited by 8
“…LIF SNNs with rate coding can approximate the realization of feedforward (and with minor modifications also of recurrent) ANNs with a nonnegative activation function of the same spatial topology to an arbitrary degree, in particular, with increasing accuracy in the number of time steps T [14].”
Artificial intelligence-based spatio-temporal vision sensors: applications and prospects
Li, Z., & Sun, H. (2023) · Frontiers in Materials · doi:10.3389/fmats.2023.1269992 · Cited by 7
Symmetric Linear Rise and Fall of Conductance in a Trilayer Stack Engineered ReRAM-Based Synapse
Vishwakarma, K., Kishore, R., & Datta, A. (2020) · ACS Applied Electronic Materials · doi:10.1021/acsaelm.0c00585 · Cited by 7
Performance Comparison of Deep Spiking CNN with Artificial Deep CNN for Image Classification Tasks
Kalbande, M., & Bhavsar, P. (2022) · IEEE Region 10 Symposium (TENSYMP) · doi:10.1109/tensymp54529.2022.9864551 · Cited by 7
“model specifies differentiable output loss also allows for direct development of learning algorithms employing principled learning criteria without the use of backpropagation techniques [6][7].”
MethodKröger, B. J. (2023) · Journal of Integrative Neuroscience · doi:10.31083/j.jin2205124 · Cited by 6
“[38]); first- and second-generation neural networks are typically favored for simulating learning and these types of neural networks are mainly used for modeling speech acquisition (c.”
BackgroundAgreeing to Stop: Reliable Latency-Adaptive Decision Making via Ensembles of Spiking Neural Networks
Chen, J., Park, S., & Simeone, O. (2024) · Entropy · doi:10.3390/e26020126 · Cited by 6
“Unlike methods based on conventional neural networks, such as transformers, spiking neural networks (SNNs) process time series with the prime objective of optimizing energy efficiency, particularly in the presence of sparse inputs [1–3].”
MethodSelf-citationNeuromorphic Wireless Split Computing With Resonate-and-Fire Neurons
Wu, D., Chen, J., Poor, H. V., Rajendran, B., & Simeone, O. (2026) · IEEE Transactions on Cognitive Communications and Networking · doi:10.1109/tccn.2026.3704603 · Cited by 5
“Traditional deep neural network (DNN) accelerators, designed primarily for batch processing, are often ill-suited to continuous, always-on time-series tasks due to their high power consumption.”
Self-citationStochastic Quantum Spiking Neural Networks With Quantum Memory and Local Learning
Chen, J., Rajendran, B., & Simeone, O. (2026) · IEEE Journal on Selected Areas in Communications · doi:10.1109/jsac.2026.3714333 · Cited by 5
“The number of pre-synaptic neurons for neuron i is thus Following the literature on neuromorphic systems (see, e.g., [19], [37]), we partition the SQS neurons in the SQSNN into two disjoint subsets: the subset O of output neurons and the subset H of hidden neurons, with S = O ∪ H .”
InfluentialSelf-citationAI-native robotic vision systems enabled by in-sensor computing
Kim, D., Kwon, J. I., Kim, Y., Kim, D., & Choi, C. (2026) · npj Unconventional Computing · doi:10.1038/s44335-025-00047-z · Cited by 5
Survey of Neuromorphic Computing: A Data Science Perspective
Clark, K., & Wu, Y. (2023) · International Conference on Computer Communication and Artificial Intelligence (CCAI) · doi:10.1109/ccai57533.2023.10201289 · Cited by 5
“nal during the training phase [29] [34] [35].”
BackgroundA generalized neural tangent kernel for surrogate gradient learning
Eilers, L., Memmesheimer, R.-M., & Goedeke, S. (2024) · neural information processing systems · doi:10.52202/079017-0287 · Cited by 5
Neuromorphic Wireless Device-Edge Co-Inference via the Directed Information Bottleneck
Ke, Y., Utkovski, Z., Heshmati, M., Simeone, O., Dommel, J., & Stańczak, S. (2024) · International Conference on Neuromorphic Systems (ICONS) · doi:10.1109/icons62911.2024.00011 · Cited by 5
“The dynamic evolution of the membrane potential u i,t is modeled as [8] where w j,i is the synaptic weight from neuron j to i , w i is a feedback weight, and γ i is a bias parameter.”
BackgroundMethodInfluentialSelf-citationALSA: Associative Learning Based Supervised Learning Algorithm for SNN
Mo, L., Wang, G., Long, E., & Zhuo, M. (2022) · Frontiers in Neuroscience · doi:10.3389/fnins.2022.838832 · Cited by 4
“More details of probabilistic SNN can be found in Jang et al. (2019), which reviews probabilistic models and training methods based on a probabilistic signal processing framework.”
BackgroundAsymptotically Optimal Nonparametric Classification Rules for Spike Train Data
Pawlak, M., Pabian, M., & Rzepka, D. (2023) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp49357.2023.10096060 · Cited by 4
“Probabilistic spiking neural networks have been introduced [2], [5] for supervised and unsupervised learning problems.”
BackgroundMethodEvent-Driven Sensing and Embedded Neuromorphic Platforms for Gamma Radiation Monitoring
Witherspoon, B., & Young, A. R. (2024) · ACM Great Lakes Symposium on VLSI (GLSVLSI) · doi:10.1145/3649476.3660363 · Cited by 4
“A potential approach to training this network could be to take advantage of information-theoretic loss functions with sparsity promoting regularization [4].”
BackgroundModern Neuromorphic AI: From Intra-Token to Inter-Token ProcessingPreprint
Simeone, O. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2601.00245 · Cited by 4
“More constrained forms of time encoding, e.g., based on first-to-spike time encoding or relative-timing encoding, have a generally lower capacity [12], [45] (see the top-right panel of Figure 7 for an illustration of first-to-spike encoding).”
Self-citationProbabilistic Spiking Neural Networks Training with Expectation - Propagation
Shen, D., Yao, D., McLaughlin, S., & Altmann, Y. (2023) · IEEE International Workshop on Computational Advances in Multi-Sensor Adaptive Processing · doi:10.1109/camsap58249.2023.10403446 · Cited by 3
“In this work, we consider a sub-class of SNNs, referred to as probabilistic SNNs (PSNNs), where in contrast to deterministic SNNs, the activation function of each neuron produces random (binary) outputs [2].”
BackgroundMethodInfluentialFPGA Implementation of an Artificial Intelligence Signal Recognition System
Rana, A., & Kim, K. K. (2022) · Journal of Sensor Science and Technology · doi:10.46670/jsst.2022.31.1.16 · Cited by 3
How AI Can Help Avoid Catastrophic Overload of Healthcare System in Times of a Worldwide Pandemic
Nagele, J., & Thamm, A. (2022) · Management for professionals · doi:10.1007/978-3-030-98764-0_5 · Cited by 3
Address-Event Variable-Length Compression for Time-Encoded Data
Jose, S. T., & Simeone, O. (2020) · Research Portal (King's College London) · doi:10.48550/arxiv.2001.02527 · Cited by 3
“This is done by maximizing the training set log-likelihood, where the likelihood of each sequence is given by (17), via gradient descent log-likelihood estimation [27].”
MethodSelf-citationSpiking Variational Graph Auto-Encoders for Efficient Graph Representation LearningPreprint
Yang, H., Zhang, R., Kong, Q., & Mao, W. (2022) · arXiv (Cornell University) · doi:10.48550/arxiv.2211.01952 · Cited by 3
“Probabilistic LIF Model Inspired by the spike response model (SRM) with stochastic threshold (Jang et al. 2019), we propose the probabilistic LIF model to generate binary latent variables z tn,c from a Bernoulli Process, i.e., Conditioned on the spiking history, the difference between the membrane…”
MethodToward stochastic neural computingPreprint
Yang, Q., Zhu, Z., Wei, Y., Cao, L., Wang, Z., Zhang, J., Lu, W., & Feng, J. (2023) · arXiv (Cornell University) · doi:10.48550/arxiv.2305.13982 · Cited by 3
“By modeling spike generation as a Bernoulli process with firing probability depending on the neuron’s input, it has been shown that a three-factor learning rule can be recovered from a probability learning objective 31 .”
BackgroundMethodInfluentialBayes Risk Consistency of Nonparametric Classification Rules for Spike Trains DataPreprint
Pawlak, M., Pabian, M., & Rzepka, D. (2023) · arXiv (Cornell University) · doi:10.48550/arxiv.2308.04796 · Cited by 3
Training of Spiking Neural Networks with Expectation-PropagationPreprint
Yao, D., McLaughlin, S., & Altmann, Y. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2506.23757 · Cited by 3
“These options correspond to classical deterministic SNNs (with Heaviside activation) and probabilistic SNNs [17], respectively.”
Neuromorphic Semantic Communications with Wake-Up Radios
Chen, J., Park, S., Popovski, P., Poor, H. V., & Simeone, O. (2024) · IEEE International Workshop on Signal Processing Advances in Wireless Communications (SPAWC) · doi:10.1109/spawc60668.2024.10694141 · Cited by 2
“Motivation : Neuromorphic processing units (NPUs), such as Intel’s Loihi or BrainChip’s Akida, leverage the sparsity of temporal data to reduce processing energy by activating a small subset of neurons and synapses at each time step [1, 2].”
BackgroundSelf-citationPoC Implementation of Neuromorphic Wireless Cognition: Gesture Recognition for Robotic Control
Ke, Y., Heshmati, M., Utkovski, Z., Dommel, J., & Stańczak, S. (2024) · IEEE International Conference on Machine Learning for Communication and Networking (ICMLCN) · doi:10.1109/icmlcn59089.2024.10624692 · Cited by 2
“In neuromorphic computing, processing is performed by employing spiking neural networks (SNNs), which are networks of dynamic spiking neurons that communicate and process with the timings of spikes (mimicking the operation of biological neurons [4]).”
MethodNeuromorphic Computing for IoT: Ultra-Low Power AI for Real-Time Intelligence
Kundu, S. (2024) · International Journal For Multidisciplinary Research · doi:10.36948/ijfmr.2024.v06i06.40671 · Cited by 2
“These chips can take advantage of existing digital design tools and manufacturing processes, making them easier to integrate into current IoT ecosystems [11].”
A Biologically Inspired Attention Model for Neural Signal AnalysisPreprint
Skatchkovsky, N., Glazman, N., Egea-Weiss, A., Sadeh, S., & Iacaruso, M. F. (2024) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2024.08.13.607787 · Cited by 2
“Alternatively, one can use an RNN or a probabilistic SNN [62] to With such a network, we use a standard variational inequality [60] to lower bound the decoder log-likelihood Averaging over time-steps, we obtain the variational predictive likelihood where 𝒘 = (𝒘 7 , 𝒘 𝒅 ) , that we maximise via…”
A Convolutional Neural Network to Spiking Neural Network Conversion Framework for Seismic Denoising
Chen, S., Liu, Z., Qin, Z., Liu, X., Xue, Y., & Cao, J. (2025) · IEEE Access · doi:10.1109/access.2025.3617570 · Cited by 1
“This mechanism enables significant reduction in computational energy consumption when processing data with high temporal redundancy, such as in computer vision and signal processing [3] and [14].”
Guo, R., Li, R., Ding, J., Wen, L., Zhang, Y., Wen, C., & Jiao, M. (2026) · Microchemical Journal · doi:10.1016/j.microc.2026.118008 · Cited by 1
“SNNs closely resemble biological olfactory information processing methods by using event-driven discrete spiking signals for information transfer [31].”
Spike neuron optimization using deep reinforcement learning
Hui, T. S., & Ishak, M. K. (2021) · IAES International Journal of Artificial Intelligence · doi:10.11591/ijai.v10.i1.pp175-183 · Cited by 1
“Spikes are sequences of action potential that is used in signal transmission in spike neurons [5].”
BackgroundJang, H., & Simeone, O. (2021) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp39728.2021.9414804 · Cited by 1
Self-citationLearning Spiking Neural Network from Easy to Hard Task
Tang, L., Hu, J., Hua, Y., Liu, S., & Chu, J. (2023) · International Conference on Digital Society and Intelligent Systems (DSInS) · doi:10.1109/dsins60115.2023.10455649 · Cited by 1
“and information processing of neurons to better approximate the functioning principles of the biological brain [1], [2].”
BackgroundВикторович, С. С., Lebedev, A. A., Levanova, T. A., & Kazantsev, V. (2024) · International Conference Neurotechnologies and Neurointerfaces (CNN) · doi:10.1109/cnn63506.2024.10705826 · Cited by 1
“It is worth noting that spiking neural networks have higher computational efficiency, more powerful capabilities for processing spatiotemporal information, better biointerpretability, and promise energy-efficient hardware implementations compared to classical neural networks [37]– [39].”
BackgroundStabilizing sequence learning in stochastic spiking networks with GABA-Modulated STDP
Vieth, M., & Triesch, J. (2024) · Neural Networks · doi:10.1016/j.neunet.2024.106985 · Cited by 1
Screening the Bioactivity of the P450 Enzyme by Spiking Neural Networks
Nascimben, M., & Rimondini, L. (2025) · Lecture notes in computer science · doi:10.1007/978-3-031-90714-2_20 · Cited by 1
SpinAPS: A High-Performance Spintronic Accelerator for Probabilistic Spiking Neural NetworksPreprint
Babu, A. V., Simeone, O., & Rajendran, B. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2008.02189 · Cited by 1
“Such definitions help in applying maximum likelihood criteria and then derive flexible learning rules without requiring back-propagation mechanisms, conversions or other approximations from pre-trained ANNs [3].”
BackgroundMethodSelf-citationMulti-Compartment Variational Online Learning for Spiking Neural Networks.Preprint
Jang, H., & Simeone, O. (2020) · arXiv (Cornell University)
Self-citationMiranda, E. R. (2022) · Springer series on cultural computing · doi:10.1007/978-3-031-10960-7_13
Deep Image Clustering by Spiking Neural Networks
Mahyari, A., & Aliakbarpour, H. (2023) · IEEE Applied Imagery Pattern Recognition Workshop · doi:10.1109/aipr60534.2023.10440717
Bio Inspired Approach on Automatic License Plate Recognition Technique
Mahalakshmi, S., & Dheeba, J. (2024) · Salud Ciencia y Tecnología - Serie de Conferencias · doi:10.56294/sctconf2024698
Impacts of Parasitic Effects on PCM-based Neuromorphic Circuits Under Advanced Technology Nodes
Zhu, X., Peng, B., Ding, F., Xie, Z., Chen, Y., & Zhang, L. (2024) · International Symposium of Electronics Design Automation (ISEDA) · doi:10.1109/iseda62518.2024.10617774
“Spiking neural networks (SNNs) are brain-inspired algorithms and can save more memory and power than DNN, the preceding generation of neural networks [1][2].”
BackgroundEvaluación de un sistema de identificación de fluctuaciones (estado ON/OFF) en enfermos de Parkinson
Barrachina, M. (2024) · UPM Digital Archive (Technical University of Madrid) · doi:10.20868/upm.thesis.81685
Metadata
- Authors
- Jang, H., Simeone, O., Gardner, B., & Gruning, A.
- Affiliations
- King's College London (GB)
- University of Surrey (GB)
- Venue
- IEEE Signal Processing Magazine
- Published
- 2019-11
- Volume
- 36
- Issue
- 6
- Pages
- 64-77
- ISSN
- 1053-5888 (ISSN-L)
- 1558-0792
- OpenAlex
- W2985873131
- Cited by
- 101
- References
- 35
- Citations by year
- 2026: 8 · 2025: 12 · 2024: 21 · 2023: 19 · 2022: 16 · 2021: 18 · 2020: 7
- FWCI
- 3.68
- Type
- journal article
- Language
- en
- Open access
- green
- kclpure.kcl.ac.uk
- Licence
- Locations
- IEEE Signal Processing Magazine (publishedVersion)
- Research Portal (King's College London) (publishedVersion, other-oa)
- arXiv (Cornell University) (acceptedVersion)
- arXiv (Cornell University)
- Funders
- European Union Horizon 2020 (725731)
- U.S. National Science Foundation (1710009)
- European Union Horizon 2020 Framework Programme (785907 (Human Brain Project SGA2))
- Topics
- Physical Sciences › Engineering › Electrical and Electronic Engineering › Advanced Memory and Neural Computing
- Life Sciences › Neuroscience › Cognitive Neuroscience › Neural dynamics and brain function
- Physical Sciences › Computer Science › Artificial Intelligence › Neural Networks and Applications
- Keywords
- spiking neural networks, probabilistic models, learning rules, energy-efficient hardware, event-driven computing, training algorithms, biological plausibility, neuromorphic computing
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.