Abstract
Artificial Neural Networks (ANN) have become one of the most powerful machine learning tools that cover a wide range of applications such as surveillance, video and image recognition, medical image analysis, control systems, robotics, bioinformatics, etc. These wide applications have encouraged researchers to search for more realistic neuron models that really mimic human biological neurons. Recent neurological research explored a set of new characteristics of biological neurons which led to generating the third-generation neural networks called Spiking Neural Networks (SNN). SNNs are more faithful to drawing biological properties which makes them energy-efficient and fast with higher processing capability. Many SNN models along with various learning algorithms have been proposed in the last decade to explore fast and efficient machine learning applications. In this paper, we have reviewed recent advancements in SNN architectures, their learning algorithms, applications, advantages, limitations and future scopes. We have also presented a brief comparison among some well-cited state-of-the-art works in terms of performance, advantages and limitations.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Abbott LF (1999) Lapicque’s introduction of the integrate-and-fire model neuron (1907). Brain Res Bull 50:303–304
Amit DJ, Brunel N, Tsodyks M (1994) Correlations of cortical Hebbian reverberations: theory versus experiment. J Neurosci 14(11):6435–6445
Bi G, Poo M (1998) Synaptic modifications in cultured hippocampal neurons: dependence on spike timing, synaptic strength, and postsynaptic cell type. J Neurosci 18(24):10464–10472
Brette R, Gerstner W (2005) Adaptive exponential integrate-and-fire model as an effective description of neuronal activity. J Neurophysiol 94:3637–3642. https://doi.org/10.1152/jn.00686.2005
Dayan P, Abbott LF (2005) Theoretical neuroscience: computational and mathematical modeling of neural systems. MIT Press
Diehl PU, Neil D, Binas J, Cook M, Liu SC, Pfeiffer M (2015) Fast-classifying, high-accuracy spiking deep networks through weight and threshold balancing. In: 2015 international joint conference on neural networks (IJCNN), pp 1–8. https://doi.org/10.1109/IJCNN.2015.7280696
Eshraghian JK, Ward M, Neftci E, Wang X, Lenz G, Dwivedi G, Bennamoun M, Jeong DS, Lu WD (2021) Training spiking neural networks using lessons from deep learning. CoRR. arXiv:2109.12894
Esser SK, Merolla PA, Arthur JV, Cassidy AS, Appuswamy R, Andreopoulos A, Berg DJ, McKinstry JL, Melano T, Barch DR, di Nolfo C, Datta P, Amir A, Taba B, Flickner MD, Modha DS (2016) Convolutional networks for fast, energy-efficient neuromorphic computing. Proc Natl Acad Sci 113(41):11441–11446. https://doi.org/10.1073/pnas.1604850113
FitzHugh R (1961) Impulses and physiological states in theoretical models of nerve membrane. Biophys J 1(6):445–466. https://doi.org/10.1016/S0006-3495(61)86902-6
Gerstner W (2001) A framework for spiking neuron models: the spike response model. In: Handbook of biological physics, vol 4. Elsevier, pp 469–516
Hodgkin AL, Huxley AF (1952) A quantitative description of membrane current and its application to conduction and excitation in nerve. J Physiol 117(4):500
Hopfield J (1982) Neural networks and physical systems with emergent collective computational abilities. Proc Natl Acad Sci USA 79:2554–2558. https://doi.org/10.1073/pnas.79.8.2554
Izhikevich E (2003) Simple model of spiking neurons. IEEE Trans Neural Netw 14(6):1569–1572. https://doi.org/10.1109/TNN.2003.820440
Kheradpisheh SR, Masquelier T (2020) Temporal backpropagation for spiking neural networks with one spike per neuron. Int J Neural Syst 30. https://doi.org/10.1142/S0129065720500276
Kirkland P, Manna D, Vicente Sola A, Di Caterina G (2022) Unsupervised spiking instance segmentation on event data using STDP features. IEEE Trans Comput 71:1–12. https://doi.org/10.1109/TC.2022.3191968
Lee JH, Delbruck T, Pfeiffer M (2016) Training deep spiking neural networks using backpropagation. Front Neurosci 10. https://doi.org/10.3389/fnins.2016.00508, https://www.frontiersin.org/articles/10.3389/fnins.2016.00508
Liu T, Liu Z, Lin F, Jin Y, Quan G, Wen W (2017) MT-Spike: a multilayer time-based spiking neuromorphic architecture with temporal error backpropagation. In: Proceedings of the 36th international conference on computer-aided design, ICCAD’17. IEEE Press, pp 450–457
Neftci EO, Mostafa H, Zenke F (2019) Surrogate gradient learning in spiking neural networks: Bringing the power of gradient-based optimization to spiking neural networks. IEEE Signal Process Mag 36(6):51–63
O’Connor P, Welling M (2016) Deep spiking networks. CoRR. arXiv:1602.08323
Tavanaei A, Maida AS (2017) BP-STDP: approximating backpropagation using spike timing dependent plasticity. CoRR. arXiv:1711.04214
Wunderlich T, Pehle C (2021) Event-based backpropagation can compute exact gradients for spiking neural networks. Sci Rep 11:12829. https://doi.org/10.1038/s41598-021-91786-z
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Agarwal, R., Ghosal, P., Murmu, N., Nandi, D. (2023). Spiking Neural Network in Computer Vision: Techniques, Tools and Trends. In: Borah, S., Gandhi, T.K., Piuri, V. (eds) Advanced Computational and Communication Paradigms . ICACCP 2023. Lecture Notes in Networks and Systems, vol 535. Springer, Singapore. https://doi.org/10.1007/978-981-99-4284-8_16
Download citation
DOI: https://doi.org/10.1007/978-981-99-4284-8_16
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-99-4283-1
Online ISBN: 978-981-99-4284-8
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)