Abstract
The human brain is regarded as a power-efficient learning machine capable of carrying out complex computations while using only little resources. A sophisticated property that makes energy-efficient computation possible is the distinct sparse communication among many spiking neurons. The primary goal of neuromorphic hardware is to emulate brain-like neural networks to solve real-world problems. However, training on neuromorphic systems is challenging due to the required non-local computations of gradient-based learning algorithms. In Spiking neural networks, there are two fundamental modes: inference and learning. The learning phase, which minimizes a particular cost or loss function, is a complex process of acquiring the parameters to output the correct inference results. On the other hand, the inference computes the output values based on the given input and the network parameters. This chapter presents how learning in neuromorphic computing systems is conducted.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Ben Abdallah A, Dang KN (2021) Toward robust cognitive 3d brain-inspired cross-paradigm system. Frontiers Neurosci 15:795
Bohte SM, Kok JN, La Poutré JA (2000) Spikeprop: backpropagation for networks of spiking neurons. In: ESANN, vol 48, pp 17–37
Booij O, tat Nguyen H (2005) A gradient descent rule for spiking neurons emitting multiple spikes. Inf Process Lett 95(6):552–558
Brader JM, Senn W, Fusi S (2007) Learning real-world stimuli in a neural network with spike-driven synaptic dynamics. Neural Comput 19(11):2881–2912
Cai W, Ellinger F, Tetzlaff R (2014) Neuronal synapse as a memristor: Modeling pair-and triplet-based stdp rule. IEEE Trans Biomed Circuits Syst 9(1):87–95
Cao Y, Chen Y, Khosla D (2015) Spiking deep convolutional neural networks for energy-efficient object recognition. Int J Comput Vis 113(1):54–66
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). IEEE, pp 1–8
Florian RV (2008) Tempotron-like learning with resume. In: International conference on artificial neural networks. Springer, pp 368–375
Gerstner W, Kempter R, Van Hemmen JL, Wagner H (1996) A neuronal learning rule for sub-millisecond temporal coding. Nature 383(6595):76–78
Gütig R, Sompolinsky H (2006) The tempotron: a neuron that learns spike timing–based decisions. Nat Neurosci 9(3):420–428
Han B, Srinivasan G, Roy K (2020) Rmp-snn: Residual membrane potential neuron for enabling deeper high-accuracy and low-latency spiking neural network. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pp 13558–13567
Hu Y, Tang H, Wang Y, Pan G (2018) Spiking deep residual network. Preprint. ar**v:1805.01352
Hunsberger E, Eliasmith C (2015) Spiking deep networks with LIF neurons. Preprint. ar**v:1510.08829
Ikechukwu OM, Dang KN, Abdallah AB (2021) On the design of a fault-tolerant scalable three dimensional NoC-based digital neuromorphic system with on-chip learning. IEEE Access 9:64331–64345
Ioffe S, Szegedy C (2015) Batch normalization: Accelerating deep network training by reducing internal covariate shift. Preprint. ar**v:1502.03167
Izhikevich EM (2007) Solving the distal reward problem through linkage of STDP and dopamine signaling. Cerebral Cortex 17(10):2443–2452
Krizhevsky A, Sutskever I, Hinton GE (2012) Imagenet classification with deep convolutional neural networks. In: Advances in neural information processing systems, pp 1097–1105
Lee C, Sarwar SS, Panda P, Srinivasan G, Roy K (2020) Enabling spike-based backpropagation for training deep neural network architectures. Frontiers Neurosci 14, 119
Masquelier T, Thorpe SJ (2007) Unsupervised learning of visual features through spike timing dependent plasticity. PLoS Comput Biol 3(2), e31
McKennoch S, Liu D, Bushnell LG (2006) Fast modifications of the spikeprop algorithm. In: The 2006 IEEE international joint conference on neural network proceedings. IEEE, pp 3970–3977
Mikolov T, Kombrink S, Burget L, J Černockỳ, Khudanpur S (2011) Extensions of recurrent neural network language model. In: 2011 IEEE international conference on acoustics, speech and signal processing (ICASSP). IEEE, pp 5528–5531
Morrison A, Diesmann M, Gerstner W (2008) Phenomenological models of synaptic plasticity based on spike timing. Biol Cybern 98(6):459–478
Nair V, Hinton GE (2010) Rectified linear units improve restricted Boltzmann machines. In: Proceedings of the 27th international conference on machine learning (ICML-10), pp 807–814
Natschläger T, Ruf B (1998) Spatial and temporal pattern analysis via spiking neurons. Network Comput Neural Syst 9(3):319–332
Neil D, Pfeiffer M, Liu SC (2016) Learning to be efficient: Algorithms for training low-latency, low-compute deep spiking neural networks. In Proceedings of the 31st annual ACM symposium on applied computing, pp 293–298
Nessler B, Pfeiffer M, Maass W (2009) STDP enables spiking neurons to detect hidden causes of their inputs. In: Advances in neural information processing systems, pp 1357–1365
Orchard G, Meyer C, R Etienne-Cummings, Posch C, Thakor N, Benosman R (2015) Hfirst: a temporal approach to object recognition. IEEE Trans Pattern Anal Mach Intell 37(10):2028–2040
Pérez-Carrasco JA, Zhao B, Serrano C, Acha B, Serrano-Gotarredona T, Chen S, Linares-Barranco B (2013) Map** from frame-driven to frame-free event-driven vision systems by low-rate rate coding and coincidence processing–application to feedforward convnets. IEEE Trans Pattern Anal Mach Intell 35(11):2706–2719
Pfister JP, Gerstner W (2006) Triplets of spikes in a model of spike timing-dependent plasticity. J Neurosci 26(38):9673–9682
Ponulak F (2006) Supervised learning in spiking neural networks with resume method. Phd, Poznan University of Technology 46:47
Riedmiller M, Braun H (1993) A direct adaptive method for faster backpropagation learning: The RPROP algorithm. In: IEEE international conference on neural networks. IEEE, pp 586–591
Roy K, Jaiswal A, Panda P (2019) Towards spike-based machine intelligence with neuromorphic computing. Nature 575(7784):607–617
Rueckauer B, Liu SC (2018) Conversion of analog to spiking neural networks using sparse temporal coding. In: 2018 IEEE international symposium on circuits and systems (ISCAS). IEEE, pp 1–5
Rueckauer B, Lungu IA, Hu Y, Pfeiffer M, Liu SC (2017) Conversion of continuous-valued deep networks to efficient event-driven networks for image classification. Frontiers Neurosci 11:682
Scherer D, Müller A, Behnke S (2010) Evaluation of pooling operations in convolutional architectures for object recognition. In International conference on artificial neural networks. Springer, pp 92–101
Schrauwen B, Van Campenhout J (2004) Extending spikeprop. In 2004 IEEE international joint conference on neural networks (IEEE Cat. No. 04CH37541). IEEE, vol 1, pp 471–475
Schultz W (1998) Predictive reward signal of dopamine neurons. J Neurophysiol 80(1):1–27
Sengupta A, Ye Y, Wang R, Liu C, Roy K (2019) Going deeper in spiking neural networks: VGG and residual architectures. Frontiers Neurosci 13:95
Shrestha SB, Song Q (2015) Adaptive learning rate of spikeprop based on weight convergence analysis. Neural Netw 63:185–198
Shrestha S, Song Q (2017) Robust learning in spikeprop. Neural Netw 86:54–68
Simonyan K, Zisserman A (2014) Very deep convolutional networks for large-scale image recognition. Preprint. ar**v:1409.1556
Srivastava N, Hinton G, Krizhevsky A, Sutskever I, Salakhutdinov R (2014) Dropout: a simple way to prevent neural networks from overfitting. J Mach Learn Res 15(1):1929–1958
Tang J, Yuan F, Shen X, Wang Z, Rao M, He Y, Sun Y, Li X, Zhang W, Li Y, et al (2019) Bridging biological and artificial neural networks with emerging neuromorphic devices: fundamentals, progress, and challenges. Adv Mater 31(49):1902761
Vu TH, Ikechukwu OM, Abdallah AB (2019) Fault-tolerant spike routing algorithm and architecture for three dimensional NoC-based neuromorphic systems. IEEE Access 7:90436–90452
Vu TH, Murakami Y, Abdallah AB (2019) Graceful fault-tolerant on-chip spike routing algorithm for mesh-based spiking neural networks. In: 2019 2nd International conference on intelligent autonomous systems (ICoIAS), Singapore, February 2019
Vu TH, Murakami Y, Abdallah AB (2019) A low-latency tree-based multicast spike routing for scalable multicore neuromorphic chips. In: ACM 5th international conference of computing for engineering and sciences, Hammamet, Tunisia, July 2019
Vu TH, Okuyama Y, Abdallah AB (2019) Comprehensive analytic performance assessment and k-means based multicast routing algorithm and architecture for 3d-NoC of spiking neurons. ACM J Emerg Technol Comput Syst 15(4):1–28
Wang HX, Gerkin RC, Nauen DW, Bi GQ (2005) Coactivation and timing-dependent integration of synaptic potentiation and depression. Nat Neurosci 8(2):187–193
Wu J, Chua Y, Zhang M, Yang Q, Li G, Li H (2019) Deep spiking neural network with spike count based learning rule. In 2019 International joint conference on neural networks (IJCNN). IEEE, pp 1–6
**n J, Embrechts MJ (2001) Supervised learning with spiking neural networks. In: IJCNN’01. International joint conference on neural networks. Proceedings (Cat. No. 01CH37222). IEEE, vol 3, pp 1772–1777
Yan H, Liu X, Huo H, Fang T (2019) Mechanisms of reward-modulated STDP and winner-take-all in bayesian spiking decision-making circuit. In: Neural information processing. Springer International Publishing, pp 162–172
Yu AJ, Giese MA, Poggio TA (2002) Biophysiologically plausible implementations of the maximum operation. Neural Comput 14(12):2857–2881
Zambrano D, Bohte SM (2016) Fast and efficient asynchronous neural computation with adapting spiking neural networks. Preprint. ar**v:1609.02053
Zhang L, Zhou S, Zhi T, Du Z, Chen Y (2019) Tdsnn: From deep neural networks to deep spike neural networks with temporal-coding. In: Proceedings of the AAAI conference on artificial intelligence, vol 33, pp 1319–1326
Author information
Authors and Affiliations
Corresponding authors
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this chapter
Cite this chapter
Ben Abdallah, A., N. Dang, K. (2022). Learning in Neuromorphic Systems. In: Neuromorphic Computing Principles and Organization. Springer, Cham. https://doi.org/10.1007/978-3-030-92525-3_3
Download citation
DOI: https://doi.org/10.1007/978-3-030-92525-3_3
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-92524-6
Online ISBN: 978-3-030-92525-3
eBook Packages: Computer ScienceComputer Science (R0)