Abstract
In this work, we report a spike-timing-dependent plasticity (STDP)-based weight-quantized/binarized online-learning spiking neural network (SNN). The SNN uses bio-plausible integrate-and-fire (IF) neuron and conductance-based synapse as the basic building blocks and realizes online learning by STDP and winner-take-all (WTA) mechanism. Weight quantization/binarization is introduced into the online-learning SNN to reduce storage requirements and improve computing efficiency. After the training process with STDP and weight quantization on the MNIST training set, the quantized SNN with 4-bit weight achieves a recognition accuracy of 93.8% on the MNIST test set, showing little loss compared with the accuracy of the non-quantized 32-bit SNN (94.1%). The accuracy of the binarized SNN slightly decreases to 92.9%, which is cost-effective considering the reduction in the weight storage space by ~ 32 times, and the product of input and weight in the binarized SNN can be realized by computationally cheap 1-bit “AND” operation. The proposed weight quantization/binarization online-learning scheme can largely save hardware costs. The area of the quantized (8-bit and 4-bit) and binarized (1-bit) SNN-based hardware is evaluated to be 448,524, 179,263, and 162,129 μm2, respectively, which is much smaller than their non-quantized 32-bit competitor (area of ~ 5.862 × 108 μm2). The hardware resource evaluation also provides a guide to make a trade-off between computational cost and performance. Moreover, the quantized/binarized STDP training method can be further extended to train various types of SNNs. In this regard, a hybrid STDP SNN and a hybrid STDP convolutional SNN, which are trained by combining unsupervised quantized/binarized STDP and supervised backpropagation (BP) training methods, achieve high accuracy in facial expression recognition scenarios.
Similar content being viewed by others
References
Krizhevsky A, Sutskever I, Hinton GE (2017) Imagenet classification with deep convolutional neural networks. Commun ACM 60(6):84–90
Long J, Shelhamer E, Darrell T (2015) Fully convolutional networks for semantic segmentation. IEEE Trans Pattern Anal Mach Intell 39(4):640–651
Bellec G, Salaj D, Subramoney A, Legenstein R, Maass W (2018) Long short-term memory and learning-to-learn in networks of spiking neurons. Adv Neural Inform Process Syst 2018:787–797
Hinton G, Deng L, Yu D, Dahl GE, Kingsbury B (2012) Deep Neural networks for acoustic modeling in speech recognition: The shared views of four research groups. IEEE Signal Process Mag 29(6):82–97
Neil D, Pfeiffer M, Liu S-C (2016) Phased lstm: accelerating recurrent network training for long or event-based sequences. Adv Neural Inform Process Syst 2016:3882–3890
Zhang X, Zhao J, LeCun Y (2015) Character-level convolutional networks for text classification. Adv Neural Inform Process Syst 2015:649–657
Roy K, Jaiswal A, Panda PJN (2019) Towards spike-based machine intelligence with neuromorphic computing. Nature 575(7784):607–617
Hayati M, Nouri M, Haghiri S, Abbott D (2015) Digital multiplierless realization of two coupled biological Morris-Lecar neuron model. IEEE Trans Circuits Syst I Regul Pap 62(7):1805–1814
Pei J et al (2019) Towards artificial general intelligence with hybrid Tianjic chip architecture. Nature 572(7767):106
Bi G-Q, Poo M-M (1998) Synaptic modifications in cultured hippocampal neurons: dependence on spike timing, synaptic strength, and postsynaptic cell type. J Neurosci 18(24):10464–10472
Merolla PA et al (2014) Artificial brains. A million spiking-neuron integrated circuit with a scalable communication network and interface. Science 345(6197):668–673
Schuman CD et al (2017) A survey of neuromorphic computing and neural networks in hardware. arXiv preprint arXiv;1705.06963
Akopyan F et al (2015) TrueNorth: design and tool flow of a 65 mW 1 million neuron programmable neurosynaptic chip. IEEE Trans Comput Aided Des Integr Circuits Syst 34(10):1537–1557
Davies M et al (2018) Loihi: a neuromorphic manycore processor with on-chip learning. IEEE Micro 99:1–1
Rastegari M, Ordonez V, Redmon J, Farhadi A (2016) Xnor-net: Imagenet classification using binary convolutional neural networks. European conference on computer vision. Springer, pp 525–542
Wang Z, Liu K, Cui X, Wang Y (2020) Deep spiking binary neural network for digital neuromorphic hardware. In: 2020 IEEE 15th international conference on solid-state & integrated circuit technology (ICSICT). IEEE, New York, pp 1–3
Sorbaro M, Liu Q, Bortone M, Sheik S (2020) Optimizing the energy consumption of spiking neural networks for neuromorphic applications. Front Neurosci 14:662
Courbariaux M, Bengio Y, David J-P (2015) Binaryconnect: training deep neural networks with binary weights during propagations. In: Advances in neural information processing systems, 2015, pp 3123–3131
Li F, Zhang B, Liu B (2016) Ternary weight networks. arXiv preprint arXiv;1605.04711
Hubara I, Courbariaux M, Soudry D, Ran EY, Bengio Y (2016) Quantized neural networks: training neural networks with low precision weights and activations. J Mach Learn Res 18:1
Tavanaei A, Ghodrati M, Kheradpisheh SR, Masquelier T, Maida A (2018) Deep learning in spiking neural networks. Neural Netw
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
Lobo JL, Del Ser J, Bifet A, Kasabov N (2020) Spiking neural networks and online learning: an overview and perspectives. Neural Netw 121:88–100
Abbott LF (1999) Lapicque’s introduction of the integrate-and-fire model neuron (1907). Brain Res Bull 50(5–6):303–304
Delorme A, Gautrais J, Van Rullen R, Thorpe S (1999) SpikeNET: a simulator for modeling large networks of integrate and fire neurons. Neurocomputing 26:989–996
Diehl PU, Neil D, Binas J, Cook M, Liu S-C, Pfeiffer M (2015) Fast-classifying, high-accuracy spiking deep networks through weight and threshold balancing. In: 2015 international joint conference on neural networks (IJCNN), 2015. IEEE, pp 1–8
Pehlevan C, Chklovskii DB (2019) Neuroscience-inspired online unsupervised learning algorithms: artificial neural networks. IEEE Signal Process Mag 36(6):88–96
Hebb DO (2013) The organization of behavior A neuropsychological theory. Chapman & Hall, John Wiley
Sejnowski TJ (1977) Storing covariance with nonlinearly interacting neurons. J Math Biol 4(4):303–321
Oja E (1982) Simplified neuron model as a principal component analyzer. J Math Biol 15(3):267–273
Bienenstock EL, Cooper LN, Munro PW (1982) Theory for the development of neuron selectivity: orientation specificity and binocular interaction in visual cortex. J Neurosci 2(1):32–48
Caporale N, Dan Y (2008) Spike timing-dependent plasticity: a Hebbian learning rule. Annual Rev Neuroence 31(1):25–46
E C et al (2012) A large-scale model of the functioning brain. Science 338(6111): 1202
Diehl PU, Matthew C (2015) Unsupervised learning of digit recognition using spike-timing-dependent plasticity. Front Comput Neuroence 9(429):99
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
Tavanaei A, Maida A (2019) BP-STDP: approximating backpropagation using spike timing dependent plasticity. Neurocomputing 330:39–47
Querlioz D, Bichler O, Dollfus P, Gamrat C (2013) Immunity to device variations in a spiking neural network with memristive nanodevices. IEEE Trans Nanotechnol 12(3):288–295
Capizzi G, Sciuto GL, Napoli C, Woźniak M, Susi G (2020) A spiking neural network-based long-term prediction system for biogas production. Neural Netw
Toğaçar M, Ergen B, Cömert Z (2020) Detection of weather images by using spiking neural networks of deep learning models. Neural Comput Appl 1–13
Bing Z, Meschede C, Chen G, Knoll A, Huang K (2020) Indirect and direct training of spiking neural networks for end-to-end control of a lane-keeping vehicle. Neural Netw 121:21–36
Tavanaei A, Maida AS (2017) Multi-layer unsupervised learning in a spiking convolutional neural network. In: International joint conference on neural networks, 2017
Zhao D, Zeng Y, Zhang T, Shi M, Zhao F (2020) GLSNN: A multi-layer spiking neural network based on global feedback alignment and local STDP plasticity. Front Comput Neurosci
Saunders DJ, Patel D, Hazan H, Siegelmann HT, Kozma R (2019) Locally connected spiking neural networks for unsupervised feature learning. Neural Netw 119:332–340
Kasabov NK (2018) Time-space, spiking neural networks and brain-inspired artificial intelligence. Springer
Qiao GC et al (2020) STBNN: hardware-friendly spatio-temporal binary neural network with high pattern recognition accuracy. Neurocomputing 409:351–360. https://doi.org/10.1016/j.neucom.2020.06.084
Hubara I, Courbariaux M, Soudry D, El-Yaniv R, Bengio Y (2017) Quantized neural networks: training neural networks with low precision weights and activations. J Mach Learn Res 18(1):6869–6898
Qiao G et al (2019) A neuromorphic-hardware oriented bio-plausible online-learning spiking neural network model. IEEE Access 7:71730–71740
Fang Y, Cohen MA, Kincaid TG (1996) Dynamics of a winner-take-all neural network. Neural Netw 9(7):1141–1154
Gerstner W, Kistler WM (2002) Spiking neuron models: single neurons, populations, plasticity. Cambridge University Press
Mensi S, Naud R, Pozzorini C, Avermann M, Petersen CCH, Gerstner W (2012) Parameter extraction and classification of three cortical neuron types reveals two distinct adaptation mechanisms. J Neurophysiol 107(6):1756
Morrison A, Aertsen A, Diesmann M (2007) Spike-timing-dependent plasticity in balanced random networks. Neural Comput 19(6):1437–1467
Goodman DF, Brette R (2008) Brian: a simulator for spiking neural networks in python. Front Neuroinform 2:5
Lyons MJ, Akamatsu S, Kamachi MG, Gyoba J (1998) Coding facial expressions with Gabor wavelets. In: Proceedings third IEEE international conference on automatic face and gesture recognition, 1998, 200–205.
Lucey P, Cohn JF, Kanade T, Saragih J, Ambadar Z, Matthews I (2010) The extended cohn-kanade dataset (ck+): a complete dataset for action unit and emotion-specified expression. In: 2010 IEEE computer society conference on computer vision and pattern recognition-workshops, 2010. IEEE, pp 94–101
Acknowledgements
This work was supported in part by NSFC under Projects 61771097 and 61774028 and in part by the Fundamental Research Funds for the Central Universities under Project ZYGX2016Z007.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
The authors declare that they have no conflict of interest.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Hu, S.G., Qiao, G.C., Chen, T.P. et al. Quantized STDP-based online-learning spiking neural network. Neural Comput & Applic 33, 12317–12332 (2021). https://doi.org/10.1007/s00521-021-05832-y
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00521-021-05832-y