Abstract
Memristive neural networks (MNNs) attract the attention of many researchers because memristor can mimic the learning mechanism of biologic neuron, spike timing-dependent plasticity (STDP). While STDP brings huge potentials on many applications for memristive neural networks, it also gives complex calculation process for hardware implement. In this work, a non-STDP learning mechanism is proposed, which is implemented in two common frameworks including feedforward neural network and crossbar. The non-STDP learning mechanism relies on the linear relationship between the value of memristor and area of input spikes, which gives the proposed method a simple calculation process and better hardware compatibility. Experimental results show that the non-STDP learning mechanism can help to achieve good hardware performance in both feedforward neural network and crossbar frameworks. Compared with STDP based memristive neural networks, the proposed method can save 2.19%-24.4% hardware resource (ALMs) and improve 1.56-12.25 MHz processing speed under a set of different network scales. In future, some other complex memristor models with non-STDP learning mechanism should be taken into consideration, which will give more room for practical applications of memristive neural networks.
Similar content being viewed by others
References
Amara SG, Kuhar MJ (1993) Neurotransmitter transporters: recent progress. Ann Rev Neurosci 16(1):73–93
Ambrogio S, Balatti S, Nardi F, Facchinetti S, Ielmini D (2013) Spike-timing dependent plasticity in a transistor-selected resistive switching memory. Nanotechnology 24(38):384012
Ankit A, Sengupta A, Panda P, Roy K (2017) Resparc: a reconfigurable and energy-efficient architecture with memristive crossbars for deep spiking neural networks. In: Proceedings of the 54th Annual Design Automation Conference 2017, pp 1–6
Basu A, Acharya J, Karnik T, Liu H, Li H, Seo JS, Song C (2018) Low-power, adaptive neuromorphic systems: Recent progress and future directions. IEEE J Emerg Sel Top Circ Syst 8(1):6–27
Chua L (1971) Memristor-the missing circuit element. IEEE Trans Circ Theory 18(5):507–519
Covi E, Brivio S, Serb A, Prodromakis T, Fanciulli M, Spiga S (2016) Hfo2-based memristors for neuromorphic applications. In: 2016 IEEE International symposium on circuits and systems (ISCAS). IEEE, pp 393–396
Duan S, Hu X, Dong Z, Wang L, Mazumder P (2014) Memristor-based cellular nonlinear/neural network: design, analysis, and applications. IEEE Trans Neural Netw Learn Syst 26(6):1202–1213
Falez P (2019) Improving spiking neural networks trained with spike timing dependent plasticity for image recognition. Ph.D. thesis, Université de Lille
Fan D, Sharad M, Roy K (2014) Design and synthesis of ultralow energy spin-memristor threshold logic. IEEE Trans Nanotechnol 13(3):574–583
Gerstner W (2001) A framework for spiking neuron models: The spike response model. In: Handbook of biological physics, vol 4. Elsevier, pp 469–516
Hao Y, Huang X, Dong M, Xu B (2020) A biologically plausible supervised learning method for spiking neural networks using the symmetric stdp rule. Neural Netw 121:387–395
Hu M, Graves CE, Li C, Li Y, Ge N, Montgomery E, Davila N, Jiang H, Williams RS, Yang JJ, et al. (2018) Memristor-based analog computation and neural network classification with a dot product engine. Adv Mater 30(9):1705914
Hu R, Tang Z, Song X, Luo J, Wu EQ, Chang S (2020) Ensemble echo network with deep architecture for time-series modeling. Neural Comput Appl:1–14
Hu R, Zhou S, Liu Y, Tang Z (2019) Margin-based pareto ensemble pruning: An ensemble pruning algorithm that learns to search optimized ensembles. Computational Intelligence and Neuroscience
Jo SH, Nazarian H (2015) Resistive random access memory with high selectivity and on/off ratio amplification sensing. In: 2015 IEEE 11Th international conference on ASIC (ASICON). IEEE, pp 1–3
Kvatinsky S, Belousov D, Liman S, Satat G, Wald N, Friedman EG, Kolodny A, Weiser UC (2014) Magic—memristor-aided logic. IEEE Trans Circ Syst II: Express Briefs 61(11):895–899
Li C, Belkin D, Li Y, Yan P, Hu M, Ge N, Jiang H, Montgomery E, Lin P, Wang Z et al (2018) Efficient and self-adaptive in-situ learning in multilayer memristor neural networks. Nat Commun 9(1):1–8
Li C, Wang Z, Rao M, Belkin D, Song W, Jiang H, Yan P, Li Y, Lin P, Hu M et al (2019) Long short-term memory networks in memristor crossbar arrays. Nat Mach Intell 1(1):49–57
Lin Q, Wang J, Yang S, Yi G, Deng B, Wei X, Yu H (2017) The dynamical analysis of modified two-compartment neuron model and fpga implementation. Physica A: Stat Mech Appl 484:199–214
Moon J, Ma W, Shin JH, Cai F, Du C, Lee SH, Lu WD (2019) Temporal data classification and forecasting using a memri stor-based reservoir computing system. Nat Electron 2(10):480–487
Pershin YV, Di Ventra M (2010) Experimental demonstration of associative memory with memristive neural networks. Neural Netw 23(7):881–886
Pham VT, Jafari S, Vaidyanathan S, Volos C, Wang X (2016) A novel memristive neural network with hidden attractors and its circuitry implementation. Sci China Technol Sci 59(3):358–363
Pham VT, Volos C, Jafari S, Wang X, Vaidyanathan S et al (2014) Hidden hyperchaotic attractor in a novel simple memristive neural network. Optoelectron Adv Mater Rapid Commun 8(11-12):1157–1163
Phinyomark A, Phukpattaranont P, Limsakul C (2012) Feature reduction and selection for emg signal classification. Expert Syst Appl 39(8):7420–7431
Schuman CD, Potok TE, Patton RM, Birdwell JD, Dean ME, Rose GS, Plank JS (2017) A survey of neuromorphic computing and neural networks in hardware. arXiv:1705.06963
Shi Y, Nguyen L, Oh S, Liu X, Koushan F, Jameson JR, Kuzum D (2018) Neuroinspired unsupervised learning and pruning with subquantum cbram arrays. Nat Commun 9(1):1–11
Strukov DB, Snider GS, Stewart DR, Williams RS (2008) The missing memristor found. Nature 453(7191):80
Tang Z, Chen Y, Ye S, Hu R, Wang H, He J, Huang Q, Chang S (2020) Fully memristive spiking-neuron learning framework and its applications on pattern recognition and edge detection. Neurocomputing 403:80–87
Tang Z, Zhu R, Hu R, Chen Y, Wu EQ, Wang H, He J, Huang Q, Chang S (2020) A multilayer neural network merging image preprocessing and pattern recognition by integrating diffusion and drift memristors. IEEE Transactions on Cognitive and Developmental Systems
Tang Z, Zhu R, Lin P, He J, Wang H, Huang Q, Chang S, Ma Q (2019) A hardware friendly unsupervised memristive neural network with weight sharing mechanism. Neurocomputing 332:193–202
Wang J, Hu S, Zhan X, Yu Q, Liu Z, Chen TP, Yin Y, Hosaka S, Liu Y (2018) Handwritten-digit recognition by hybrid convolutional neural network based on hfo 2 memristive spiking-neuron. Sci Rep 8(1):1–7
Wang Z, Joshi S, Savel’ev SE, Jiang H, Midya R, Lin P, Hu M, Ge N, Strachan JP, Li Z et al (2017) Memristors with diffusive dynamics as synaptic emulators for neuromorphic computing. Nat Mater 16(1):101
Wang Z, Li C, Lin P, Rao M, Nie Y, Song W, Qiu Q, Li Y, Yan P, Strachan JP et al (2019) In situ training of feed-forward and recurrent convolutional memristor networks. Nat Mach Intell 1(9):434–442
Wang Z, Li C, Song W, Rao M, Belkin D, Li Y, Yan P, Jiang H, Lin P, Hu M et al (2019) Reinforcement learning with analogue memristor arrays. Nat Electron 2(3):115–124
Wang Z, Rao M, Han JW, Zhang J, Lin P, Li Y, Li C, Song W, Asapu S, Midya R et al (2018) Capacitive neural network with neuro-transistors. Nat Commun 9(1):1–10
Wang Z, Wang X, Lu Z, Wu W, Zeng Z (2020) The design of memristive circuit for affective multi-associative learning. IEEE Transactions on Biomedical Circuits and Systems
Wang Z, Wu H, Burr GW, Hwang CS, Wang KL, Xia Q, Yang JJ (2020) Resistive switching materials for information processing. Nat Rev Mater:1–23
Wang Z, Zeng T, Ren Y, Lin Y, Xu H, Zhao X, Liu Y, Ielmini D (2020) Toward a generalized bienenstock-cooper-munro rule for spatiotemporal learning via triplet-stdp in memristive devices. Nat Commun 11(1):1–10
Wu A, Zeng Z (2015) Global mittag–leffler stabilization of fractional-order memristive neural networks. IEEE Trans Neural Netw Learn Syst 28(1):206–217
Wu EQ, Deng PY, Qu XY, Tang Z, Zhang WM, Zhu LM, Ren H, Zhou GR, Sheng RS (2020) Detecting fatigue status of pilots based on deep learning network using eeg signals. IEEE Transactions on Cognitive and Developmental Systems
Wu EQ, Hu D, Deng PY, Tang Z, Cao Y, Zhang WM, Zhu LM, Ren H (2020) Nonparametric bayesian prior inducing deep network for automatic detection of cognitive status. IEEE Transactions on Cybernetics
Xia Q, Robinett W, Cumbie MW, Banerjee N, Cardinali TJ, Yang JJ, Wu W, Li X, Tong WM, Strukov DB et al (2009) Memristor- cmos hybrid integrated circuits for reconfigurable logic. Nano Lett 9(10):3640–3645
Xie X, Zou L, Wen S, Zeng Z, Huang T (2019) A flux-controlled logarithmic memristor model and emulator. Circ Syst Signal Process 38(4):1452–1465
Yang JJ, Strukov DB, Stewart DR (2013) Memristive devices for computing. Nat Nanotechnol 8(1):13–24
Zhang X, Zhuo Y, Luo Q, Wu Z, Midya R, Wang Z, Song W, Wang R, Upadhyay NK, Fang Y et al (2020) An artificial spiking afferent nerve based on mott memristors for neurorobotics. Nat Commun 11(1):1–9
Zhu R, Chang S, Wang H, Huang Q, He J, Yi F (2017) A versatile and accurate compact model of memristor with equivalent resistor topology. IEEE Electron Dev Lett 38(10):1367–1370
Zhu R, Ye S, Tang Z, Lin P, Huang Q, Wang H, He J, Chang S (2019) Influence of compact memristors’ stability on machine learning. IEEE Access 7:47472–47478
Zhu X, Li D, Liang X, Lu WD (2019) Ionic modulation and ionic coupling effects in mos 2 devices for neuromorphic computing. Nat Mater 18(2):141–148
Author information
Authors and Affiliations
Contributions
All authors contributed to the study conception and design. Material preparation, data collection and analysis were performed by Yanhua Chen, Zhihua Wang, Ruihan Hu, and Edmond Q. Wu. The first draft of the manuscript was written by Zhiri Tang and all authors commented on previous versions of the manuscript. All authors read and approved the final manuscript.
Corresponding author
Ethics declarations
Conflict of interests
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
Tang, Z., Chen, Y., Wang, Z. et al. Non-spike timing-dependent plasticity learning mechanism for memristive neural networks. Appl Intell 51, 3684–3695 (2021). https://doi.org/10.1007/s10489-020-01985-w
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10489-020-01985-w