Towards spike-based machine intelligence with neuromorphic computing

Article metrics

Abstract

Guided by brain-like ‘spiking’ computational frameworks, neuromorphic computing—brain-inspired computing for machine intelligence—promises to realize artificial intelligence while reducing the energy requirements of computing platforms. This interdisciplinary field began with the implementation of silicon circuits for biological neural routines, but has evolved to encompass the hardware implementation of algorithms with spike-based encoding and event-driven representations. Here we provide an overview of the developments in neuromorphic computing for both algorithms and hardware and highlight the fundamentals of learning and hardware frameworks. We discuss the main challenges and the future prospects of neuromorphic computing, with emphasis on algorithm–hardware codesign.

Access options

Rent or Buy article

Get time limited or full article access on ReadCube.

from$8.99

All prices are NET prices.

Fig. 1: Key attributes of biological and silicon-based computing frameworks.
Fig. 2: Timeline of major discoveries and advances in intelligent computing, from the 1940s to the present6, 10, 14, 73, 78, 84, 93, 105, 115, 136,150,151.
Fig. 3: SNN computational models.
Fig. 4: Global and local-learning principles in spiking networks.
Fig. 5: Some representative ‘Big Brain’ chips and AER methods.
Fig. 6: The use of non-volatile memory devices as synaptic storage.

References

  1. 1.

    Silver, D. et al. Mastering the game of Go without human knowledge. Nature 550, 354–359 (2017).

  2. 2.

    Cox, D. D. & Dean, T. Neural networks and neuroscience-inspired computer vision. Curr. Biol. 24, R921–R929 (2014).

  3. 3.

    Milakov, M. Deep Learning With GPUs. https://www.nvidia.co.uk/docs/IO/147844/Deep-Learning-With-GPUs-MaximMilakov-NVIDIA.pdf (Nvidia, 2014).

  4. 4.

    Bullmore, E. & Sporns, O. The economy of brain network organization. Nat. Rev. Neurosci. 13, 336–349 (2012).

  5. 5.

    Felleman, D. J. & Van Essen, D. C. Distributed hierarchical processing in the primate cerebral cortex. Cereb. Cortex 1, 1–47 (1991).

  6. 6.

    Krizhevsky, A., Sutskever, I. & Hinton, G. E. ImageNet classification with deep convolutional neural networks. In Advances in Neural Information Processing Systems Vol. 28 (eds Pereira, F. et al.) 1097–1105 (Neural Information Processing Systems Foundation, 2012). This work—using deep convolutional networks—was the first to win the ImageNet challenge, fuelling the subsequent deep-learning revolution.

  7. 7.

    Deco, G., Rolls, E. T. & Romo, R. Stochastic dynamics as a principle of brain function. Prog. Neurobiol. 88, 1–16 (2009).

  8. 8.

    Venkataramani, S., Roy, K. & Raghunathan, A. Efficient embedded learning for IoT devices. In 21st Asia and South Pacific Design Automation Conf. 308–311 (IEEE, 2016).

  9. 9.

    Maass, W. Networks of spiking neurons: the third generation of neural network models. Neural Netw. 10, 1659–1671 (1997). This paper was one of the first works to provide a rigorous mathematical analysis of the computational power of spiking neurons, categorizing them as the third generation of neural networks (after perceptron and sigmoidal neurons).

  10. 10.

    McCulloch, W. S. & Pitts, W. A logical calculus of the ideas immanent in nervous activity. Bull. Math. Biophys. 5, 115–133 (1943).

  11. 11.

    Nair, V. & Hinton, G. E. Rectified linear units improve restricted Boltzmann machines. In Proc. 27th Int. Conf. on Machine Learning (eds Fürnkranz, J. & Joachims, T.) 807–814 (IMLS, 2010).

  12. 12.

    Rumelhart, D. E., Hinton, G. E. & Williams, R. J. Learning representations by back-propagating errors. Nature 323, 533–536 (1986). This seminal work proposed gradient-descent-based backpropagation as a learning method for neural networks.

  13. 13.

    Izhikevich, E. M. Simple model of spiking neurons. IEEE Trans. Neural Netw. 14, 1569–1572 (2003).

  14. 14.

    Hebb, D. O. The Organization of Behavior: A Neuropsychological Theory (Wiley, 1949).

  15. 15.

    Abbott, L. F. & Nelson, S. B. Synaptic plasticity: taming the beast. Nat. Neurosci. 3, 1178–1183 (2000).

  16. 16.

    Liu, S.-C. & Delbruck, T. Neuromorphic sensory systems. Curr. Opin. Neurobiol. 20, 288–295 (2010).

  17. 17.

    Lichtsteiner, P., Posch, C. & Delbruck, T. A. 128×128 120 db 15 μs latency asynchronous temporal contrast vision sensor. IEEE J. Solid-State Circuits 43, 566–576 (2008).

  18. 18.

    Vanarse, A., Osseiran, A. & Rassau, A. A review of current neuromorphic approaches for vision, auditory, and olfactory sensors. Front. Neurosci. 10, 115 (2016).

  19. 19.

    Benosman, R., Ieng, S.-H., Clercq, C., Bartolozzi, C. & Srinivasan, M. Asynchronous frameless event-based optical flow. Neural Netw. 27, 32–37 (2012).

  20. 20.

    Wongsuphasawat, K. & Gotz, D. Exploring flow, factors, and outcomes of temporal event sequences with the outflow visualization. IEEE Trans. Vis. Comput. Graph. 18, 2659–2668 (2012).

  21. 21.

    Rogister, P., Benosman, R., Ieng, S.-H., Lichtsteiner, P. & Delbruck, T. Asynchronous event-based binocular stereo matching. IEEE Trans. Neural Netw. Learn. Syst. 23, 347–353 (2012).

  22. 22.

    Osswald, M., Ieng, S.-H., Benosman, R. & Indiveri, G. A spiking neural network model of 3D perception for event-based neuromorphic stereo vision systems. Sci. Rep. 7, 40703 (2017).

  23. 23.

    Hinton, G. E., Srivastava, N., Krizhevsky, A., Sutskever, I. & Salakhutdinov, R. R. Improving neural networks by preventing co-adaptation of feature detectors. Preprint at http://arxiv.org/abs/1207.0580 (2012).

  24. 24.

    Deng, J. et al. ImageNet: a large-scale hierarchical image database. In IEEE Conf. on Computer Vision and Pattern Recognition 248–255 (IEEE, 2009).

  25. 25.

    Rullen, R. V. & Thorpe, S. J. Rate coding versus temporal order coding: what the retinal ganglion cells tell the visual cortex. Neural Comput. 13, 1255–1283 (2001).

  26. 26.

    Hu, Y., Liu, H., Pfeiffer, M. & Delbruck, T. DVS benchmark datasets for object tracking, action recognition, and object recognition. Front. Neurosci. 10, 405 (2016).

  27. 27.

    Geiger, A., Lenz, P., Stiller, C. & Urtasun, R. Vision meets robotics: the KITTI dataset. Int. J. Robot. Res. 32, 1231–1237 (2013).

  28. 28.

    Barranco, F., Fermuller, C., Aloimonos, Y. & Delbruck, T. A dataset for visual navigation with neuromorphic methods. Front. Neurosci. 10, 49 (2016).

  29. 29.

    Sengupta, A., Ye, Y., Wang, R., Liu, C. & Roy, K. Going deeper in spiking neural networks: VGG and residual architectures. Front. Neurosci. 13, 95 (2019). This paper was the first to demonstrate the competitive performance of a conversion-based spiking neural network on ImageNet data for deep neural architectures.

  30. 30.

    Cao, Y., Chen, Y. & Khosla, D. Spiking deep convolutional neural networks for energy-efficient object recognition. Int. J. Comput. Vis. 113, 54–66 (2015).

  31. 31.

    Diehl, P. U. et al. Fast-classifying, high-accuracy spiking deep networks through weight and threshold balancing. In Int. Joint Conf. on Neural Networks 2933–2341 (IEEE, 2015).

  32. 32.

    Pérez-Carrasco, J. A. et al. Mapping 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, 2706–2719 (2013).

  33. 33.

    Rueckauer, B., Lungu, I.-A., Hu, Y., Pfeiffer, M. & Liu, S.-C. Conversion of continuous-valued deep networks to efficient event-driven networks for image classification. Front. Neurosci. 11, 682 (2017).

  34. 34.

    Diehl, P. U., Zarrella, G., Cassidy, A. S., Pedroni, B. U. & Neftci, E. Conversion of artificial recurrent neural networks to spiking neural networks for low-power neuromorphic hardware. In Int. Conf. on Rebooting Computing 20 (IEEE, 2016).

  35. 35.

    Abadi, M. et al. Tensorflow: a system for large-scale machine learning. In 12th USENIX Symp. Operating Systems Design and Implementation 265–283 (2016).

  36. 36.

    Hunsberger, E. & Eliasmith, C. Spiking deep networks with LIF neurons. Preprint at http://arxiv.org/abs/1510.08829 (2015).

  37. 37.

    Pfeiffer, M. & Pfeil, T. Deep learning with spiking neurons: opportunities and challenges. Front. Neurosci. 12, 774 (2018).

  38. 38.

    Ponulak, F. & Kasiński, A. Supervised learning in spiking neural networks with ReSuMe: sequence learning, classification, and spike shifting. Neural Comput. 22, 467–510 (2010).

  39. 39.

    Gütig, R. & Sompolinsky, H. The tempotron: a neuron that learns spike-timing-based decisions. Nat. Neurosci. 9, 420–428 (2006).

  40. 40.

    Bohte, S. M., Kok, J. N. & La Poutré, H. Error-backpropagation in temporally encoded networks of spiking neurons. Neurocomputing 48, 17–37 (2002).

  41. 41.

    Ghosh-Dastidar, S. & Adeli, H. A new supervised learning algorithm for multiple spiking neural networks with application in epilepsy and seizure detection. Neural Netw. 22, 1419–1431 (2009).

  42. 42.

    Anwani, N. & Rajendran, B. NormAD: normalized approximate descent-based supervised learning rule for spiking neurons. In Int. Joint Conf. on Neural Networks 2361–2368 (IEEE, 2015).

  43. 43.

    Lee, J. H., Delbruck, T. & Pfeiffer, M. Training deep spiking neural networks using backpropagation. Front. Neurosci. 10, 508 (2016).

  44. 44.

    Orchard, G. et al. HFirst: a temporal approach to object recognition. IEEE Trans. Pattern Anal. Mach. Intell. 37, 2028–2040 (2015).

  45. 45.

    Mostafa, H. Supervised learning based on temporal coding in spiking neural networks. IEEE Trans. Neural Netw. Learn. Syst. 29, 3227–3235 (2018).

  46. 46.

    Panda, P. & Roy, K. Unsupervised regenerative learning of hierarchical features in spiking deep networks for object recognition. In Int. Joint Conf. on Neural Networks 299–306 (IEEE, 2016).

  47. 47.

    LeCun, Y., Cortes, C. & Burges, C. J. C. The MNIST Database of Handwritten Digits http://yann.lecun.com/exdb/mnist/ (1998).

  48. 48.

    Masquelier, T., Guyonneau, R. & Thorpe, S. J. Competitive STDP-based spike pattern learning. Neural Comput. 21, 1259–1276 (2009).

  49. 49.

    Diehl, P. U. & Cook, M. Unsupervised learning of digit recognition using spike-timing-dependent plasticity. Front. Comput. Neurosci. 9, 99 (2015). This is a good introduction to implementing spiking neural networks with unsupervised STDP-based learning for real-world tasks such as digit recognition.

  50. 50.

    Kheradpisheh, S. R., Ganjtabesh, M., Thorpe, S. J. & Masquelier, T. STDP-based spiking deep convolutional neural networks for object recognition. Neural Netw. 99, 56–67 (2018).

  51. 51.

    Neftci, E., Das, S., Pedroni, B., Kreutz-Delgado, K. & Cauwenberghs, G. Event-driven contrastive divergence for spiking neuromorphic systems. Front. Neurosci. 7, 272 (2014).

  52. 52.

    Stromatias, E., Soto, M., Serrano-Gotarredona, T. & Linares-Barranco, B. An event-driven classifier for spiking neural networks fed with synthetic or dynamic vision sensor data. Front. Neurosci. 11, 350 (2017).

  53. 53.

    Lee, C., Panda, P., Srinivasan, G. & Roy, K. Training deep spiking convolutional neural networks with STDP-based unsupervised pre-training followed by supervised fine-tuning. Front. Neurosci. 12, 435 (2018).

  54. 54.

    Mostafa, H., Ramesh, V. & Cauwenberghs, G. Deep supervised learning using local errors. Front. Neurosci. 12, 608 (2018).

  55. 55.

    Neftci, E. O., Augustine, C., Paul, S. & Detorakis, G. Event-driven random back-propagation: enabling neuromorphic deep learning machines. Front. Neurosci. 11, 324 (2017).

  56. 56.

    Srinivasan, G., Sengupta, A. & Roy, K. Magnetic tunnel junction based long-term short-term stochastic synapse for a spiking neural network with on-chip STDP learning. Sci. Rep. 6, 29545 (2016).

  57. 57.

    Tavanaei, A., Masquelier, T. & Maida, A. S. Acquisition of visual features through probabilistic spike-timing-dependent plasticity. In Int. Joint Conf. on Neural Networks 307–314 (IEEE, 2016).

  58. 58.

    Bagheri, A., Simeone, O. & Rajendran, B. Training probabilistic spiking neural networks with first-to-spike decoding. In Int. Conf. on Acoustics, Speech and Signal Processing 2986–2990 (IEEE, 2018).

  59. 59.

    Rastegari, M., Ordonez, V., Redmon, J. & Farhadi, A. XNOR-Net: ImageNet classification using binary convolutional neural networks. In Eur. Conf. on Computer Vision 525–542 (Springer, 2016).

  60. 60.

    Courbariaux, M., Bengio, Y. & David, J.-P. BinaryConnect: training deep neural networks with binary weights during propagations. In Advances in Neural Information Processing Systems Vol. 28 (eds Cortes, C. et al) 3123–3131 (Neural Information Processing Systems Foundation, 2015).

  61. 61.

    Stromatias, E. et al. Robustness of spiking deep belief networks to noise and reduced bit precision of neuro-inspired hardware platforms. Front. Neurosci. 9, 222 (2015).

  62. 62.

    Florian, R. V. Reinforcement learning through modulation of spike-timing-dependent synaptic plasticity. Neural Comput. 19, 1468–1502 (2007).

  63. 63.

    Vasilaki, E., Frémaux, N., Urbanczik, R., Senn, W. & Gerstner, W. Spike-based reinforcement learning in continuous state and action space: when policy gradient methods fail. PLOS Comput. Biol. 5, e1000586 (2009).

  64. 64.

    Zuo, F. et al. Habituation-based synaptic plasticity and organismic learning in a quantum perovskite. Nat. Commun. 8, 240 (2017).

  65. 65.

    Masquelier, T. & Thorpe, S. J. Unsupervised learning of visual features through spike-timing-dependent plasticity. PLOS Comput. Biol. 3, e31 (2007).

  66. 66.

    Rao, R. P. & Sejnowski, T. J. Spike-timing-dependent Hebbian plasticity as temporal difference learning. Neural Comput. 13, 2221–2237 (2001).

  67. 67.

    Roy, S. & Basu, A. An online unsupervised structural plasticity algorithm for spiking neural networks. IEEE Trans. Neural Netw. Learn. Syst. 28, 900–910 (2017).

  68. 68.

    Maass, W. Liquid state machines: motivation, theory, and applications. In Computability in Context: Computation and Logic in the Real World (eds Cooper, S. B. & Sorbi, A.) 275–296 (Imperial College Press, 2011).

  69. 69.

    Schrauwen, B., D’Haene, M., Verstraeten, D. & Van Campenhout, J. Compact hardware liquid state machines on FPGA for real-time speech recognition. Neural Netw. 21, 511–523 (2008).

  70. 70.

    Verstraeten, D., Schrauwen, B., Stroobandt, D. & Van Campenhout, J. Isolated word recognition with the liquid state machine: a case study. Inf. Process. Lett. 95, 521–528 (2005).

  71. 71.

    Panda, P. & Roy, K. Learning to generate sequences with combination of Hebbian and non-Hebbian plasticity in recurrent spiking neural networks. Front. Neurosci. 11, 693 (2017).

  72. 72.

    Maher, M. A. C., Deweerth, S. P., Mahowald, M. A. & Mead, C. A. Implementing neural architectures using analog VLSI circuits. IEEE Trans. Circ. Syst. 36, 643–652 (1989).

  73. 73.

    Mead, C. Neuromorphic electronic systems. Proc. IEEE 78, 1629–1636 (1990). This seminal work established neuromorphic electronic systems as a new paradigm in hardware computing and highlights Mead’s vision of going beyond the precise and well defined nature of digital computing towards brain-like aspects.

  74. 74.

    Mead, C. A. Neural hardware for vision. Eng. Sci. 50, 2–7 (1987).

  75. 75.

    NVIDIA Launches the World’s First Graphics Processing Unit GeForce 256. https://www.nvidia.com/object/IO_20020111_5424.html (Nvidia, 1999).

  76. 76.

    Nageswaran, J. M., Dutt, N., Krichmar, J. L., Nicolau, A. & Veidenbaum, A. V. A configurable simulation environment for the efficient simulation of large-scale spiking neural networks on graphics processors. Neural Netw. 22, 791–800 (2009).

  77. 77.

    Fidjeland, A. K. & Shanahan, M. P. Accelerated simulation of spiking neural networks using GPUs. In Int. Joint. Conf. on Neural Networks 3041–3048 (IEEE, 2010).

  78. 78.

    Davies, M. et al. Loihi: a neuromorphic manycore processor with on-chip learning. IEEE Micro 38, 82–99 (2018).

  79. 79.

    Blouw, P., Choo, X., Hunsberger, E. & Eliasmith, C. Benchmarking keyword spotting efficiency on neuromorphic hardware. In Proc. 7th Annu. Neuro-inspired Computational Elements Workshop 1 (ACM, 2018).

  80. 80.

    Hsu, J. How IBM got brainlike efficiency from the TrueNorth chip. IEEE Spectrum https://spectrum.ieee.org/computing/hardware/how-ibm-got-brainlike-efficiency-from-the-truenorth-chip (29 September 2014).

  81. 81.

    Khan, M. M. et al. SpiNNaker: mapping neural networks onto a massively parallel chip multiprocessor. In Int. Joint Conf. on Neural Networks 2849–2856 (IEEE, 2008). This was one of the first works to implement a large-scale spiking neural network on hardware using event-driven computations and commercial processors.

  82. 82.

    Benjamin, B. V. et al. Neurogrid: a mixed-analog–digital multichip system for large-scale neural simulations. Proc. IEEE 102, 699–716 (2014).

  83. 83.

    Schemmel, J. et al. A wafer-scale neuromorphic hardware system for large-scale neural modeling. In Int. Symp. Circuits and Systems 1947–1950 (IEEE, 2010).

  84. 84.

    Merolla, P. A. et al. A million spiking-neuron integrated circuit with a scalable communication network and interface. Science 345, 668–673 (2014). This work describes TrueNorth, the first digital custom-designed, large-scale neuromorphic processor, an outcome of the DARPA SyNAPSE programme; it was geared towards solving commercial applications through a digital neuromorphic implementation.

  85. 85.

    Furber, S. Large-scale neuromorphic computing systems. J. Neural Eng. 13, 051001 (2016).

  86. 86.

    Qiao, N. et al. A reconfigurable on-line learning spiking neuromorphic processor comprising 256 neurons and 128k synapses. Front. Neurosci. 9, 141 (2015).

  87. 87.

    Indiveri, G. et al. Neuromorphic silicon neuron circuits. Front. Neurosci. 5, 73 (2011).

  88. 88.

    Seo, J.-s. et al. A 45 nm CMOS neuromorphic chip with a scalable architecture for learning in networks of spiking neurons. In Custom Integrated Circuits Conf. 311–334 (IEEE, 2011).

  89. 89.

    Boahen, K. A. Point-to-point connectivity between neuromorphic chips using address events. IEEE Trans. Circuits Syst. II 47, 416–434 (2000). This paper describes the fundamentals of address event representation and its application to neuromorphic systems.

  90. 90.

    Serrano-Gotarredona, R. et al. AER building blocks for multi-layer multi-chip neuromorphic vision systems. In Advances in Neural Information Processing Systems Vol. 18 (eds Weiss, Y., Schölkopf, B. & Platt, J. C.) 1217–1224 (Neural Information Processing Systems Foundation, 2006).

  91. 91.

    Moore, G. E. Cramming more components onto integrated circuits. Proc. IEEE 86, 82–85 (1998).

  92. 92.

    Waldrop, M. M. The chips are down for Moore’s law. Nature 530, 144 (2016).

  93. 93.

    von Neumann, J. First draft of a report on the EDVAC. IEEE Ann. Hist. Comput. 15, 27–75 (1993).

  94. 94.

    Mahapatra, N. R. & Venkatrao, B. The processor–memory bottleneck: problems and solutions. Crossroads 5, 2 (1999).

  95. 95.

    Gokhale, M., Holmes, B. & Iobst, K. Processing in memory: the Terasys massively parallel PIM array. Computer 28, 23–31 (1995).

  96. 96.

    Elliott, D., Stumm, M., Snelgrove, W. M., Cojocaru, C. & McKenzie, R. Computational RAM: implementing processors in memory. IEEE Des. Test Comput. 16, 32–41 (1999).

  97. 97.

    Ankit, A., Sengupta, A., Panda, P. & Roy, K. RESPARC: a reconfigurable and energy-efficient architecture with memristive crossbars for deep spiking neural networks. In Proc. 54th ACM/EDAC/IEEE Annual Design Automation Conf. 63.2 (IEEE, 2017).

  98. 98.

    Bez, R. & Pirovano, A. Non-volatile memory technologies: emerging concepts and new materials. Mater. Sci. Semicond. Process. 7, 349–355 (2004).

  99. 99.

    Xue, C. J. et al. Emerging non-volatile memories: opportunities and challenges. In Proc. 9th Int. Conf. on Hardware/Software Codesign and System Synthesis 325–334 (IEEE, 2011).

  100. 100.

    Wong, H.-S. P. & Salahuddin, S. Memory leads the way to better computing. Nat. Nanotechnol. 10, 191 (2015); correction 10, 660 (2015).

  101. 101.

    Chi, P. et al. Prime: a novel processing-in-memory architecture for neural network computation in ReRAM-based main memory. In Proc. 43rd Int. Symp. Computer Architecture 27–39 (IEEE, 2016).

  102. 102.

    Shafiee, A. et al. ISAAC: a convolutional neural network accelerator with in-situ analog arithmetic in crossbars. In Proc. 43rd Int. Symp. Computer Architecture 14–26 (IEEE, 2016).

  103. 103.

    Burr, G. W. et al. Neuromorphic computing using non-volatile memory. Adv. Phys. X 2, 89–124 (2017).

  104. 104.

    Snider, G. S. Spike-timing-dependent learning in memristive nanodevices. In Proc. Int. Symp. on Nanoscale Architectures 85–92 (IEEE, 2008).

  105. 105.

    Chua, L. Memristor—the missing circuit element. IEEE Trans. Circuit Theory 18, 507–519 (1971). This was the first work to conceptualize memristors as fundamental passive circuit elements; they are currently being investigated as high-density storage devices through various emerging technologies for conventional general-purpose and neuromorphic computing architectures.

  106. 106.

    Strukov, D. B., Snider, G. S., Stewart, D. R. & Williams, R. S. The missing memristor found. Nature 453, 80–83 (2008).

  107. 107.

    Waser, R., Dittmann, R., Staikov, G. & Szot, K. Redox-based resistive switching memories—nanoionic mechanisms, prospects, and challenges. Adv. Mater. 21, 2632–2663 (2009).

  108. 108.

    Burr, G. W. et al. Recent progress in phase-change memory technology. IEEE J. Em. Sel. Top. Circuits Syst. 6, 146–162 (2016).

  109. 109.

    Hosomi, M. et al. A novel nonvolatile memory with spin torque transfer magnetization switching: spin-RAM. In Int. Electron Devices Meeting 459–462 (IEEE, 2005).

  110. 110.

    Ambrogio, S. et al. Statistical fluctuations in HfOx resistive-switching memory. Part I—set/reset variability. IEEE Trans. Electron Dev. 61, 2912–2919 (2014).

  111. 111.

    Fantini, A. et al. Intrinsic switching variability in HfO2 RRAM. In 5th Int. Memory Workshop 30–33 (IEEE, 2013).

  112. 112.

    Merrikh-Bayat, F. et al. High-performance mixed-signal neurocomputing with nanoscale floating-gate memory cell arrays. IEEE Trans. Neural Netw. Learn. Syst. 29, 4782–4790 (2017).

  113. 113.

    Ramakrishnan, S., Hasler, P. E. & Gordon, C. Floating-gate synapses with spike-time-dependent plasticity. IEEE Trans. Biomed. Circuits Syst. 5, 244–252 (2011).

  114. 114.

    Hasler, J. & Marr, H. B. Finding a roadmap to achieve large neuromorphic hardware systems. Front. Neurosci. 7, 118 (2013).

  115. 115.

    Hasler, P. E., Diorio, C., Minch, B. A. & Mead, C. Single transistor learning synapses. In Advances in Neural Information Processing Systems Vol. 7 (eds Tesauro, G., Touretzky, D. S. & Leen, T. K.) 817–824 (Neural Information Processing Systems Foundation, 1995). This was one of the first works to use a non-volatile memory device—specifically, a floating-gate transistor—as a synaptic element.

  116. 116.

    Holler, M., Tam, S., Castro, H. & Benson, R. An electrically trainable artificial neural network (ETANN) with 10240 ‘floating gate’ synapses. In Int. Joint Conf. on Neural Networks Vol. 2, 191–196 (1989).

  117. 117.

    Chen, P.-Y. et al. Technology–design co-optimization of resistive cross-point array for accelerating learning algorithms on chip. In Proc. Eur. Conf. on Design, Automation & Testing 854–859 (IEEE, 2015).

  118. 118.

    Chakraborty, I., Roy, D. & Roy, K. Technology aware training in memristive neuromorphic systems for nonideal synaptic crossbars. IEEE Trans. Em. Top. Comput. Intell. 2, 335–344 (2018).

  119. 119.

    Alibart, F., Gao, L., Hoskins, B. D. & Strukov, D. B. High precision tuning of state for memristive devices by adaptable variation-tolerant algorithm. Nanotechnology 23, 075201 (2012).

  120. 120.

    Dong, Q. et al. A 4 + 2T SRAM for searching and in-memory computing with 0.3-V V DDmin. IEEE J. Solid-State Circuits 53, 1006–1015 (2018).

  121. 121.

    Agrawal, A., Jaiswal, A., Lee, C. & Roy, K. X-SRAM: enabling in-memory Boolean computations in CMOS static random-access memories. IEEE Trans. Circuits Syst. I 65, 4219–4232 (2018).

  122. 122.

    Eckert, C. et al. Neural cache: bit-serial in-cache acceleration of deep neural networks. In Proc. 45th Ann. Int. Symp. Computer Architecture 383–396 (IEEE, 2018).

  123. 123.

    Gonugondla, S. K., Kang, M. & Shanbhag, N. R. A variation-tolerant in-memory machine-learning classifier via on-chip training. IEEE J. Solid-State Circuits 53, 3163–3173 (2018).

  124. 124.

    Biswas, A. & Chandrakasan, A. P. Conv-RAM: an energy-efficient SRAM with embedded convolution computation for low-power CNN-based machine learning applications. In Int. Solid-State Circuits Conf. 488–490 (IEEE, 2018).

  125. 125.

    Kang, M., Keel, M.-S., Shanbhag, N. R., Eilert, S. & Curewitz, K. An energy-efficient VLSI architecture for pattern recognition via deep embedding of computation in SRAM. In Int. Conf. on Acoustics, Speech and Signal Processing 8326–8330 (IEEE, 2014).

  126. 126.

    Seshadri, V. et al. RowClone: fast and energy-efficient in-DRAM bulk data copy and initialization. In Proc. 46th Ann. IEEE/ACM Int. Symp. Microarchitecture 185–197 (ACM, 2013).

  127. 127.

    Prezioso, M. et al. Training and operation of an integrated neuromorphic network based on metal-oxide memristors. Nature 521, 61–64 (2015).

  128. 128.

    Sebastian, A. et al. Temporal correlation detection using computational phase-change memory. Nat. Commun. 8, 1115 (2017).

  129. 129.

    Jain, S., Ranjan, A., Roy, K. & Raghunathan, A. Computing in memory with spin-transfer torque magnetic RAM. IEEE Trans. Very Large Scale Integr. (VLSI) Syst. 26, 470–483 (2018).

  130. 130.

    Jabri, M. & Flower, B. Weight perturbation: an optimal architecture and learning technique for analog VLSI feedforward and recurrent multilayer networks. IEEE Trans. Neural Netw. 3, 154–157 (1992).

  131. 131.

    Diorio, C., Hasler, P., Minch, B. A. & Mead, C. A. A floating-gate MOS learning array with locally computed weight updates. IEEE Trans. Electron Dev. 44, 2281–2289 (1997).

  132. 132.

    Bayat, F. M., Prezioso, M., Chakrabarti, B., Kataeva, I. & Strukov, D. Memristor-based perceptron classifier: increasing complexity and coping with imperfect hardware. In Proc. 36th Int. Conf. on Computer-Aided Design 549–554 (IEEE, 2017).

  133. 133.

    Guo, X. et al. Fast, energy-efficient, robust, and reproducible mixed-signal neuromorphic classifier based on embedded NOR flash memory technology. In Int. Electron Devices Meeting 6.5 (IEEE, 2017).

  134. 134.

    Liu, C., Hu, M., Strachan, J. P. & Li, H. Rescuing memristor-based neuromorphic design with high defects. In Proc. 54th ACM/EDAC/IEEE Design Automation Conf. 76.6 (IEEE, 2017).

  135. 135.

    Tuma, T., Pantazi, A., Le Gallo, M., Sebastian, A. & Eleftheriou, E. Stochastic phase-change neurons. Nat. Nanotechnol. 11, 693–699 (2016).

  136. 136.

    Fukushima, A. et al. Spin dice: a scalable truly random number generator based on spintronics. Appl. Phys. Express 7, 083001 (2014).

  137. 137.

    Le Gallo, M. et al. Mixed-precision in-memory computing. Nature Electron. 1, 246 (2018).

  138. 138.

    Krstic, M., Grass, E., Gürkaynak, F. K. & Vivet, P. Globally asynchronous, locally synchronous circuits: overview and outlook. IEEE Des. Test Comput. 24, 430–441 (2007).

  139. 139.

    Choi, H. et al. An electrically modifiable synapse array of resistive switching memory. Nanotechnology 20, 345201 (2009).

  140. 140.

    Serrano-Gotarredona, T., Masquelier, T., Prodromakis, T., Indiveri, G. & Linares-Barranco, B. STDP and STDP variations with memristors for spiking neuromorphic learning systems. Front. Neurosci. 7, 2 (2013).

  141. 141.

    Kuzum, D., Jeyasingh, R. G., Lee, B. & Wong, H.-S. P. Nanoelectronic programmable synapses based on phase change materials for brain-inspired computing. Nano Lett. 12, 2179–2186 (2012).

  142. 142.

    Krzysteczko, P., Münchenberger, J., Schäfers, M., Reiss, G. & Thomas, A. The memristive magnetic tunnel junction as a nanoscopic synapse–neuron system. Adv. Mater. 24, 762–766 (2012).

  143. 143.

    Vincent, A. F. et al. Spin-transfer torque magnetic memory as a stochastic memristive synapse for neuromorphic systems. IEEE Trans. Biomed. Circuits Syst. 9, 166–174 (2015).

  144. 144.

    Sengupta, A. & Roy, K. Encoding neural and synaptic functionalities in electron spin: a pathway to efficient neuromorphic computing. Appl. Phys. Rev. 4, 041105 (2017).

  145. 145.

    Borghetti, J. et al. ‘Memristive’ switches enable ‘stateful’ logic operations via material implication. Nature 464, 873–876 (2010).

  146. 146.

    Hu, M. et al. Dot-product engine for neuromorphic computing: programming 1T1M crossbar to accelerate matrix-vector multiplication. InProc. 53rd ACM/EDAC/IEEE Annual Design Automation Conf.21.1 (IEEE, 2016).

  147. 147.

    Sheridan, P. M. et al. Sparse coding with memristor networks. Nat. Nanotechnol. 12, 784–789 (2017).

  148. 148.

    Wright, C. D., Liu, Y., Kohary, K. I., Aziz, M. M. & Hicken, R. J. Arithmetic and biologically-inspired computing using phase-change materials. Adv. Mater. 23, 3408–3413 (2011).

  149. 149.

    Le Gallo, M., Sebastian, A., Cherubini, G., Giefers, H. & Eleftheriou, E. Compressed sensing recovery using computational memory. In Int. Electron Devices Meeting 28.3.1 (IEEE, 2017).

  150. 150.

    Rosenblatt, F. The perceptron: a probabilistic model for information storage and organization in the brain. Psychol. Rev. 65 386 (1958).

  151. 151.

    Bi, G. Q. & Poo, M. M. Synaptic modifications in cultured hippocampal neurons: dependence on spike timing, synaptic strength, and postsynaptic cell type. J. Neurosci. 18, 10464–10472 (1998).

Download references

Acknowledgements

We thank A. Sengupta (Pennsylvania State University), A. Raychowdhury (Georgia Institute of Technology) and S. Gupta (Purdue University) for their input. The work was supported in part by the Center for Brain-inspired Computing Enabling Autonomous Intelligence (C-BRIC), a DARPA-sponsored JUMP center, the Semiconductor Research Corporation, the National Science Foundation, Intel Corporation, the DoD Vannevar Bush Fellowship, the ONR-MURI programme, and the US Army Research Laboratory and the UK Ministry of Defence under agreement number W911NF-16-3-0001.

Author information

All authors contributed equally in devising the structure of the paper, designing the figures and writing the manuscript.

Correspondence to Kaushik Roy.

Ethics declarations

Competing interests

The authors declare no competing interests.

Additional information

Publisher’s note Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Roy, K., Jaiswal, A. & Panda, P. Towards spike-based machine intelligence with neuromorphic computing. Nature 575, 607–617 (2019) doi:10.1038/s41586-019-1677-2

Download citation

Comments

By submitting a comment you agree to abide by our Terms and Community Guidelines. If you find something abusive or that does not comply with our terms or guidelines please flag it as inappropriate.