Neuromorphic Algorithms

Shriram Ramanathan; Abhronil Sengupta

doi:10.1017/9781009564335.008

7 - Neuromorphic Algorithms

Published online by Cambridge University Press: aN Invalid Date NaN

Shriram Ramanathan and

Abhronil Sengupta

Show author details

Shriram Ramanathan: Affiliation:
Rutgers University, New Jersey
Abhronil Sengupta: Affiliation:
Pennsylvania State University

Book contents

Get access

Summary

The chapter begins with a discussion on standard mechanisms for training spiking neural networks ranging from – (a) unsupervised spike-timing-dependent plasticity, (b) backpropagation through time (BPTT) using surrogate gradient techniques, and (c) conversion techniques from conventional analog non-spiking networks. Subsequently, various local learning algorithms with different degrees of locality are discussed that have the potential to replace computationally expensive global learning algorithms such as BPTT. The chapter concludes with pointers to several emerging research directions in the neuromorphic algorithms domain ranging from stochastic computing, lifelong learning, and dynamical system-based approaches, among others. Finally, we also underscore the need for looking at hybrid neuromorphic algorithm design combining principles of conventional deep learning along with forging stronger connections with computational neuroscience.

Keywords

neuromorphic algorithms spiking neural networks spike-timing-dependent plasticity backpropagation through time local learning catastrophic forgetting stochastic computing energy-based learning hybrid algorithms hardware–algorithm–application–neuroscience codesign deep learning

Information

Type: Chapter
Information: Introduction to Neuromorphic Computing , pp. 145 - 168

DOI: https://doi.org/10.1017/9781009564335.008 [Opens in a new window]

Publisher: Cambridge University Press

Print publication year: 2026

Access options

Get access to the full version of this content by using one of the access options below. (Log in options will check for institutional or personal access. Content may require purchase if you do not have access.)

Book purchase

Temporarily unavailable

References

Bi, G. Q. and Poo, M. M., 1998. Synaptic modifications in cultured hippocampal neurons: Dependence on spike timing, synaptic strength, and postsynaptic cell type. Journal of Neuroscience, 18(24), pp. 10464–10472.10.1523/JNEUROSCI.18-24-10464.1998CrossRef Google Scholar PubMed

Lu, S. and Sengupta, A., 2022, June. Hybrid neuromorphic systems: An algorithm-application-hardware-neuroscience co-design perspective: Invited special session paper. In 2022 IEEE 4th International Conference on Artificial Intelligence Circuits and Systems (AICAS) (pp. 210–213). IEEE.10.1109/AICAS54282.2022.9869925CrossRef Google Scholar

Woodin, M. A., Ganguly, K. and Poo, M. M., 2003. Coincident pre-and postsynaptic activity modifies GABAergic synapses by postsynaptic changes in Cl − Transporter activity. Neuron, 39(5), pp. 807–820.10.1016/S0896-6273(03)00507-5CrossRef Google Scholar PubMed

Serrano-Gotarredona, T., Masquelier, T., Prodromakis, T., Indiveri, G. and Linares-Barranco, B., 2013. STDP and STDP variations with memristors for spiking neuromorphic learning systems. Frontiers in Neuroscience, 7, p. 2.10.3389/fnins.2013.00002CrossRef Google Scholar PubMed

Diehl, P. U. and Cook, M., 2015. Unsupervised learning of digit recognition using spike-timing-dependent plasticity. Frontiers in Computational Neuroscience, 9, p. 99.10.3389/fncom.2015.00099CrossRef Google Scholar PubMed

Lee, C., Srinivasan, G., Panda, P. and Roy, K., 2018. Deep spiking convolutional neural network trained with unsupervised spike-timing-dependent plasticity. IEEE Transactions on Cognitive and Developmental Systems, 11(3), pp. 384–394.Google Scholar

Werbos, P. J., 1990. Backpropagation through time: What it does and how to do it. Proceedings of the IEEE, 78(10), pp. 1550–1560.10.1109/5.58337CrossRef Google Scholar

Lin, J., Lu, S., Bal, M. and Sengupta, A., 2024. Benchmarking spiking neural network learning methods with varying locality. arXiv preprint arXiv:2402.01782.10.1109/ACCESS.2025.3582564CrossRef Google Scholar

Bellec, G., Salaj, D., Subramoney, A., Legenstein, R. and Maass, W., 2018. Long short-term memory and learning-to-learn in networks of spiking neurons. Advances in Neural Information Processing Systems, 31, pp. 1–11.Google Scholar

Neftci, E. O., Mostafa, H. and Zenke, F., 2019. Surrogate gradient learning in spiking neural networks: Bringing the power of gradient-based optimization to spiking neural networks. IEEE Signal Processing Magazine, 36(6), pp. 51–63.10.1109/MSP.2019.2931595CrossRef Google Scholar

Diehl, P. U., Neil, D., Binas, J., Cook, M., Liu, S. C. and Pfeiffer, M., 2015, July. Fast-classifying, high-accuracy spiking deep networks through weight and threshold balancing. In 2015 International Joint Conference on Neural Networks (IJCNN) (pp. 1–8). IEEE.10.1109/IJCNN.2015.7280696CrossRef Google Scholar

Sengupta, A., Ye, Y., Wang, R., Liu, C. and Roy, K., 2019. Going deeper in spiking neural networks: VGG and residual architectures. Frontiers in Neuroscience, 13, p. 95.10.3389/fnins.2019.00095CrossRef Google Scholar PubMed

Rathi, N., Srinivasan, G., Panda, P. and Roy, K., 2020. Enabling deep spiking neural networks with hybrid conversion and spike timing dependent backpropagation. arXiv preprint arXiv:2005.01807.Google Scholar

Lu, S. and Sengupta, A., 2022. Neuroevolution guided hybrid spiking neural network training. Frontiers in Neuroscience, 16, p. 838523.10.3389/fnins.2022.838523CrossRef Google Scholar PubMed

Lillicrap, T. P., Cownden, D., Tweed, D. B. and Akerman, C. J., 2016. Random synaptic feedback weights support error backpropagation for deep learning. Nature Communications, 7(1), p. 13276.10.1038/ncomms13276CrossRef Google Scholar PubMed

Baldi, P., Sadowski, P. and Lu, Z., 2017. Learning in the machine: The symmetries of the deep learning channel. Neural Networks, 95, pp. 110–133.CrossRef Google Scholar PubMed

Lillicrap, T. P., Santoro, A., Marris, L., Akerman, C. J. and Hinton, G., 2020. Backpropagation and the brain. Nature Reviews Neuroscience, 21(6), pp. 335–346.10.1038/s41583-020-0277-3CrossRef Google Scholar PubMed

Bellec, G., Scherr, F., Subramoney, A., Hajek, E., Salaj, D., Legenstein, R. and Maass, W., 2020. A solution to the learning dilemma for recurrent networks of spiking neurons. Nature Communications, 11(1), p. 3625.10.1038/s41467-020-17236-yCrossRef Google Scholar

Kaiser, J., Mostafa, H. and Neftci, E., 2020. Synaptic plasticity dynamics for deep continuous local learning (DECOLLE). Frontiers in Neuroscience, 14, p. 424.10.3389/fnins.2020.00424CrossRef Google Scholar PubMed

Gerstner, W., Lehmann, M., Liakoni, V., Corneil, D. and Brea, J., 2018. Eligibility traces and plasticity on behavioral time scales: Experimental support of neoHebbian three-factor learning rules. Frontiers in Neural Circuits, 12, p. 53.10.3389/fncir.2018.00053CrossRef Google Scholar PubMed

Cortes, C., Mohri, M. and Rostamizadeh, A., 2012. Algorithms for learning kernels based on centered alignment. The Journal of Machine Learning Research, 13, pp. 795–828.Google Scholar

Li, Y., Kim, Y., Park, H. and Panda, P., 2023. Uncovering the representation of spiking neural networks trained with surrogate gradient. arXiv preprint arXiv:2304.13098.Google Scholar

Maass, W., 2015. To spike or not to spike: That is the question. Proceedings of the IEEE, 103(12), pp. 2219–2224.10.1109/JPROC.2015.2496679CrossRef Google Scholar

Ardakani, A., Ardakani, A. and Gross, W. J., 2021, October. Fault-tolerance of binarized and stochastic computing-based neural networks. In 2021 IEEE Workshop on Signal Processing Systems (SiPS) (pp. 52–57). IEEE.10.1109/SiPS52927.2021.00018CrossRef Google Scholar

Roy, K., Sengupta, A. and Shim, Y., 2018. Perspective: Stochastic magnetic devices for cognitive computing. Journal of Applied Physics, 123(21), pp. 210901-1–210901-11.10.1063/1.5020168CrossRef Google Scholar

Roy, D., Chakraborty, I. and Roy, K., 2019, July. Scaling deep spiking neural networks with binary stochastic activations. In 2019 IEEE International Conference on Cognitive Computing (ICCC) (pp. 50–58). IEEE.10.1109/ICCC.2019.00020CrossRef Google Scholar

Sengupta, A., Parsa, M., Han, B. and Roy, K., 2016. Probabilistic deep spiking neural systems enabled by magnetic tunnel junction. IEEE Transactions on Electron Devices, 63(7), pp. 2963–2970.10.1109/TED.2016.2568762CrossRef Google Scholar

Islam, A. N. M., Saha, A., Jiang, Z., Ni, K. and Sengupta, A., 2023. Hybrid stochastic synapses enabled by scaled ferroelectric field-effect transistors. Applied Physics Letters, 122(12), pp. 123701-1–123701-7.10.1063/5.0132242CrossRef Google Scholar

Bagheri, A., Simeone, O. and Rajendran, B., 2018, April. Training probabilistic spiking neural networks with first-to-spike decoding. In 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (pp. 2986–2990). IEEE.10.1109/ICASSP.2018.8462410CrossRef Google Scholar

Jiang, Y., Lu, S. and Sengupta, A., 2024. Stochastic spiking neural networks with first-to-spike coding. arXiv preprint arXiv:2404.17719.CrossRef Google Scholar

Yang, K., Gm, D. P. and Sengupta, A., 2023. Leveraging probabilistic switching in superparamagnets for temporal information encoding in neuromorphic systems. IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems, 42(10), pp. 3464–3468.10.1109/TCAD.2022.3233926CrossRef Google Scholar

Bengio, Y., Léonard, N. and Courville, A., 2013. Estimating or propagating gradients through stochastic neurons for conditional computation. arXiv preprint arXiv:1308.3432.Google Scholar

McCloskey, M. and Cohen, N.J., 1989. Catastrophic interference in connectionist networks: The sequential learning problem. Psychology of Learning and Motivation 24, pp. 109–165.10.1016/S0079-7421(08)60536-8CrossRef Google Scholar

Kirkpatrick, J., Pascanu, R., Rabinowitz, N., Veness, J., Desjardins, G., Rusu, A. A., Milan, K., Quan, J., Ramalho, T., Grabska-Barwinska, A. and Hassabis, D., 2017. Overcoming catastrophic forgetting in neural networks. Proceedings of the National Academy of Sciences, 114(13), pp. 3521–3526.10.1073/pnas.1611835114CrossRef Google Scholar PubMed

Zhang, H. T., Park, T. J., Islam, A. N., Tran, D. S., Manna, S., Wang, Q., Mondal, S., Yu, H., Banik, S., Cheng, S. and Zhou, H., 2022. Reconfigurable perovskite nickelate electronics for artificial intelligence. Science, 375(6580), pp. 533–539.10.1126/science.abj7943CrossRef Google Scholar PubMed

Ernst, A., Alkass, K., Bernard, S., Salehpour, M., Perl, S., Tisdale, J., Possnert, G., Druid, H. and Frisén, J., 2014. Neurogenesis in the striatum of the adult human brain. Cell, 156(5), pp. 1072–1083.10.1016/j.cell.2014.01.044CrossRef Google Scholar PubMed

Arzate, D. M. and Covarrubias, L., 2020. Adult neurogenesis in the context of brain repair and functional relevance. Stem Cells and Development, 29(9), pp. 544–554.10.1089/scd.2019.0208CrossRef Google Scholar PubMed

Parisi, G. I., Kemker, R., Part, J. L., Kanan, C. and Wermter, S., 2019. Continual lifelong learning with neural networks: A review. Neural Networks, 113, pp. 54–71.10.1016/j.neunet.2019.01.012CrossRef Google Scholar PubMed

Stanley, K. O., Clune, J., Lehman, J. and Miikkulainen, R., 2019. Designing neural networks through neuroevolution. Nature Machine Intelligence, 1(1), pp. 24–35.10.1038/s42256-018-0006-zCrossRef Google Scholar

Marsland, S., Shapiro, J. and Nehmzow, U., 2002. A self-organising network that grows when required. Neural Networks, 15(8–9), pp. 1041–1058.10.1016/S0893-6080(02)00078-3CrossRef Google Scholar PubMed

Bal, M. and Sengupta, A., 2024, May. Equilibrium-based learning dynamics in spiking architectures. In 2024 IEEE International Symposium on Circuits and Systems (ISCAS) (pp. 1–5). IEEE.10.1109/ISCAS58744.2024.10558225CrossRef Google Scholar

Hinton, G. E., 2002. Training products of experts by minimizing contrastive divergence. Neural Computation, 14(8), pp. 1771–1800.10.1162/089976602760128018CrossRef Google Scholar PubMed

Berkes, P., Orbán, G., Lengyel, M. and Fiser, J., 2011. Spontaneous cortical activity reveals hallmarks of an optimal internal model of the environment. Science, 331(6013), pp. 83–87.10.1126/science.1195870CrossRef Google Scholar PubMed

Scellier, B. and Bengio, Y., 2017. Equilibrium propagation: Bridging the gap between energy-based models and backpropagation. Frontiers in Computational Neuroscience, 11, p. 24.CrossRef Google Scholar

Xiao, M., Meng, Q., Zhang, Z., Wang, Y. and Lin, Z., 2021. Training feedback spiking neural networks by implicit differentiation on the equilibrium state. Advances in Neural Information Processing Systems, 34, pp. 14516–14528.Google Scholar

Ernoult, M., Grollier, J., Querlioz, D., Bengio, Y. and Scellier, B., 2019. Updates of equilibrium prop match gradients of backprop through time in an RNN with static input. Advances in Neural Information Processing Systems, 32, pp. 1–11.Google Scholar

Pineda, F., 1987. Generalization of back propagation to recurrent and higher order neural networks. In Neural Information Processing Systems.10.1103/PhysRevLett.59.2229CrossRef Google Scholar

Martin, E., Ernoult, M., Laydevant, J., Li, S., Querlioz, D., Petrisor, T. and Grollier, J., 2021. EqSpike: Spike-driven equilibrium propagation for neuromorphic implementations. Iscience, 24(3), pp. 102222-1–102222-12.10.1016/j.isci.2021.102222CrossRef Google Scholar PubMed

Bal, M. and Sengupta, A., 2022. Sequence learning using equilibrium propagation. arXiv preprint arXiv:2209.09626.10.24963/ijcai.2023/329CrossRef Google Scholar

Ramsauer, H., Schäfl, B., Lehner, J., Seidl, P., Widrich, M., Adler, T., Gruber, L., Holzleitner, M., Pavlović, M., Sandve, G. K. and Greiff, V., 2020. Hopfield networks is all you need. arXiv preprint arXiv:2008.02217.Google Scholar

Krotov, D. and Hopfield, J., 2018. Dense associative memory is robust to adversarial inputs. Neural Computation, 30(12), pp. 3151–3167.10.1162/neco_a_01143CrossRef Google Scholar PubMed

Lin, J., Bal, M. and Sengupta, A., 2024. Scaling SNNs trained using equilibrium propagation to convolutional architectures. arXiv preprint arXiv:2405.02546.10.1109/ICONS62911.2024.00054CrossRef Google Scholar

Bai, S., Kolter, J. Z. and Koltun, V., 2019. Deep equilibrium models. Advances in Neural Information Processing Systems, 32, pp. 1–12.Google Scholar

Bal, M. and Sengupta, A., 2024, March. SpikingBERT: Distilling BERT to train spiking language models using implicit differentiation. In Proceedings of the AAAI Conference on Artificial Intelligence (Vol. 38, No. 10, pp. 10998–11006).10.1609/aaai.v38i10.28975CrossRef Google Scholar

Bal, M., Jiang, Y. and Sengupta, A., 2024. Exploring extreme quantization in spiking language models. arXiv preprint arXiv:2405.02543.10.1109/ICONS62911.2024.00047CrossRef Google Scholar

Lu, S. and Sengupta, A., 2022, June. Hybrid neuromorphic systems: An algorithm-Application-Hardware-Neuroscience Co-Design perspective: Invited special session paper. In 2022 IEEE 4th International Conference on Artificial Intelligence Circuits and Systems (AICAS) (pp. 210–213). IEEE.10.1109/AICAS54282.2022.9869925CrossRef Google Scholar

Lee, C., Panda, P., Srinivasan, G. and Roy, K., 2018. Training deep spiking convolutional neural networks with STDP-based unsupervised pre-training followed by supervised fine-tuning. Frontiers in Neuroscience, 12, p. 435.10.3389/fnins.2018.00435CrossRef Google Scholar PubMed

Feoktistov, V., 2006. Differential evolution. New York: Springer US.Google Scholar

Lu, S. and Sengupta, A., 2022. Neuroevolution guided hybrid spiking neural network training. Frontiers in Neuroscience, 16, p. 838523.10.3389/fnins.2022.838523CrossRef Google Scholar PubMed

Singh, S., Sarma, A., Jao, N., Pattnaik, A., Lu, S., Yang, K., Sengupta, A., Narayanan, V. and Das, C. R., 2020, May. Nebula: A neuromorphic spin-based ultra-low power architecture for SNNs and ANNs. In 2020 ACM/IEEE 47th Annual International Symposium on Computer Architecture (ISCA) (pp. 363–376). IEEE.10.1109/ISCA45697.2020.00039CrossRef Google Scholar

Pei, J., Deng, L., Song, S., Zhao, M., Zhang, Y., Wu, S., Wang, G., Zou, Z., Wu, Z., He, W. and Chen, F., 2019. Towards artificial general intelligence with hybrid Tianjic chip architecture. Nature, 572(7767), pp. 106–111.10.1038/s41586-019-1424-8CrossRef Google Scholar PubMed

Aimone, J. B., 2021. A roadmap for reaching the potential of brain‐derived computing. Advanced Intelligent Systems, 3(1), p. 2000191.10.1002/aisy.202000191CrossRef Google Scholar

Han, Z., Islam, A. N. and Sengupta, A., 2023, June. Astromorphic self-repair of neuromorphic hardware systems. In Proceedings of the AAAI Conference on Artificial Intelligence (Vol. 37, No. 6, pp. 7821–7829).10.1609/aaai.v37i6.25947CrossRef Google Scholar

London, M. and Häusser, M., 2005. Dendritic computation. Annual Review of Neuroscience, 28(1), pp. 503–532.10.1146/annurev.neuro.28.061604.135703CrossRef Google Scholar PubMed

Plagge, M., Cardwell, S. G. and Chance, F. S., 2024, April. Expressive dendrites in spiking networks. In 2024 Neuro Inspired Computational Elements Conference (NICE) (pp. 1–8). IEEE.10.1109/NICE61972.2024.10548485CrossRef Google Scholar

Goan, E. and Fookes, C., 2020. Bayesian neural networks: An introduction and survey. Case Studies in Applied Bayesian Data Science: CIRM Jean-Morlet Chair, Fall 2018, pp. 45–87.10.1007/978-3-030-42553-1_3CrossRef Google Scholar

Accessibility standard: WCAG 2.2 A

Why this information is here

This section outlines the accessibility features of this content - including support for screen readers, full keyboard navigation and high-contrast display options. This may not be relevant for you.

Accessibility Information

The PDF of this book complies with version 2.2 of the Web Content Accessibility Guidelines (WCAG), offering more comprehensive accessibility measures for a broad range of users and meets the basic (A) level of WCAG compliance, addressing essential accessibility barriers.

Content Navigation

Table of contents navigation
Allows you to navigate directly to chapters, sections, or non‐text items through a linked table of contents, reducing the need for extensive scrolling.

Index navigation
Provides an interactive index, letting you go straight to where a term or subject appears in the text without manual searching.

Reading Order & Textual Equivalents

Single logical reading order
You will encounter all content (including footnotes, captions, etc.) in a clear, sequential flow, making it easier to follow with assistive tools like screen readers.

Short alternative textual descriptions
You get concise descriptions (for images, charts, or media clips), ensuring you do not miss crucial information when visual or audio elements are not accessible.