Design of Low-Power Neuromorphic Architectures for IoT Applications
محتوى المقالة الرئيسي
الملخص
The rapid growth of the Internet of Things (IoT) demands computing systems that remain highly intelligent while adhering to tight energy constraints. For always-on edge applications, traditional processors are too power-hungry. This neuromorphic system is developed for IoT to achieve computing integrity and has remarkable efficiency. We propose computer-memory architecture which essentially is event-driven processing and temporal-spike coding. Architectural breakthroughs include clockless processing and adaptive precision and therefore exploit temporality with hierarchical event encoding. While current hardware solutions show a power consumption of 70 μW to 680 μW, our system shows 10 – 100× improvement in overall efficiency. Testing proved that with radar gesture recognition, audio pattern matching and visual event detection, we have more than 96 % accuracy. Inference energy is 1.38 nJ, and molecular operation cost is 9.9 pJ of the architecture with these efficient metrics, a new family of autonomous IoT applications can be developed, from battery-free sensor networks to implantable devices that run for years off a single charge.
##plugins.themes.bootstrap3.displayStats.downloads##
تفاصيل المقالة
القسم
كيفية الاقتباس
المراجع
Ankit, A., Haghiri, S., S., S., Sengupta, A., Panda, P. and Roy, K., 2022. Exploring non-volatile memory devices for neuromorphic computing: A case study of transfer learning on edge devices. ACM Journal on Emerging Technologies in Computing Systems. https://doi.org/10.1145/3501303.
Benjamin, B.V., Gao, P., McQuinn, E., Choudhary, S., Chandrasekaran, A.R., Bussat, J.M., Alvarez-Icaza, R., Arthur, J.V., Merolla, P.A. and Boahen, K., 2014. Neurogrid: A mixed-analog-digital multichip system for large-scale neural simulations. Proceedings of the IEEE, 102(5), pp. 699-716. https://doi.org/10.1109/JPROC.2014.2313565.
Blouw, P., Choo, X., Hunsberger, E. and Eliasmith, C., 2018. Benchmarking keyword spotting efficiency on neuromorphic hardware. arXiv preprint arXiv:1812.01739. https://doi.org/10.48550/arXiv.1812.01739.
Caccavella, C., Paredes-Vallés, F., Cannici, M. and Khacef, L., 2023. Low-power event-based face detection with asynchronous neuromorphic hardware. arXiv preprint arXiv:2312.14261. https://doi.org/10.48550/arxiv.2312.14261.
Davies, M., Srinivasa, N., Lin, T.H., Chinya, G., Cao, Y., Choday, S.H., Dimou, G., Joshi, P., Imam, N., Jain, S. and Liao, Y., 2018. Loihi: A neuromorphic manycore processor with on-chip learning. IEEE Micro, 38(1), pp. 82-99. https://doi.org/10.1109/MM.2018.112130359.
Diehl, P.U. and Cook, M., 2015. Unsupervised learning of digit recognition using spike-timing-dependent plasticity. Frontiers in Computational Neuroscience, 9, P. 99. https://doi.org/10.3389/fncom.2015.00099.
Fang, W., Xuan, Z., Chen, S. and Kang, Y., 2023. An 1.38 nJ/inference clock-free mixed-signal neuromorphic architecture using ReL-PSP function and computing-in-memory. In 2023 IEEE Biomedical Circuits and Systems Conference (BioCAS), pp. 1-5. IEEE. https://doi.org/10.1109/biocas58349.2023.10388821.
Feldmann, J., Youngblood, N., Karpov, M., Gehring, H., Li, X., Stiller, M., Follkar, F.J., Ríos, C., Wright, C.D. and Pernice, W.H., 2021. Parallel convolutional processing using an integrated photonic tensor core. Nature, 589(7840), pp. 52–58. https://doi.org/10.1038/s41586-020-03070-1.
Gallego, G., Delbruck, T., Orchard, G., Bartolozzi, C., Taba, B., Censi, A., Leutenegger, S., Davison, A.J., Conradt, J., Daniilidis, K. and Scaramuzza, D., 2022. Event-based vision: A survey. IEEE Transactions on Pattern Analysis and Machine Intelligence, 44(1), pp. 154–180. https://doi.org/10.1109/TPAMI.2020.3008413.
Goi, E., Zhang, Q., Chen, X., Luan, H. and Gu, M., 2020. Perspective on photonic memristive neuromorphic computing. PhotoniX, 1(1), pp. 1–26. https://doi.org/10.1186/S43074-020-0001-6.
Indiveri, G. and Liu, S.C., 2015. Memory and information processing in neuromorphic systems. Proceedings of the IEEE, 103(8), pp. 1379–1397. https://doi.org/10.1109/JPROC.2015.2444094.
Liu, C., Bellec, G., Vogginger, B., Kappel, D., Partzsch, J., Neumärker, F., Höppner, S., Maass, W., Furber, S.B., Legenstein, R. and Mayr, C.G., 2023. A low-power hybrid-precision neuromorphic processor with INT8 inference and INT16 online learning in 40-nm CMOS. IEEE Transactions on Circuits and Systems I: Regular Papers, 70(11), pp. 4413–4425. https://doi.org/10.1109/tcsi.2023.3300095.
Liu, D., Yu, H. and Chai, Y., 2021. Low-power computing with neuromorphic engineering. Advanced Intelligent Systems, 3(2), P. 2000150. https://doi.org/10.1002/AISY.202000150.
Maass, W., 1997. Networks of spiking neurons: The third generation of neural network models. Neural Networks, 10(9), pp. 1659–1671. https://doi.org/10.1016/S0893-6080(97)00011-7.
Merolla, P.A., Arthur, J.V., Alvarez-Icaza, R., Cassidy, A.S., Sawada, J., Akopyan, F., Jackson, B.L., Imam, N., Guo, C., Nakamura, Y. and Brezzo, B., 2014. A million spiking-neuron integrated circuit with a scalable communication network and interface. Science, 345(6197), pp. 668-673. https://doi.org/10.1126/science.1254642.
Qiao, N., Mostafa, H., Corradi, F., Osswald, M., Stefanini, F., Sumislawska, D. and Indiveri, G., 2015. A reconfigurable on-line learning spiking neuromorphic processor comprising 256 neurons and 128 K synapses. Frontiers in Neuroscience, 9, P. 141. https://doi.org/10.3389/fnins.2015.00141.
Roy, K., Jaiswal, A. and Panda, P., 2019. Towards spike-based machine intelligence with neuromorphic computing. Nature, 575, pp. 607–617. https://doi.org/10.1038/s41586-019-1677-2.
Rueckauer, B., Lungu, I.A., Hu, Y., Pfeiffer, M. and Liu, S.C., 2017. Conversion of continuous-valued deep networks to efficient event-driven networks for image classification. Frontiers in Neuroscience, 11, P. 682. https://doi.org/10.3389/fnins.2017.00682.
Safa, A., Wu, I.O. and Gielen, G.G.E., 2022. A hybrid-precision neural network processor for always-on keyword spotting. In 2022 IEEE International Symposium on Circuits and Systems (ISCAS). Austin, TX, USA, 28 May–1 June 2022.
Piscataway, NJ: IEEE, pp. 2978–2982. https://doi.org/10.1109/ISCAS48785.2022.9937666.
Sebastian, A., Le Gallo, M., Khaddam-Aljameh, R. and Eleftheriou, E., 2020. Memory devices and applications for in-memory computing. Nature Nanotechnology, 15(7), pp. 529–544. https://doi.org/10.1038/s41565-020-0655-z.
Shao, Y., Li, C., Chen, Z., Zhao, Y., Zhang, Y. and Liao, X., 2023. Energy-efficient IoT edge intelligence with neuromorphic computing: Opportunities and challenges. ACM Computing Surveys, 55(13s), pp. 1–35. https://doi.org/10.1145/3576360.
Stuijt, J., Sifalakis, M., Yousefzadeh, A. and Corradi, F., 2021. μBrain: An event-driven and fully synthesizable architecture for spiking neural networks. Frontiers in Neuroscience, 15, P. 664208. https://doi.org/10.3389/FNINS.2021.664208.
Tait, A.N., De Lima, T.F., Zhou, E., Wu, A.X., Nahmias, M.A., Shastri, B.J. and Prucnal, P.R., 2019. Silicon photonic modulator neuron. Physical Review Applied, 11(6), P. 064043. https://doi.org/10.1103/PhysRevApplied.11.064043.
Tian, F., Yang, J., Zhao, S. and Sawan, M., 2023. A generic neuromorphic edge computing framework for healthcare applications. Frontiers in Neuroscience, 17, P. 1093865. https://doi.org/10.3389/fnins.2023.1093865.
Urgese, G., Rios-Navarro, A., Linares-Barranco, A., Stewart, T.C. and Michmizos, K., 2023. Powering the next-generation IoT applications: new tools and emerging technologies for the development of Neuromorphic System of Systems. Frontiers in Neuroscience, 17, P. 1197918. https://doi.org/10.3389/fnins.2023.1197918.
Xue, J., Chen, F., Wu, L., Ying, R. and Liu, P., 2023. An optimized mapping toolchain for spiking neural network in edge computing. Sensors, 23(14), P. 6548. https://doi.org/10.3390/s23146548.
Xu, D., Li, T., Li, Y., Su, X., Tarkoma, S., Jiang, T., Crowcroft, J. and Hui, P., 2020. Edge intelligence: Architectures, challenges, and applications. arXiv preprint arXiv:2003.12172.
https://doi.org/10.48550/arXiv.2003.12172
Yik, J., den Berghe, K.V., den Blanken, D., Bouhadjar, Y., Fabre, M., Hueber, P., Kleyko, D., Pacik-Nelson, N., Sun, P.S.V., Tang, G. and Wang, S., 2024. Neurobench: a framework for benchmarking neuromorphic computing algorithms and systems. arXiv preprint arXiv:2304.04640.
Zheng, K., Qian, K., Woodford, T. and Zhang, X., 2023. NeuroRadar: A neuromorphic radar sensor for low-power IoT systems. In Proceedings of the 10th ACM International Conference on Systems for Energy-Efficient Buildings, Cities, and Transportation, pp. 1–6. https://doi.org/10.1145/3625687.3625788.
Zidan, M.A., Strachan, J.P. and Lu, W.D., 2018. The future of electronics based on memristive systems. Nature Electronics, 1(1), pp. 22–29. https://doi.org/10.1038/s41928-017-00.