Analog reservoir computing via ferroelectric mixed phase boundary transistors.
Journal
Nature communications
ISSN: 2041-1723
Titre abrégé: Nat Commun
Pays: England
ID NLM: 101528555
Informations de publication
Date de publication:
23 Oct 2024
23 Oct 2024
Historique:
received:
30
04
2024
accepted:
08
10
2024
medline:
24
10
2024
pubmed:
24
10
2024
entrez:
23
10
2024
Statut:
epublish
Résumé
Analog reservoir computing (ARC) systems have attracted attention owing to their efficiency in processing temporal information. However, the distinct functionalities of the system components pose challenges for hardware implementation. Herein, we report a fully integrated ARC system that leverages material versatility of the ferroelectric-to-mixed phase boundary (MPB) hafnium zirconium oxides integrated onto indium-gallium-zinc oxide thin-film transistors (TFTs). MPB-based TFTs (MPBTFTs) with nonlinear short-term memory characteristics are utilized for physical reservoirs and artificial neuron, while nonvolatile ferroelectric TFTs mimic synaptic behavior for readout networks. Furthermore, double-gate configuration of MPBTFTs enhances reservoir state differentiation and state expansion for physical reservoir and processes both excitatory and inhibitory pulses for neuronal functionality with minimal hardware burden. The seamless integration of ARC components on a single wafer executes complex real-world time-series predictions with a low normalized root mean squared error of 0.28. The material-device co-optimization proposed in this study paves the way for the development of area- and energy-efficient ARC systems.
Identifiants
pubmed: 39443502
doi: 10.1038/s41467-024-53321-2
pii: 10.1038/s41467-024-53321-2
doi:
Types de publication
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Pagination
9147Subventions
Organisme : National Research Foundation of Korea (NRF)
ID : RS-2023-00260527
Informations de copyright
© 2024. The Author(s).
Références
LeCun, Y., Bengio, Y. & Hinton, G. Deep learning. Nature 521, 436–444 (2015).
pubmed: 26017442
doi: 10.1038/nature14539
Prezioso, M. et al. Training and operation of an integrated neuromorphic network based on metal-oxide memristors. Nature 521, 61–64 (2015).
pubmed: 25951284
doi: 10.1038/nature14441
Wang, Z. et al. In situ training of feed-forward and recurrent convolutional memristor networks. Nat. Mach. Intell. 1, 434–442 (2019).
doi: 10.1038/s42256-019-0089-1
Danial, L. et al. Two-terminal floating-gate transistors with a low-power memristive operation mode for analogue neuromorphic computing. Nat. Electron. 2, 596–605 (2019).
doi: 10.1038/s41928-019-0331-1
Zhang, H.-T. et al. Reconfigurable perovskite nickelate electronics for artificial intelligence. Science 375, 533–539 (2022).
pubmed: 35113713
doi: 10.1126/science.abj7943
Kim, J. et al. Demonstration of In-Memory Biosignal Analysis: Novel High-Density and Low-Power 3D Flash Memory Array for Arrhythmia Detection. Adv. Sci. 11, 2308460 (2024).
doi: 10.1002/advs.202308460
Yao, P. et al. Fully hardware-implemented memristor convolutional neural network. Nature 577, 641–646 (2020).
pubmed: 31996818
doi: 10.1038/s41586-020-1942-4
Wang, Z. et al. Fully memristive neural networks for pattern classification with unsupervised learning. Nat. Electron. 1, 137–145 (2018).
doi: 10.1038/s41928-018-0023-2
Dalgaty, T. et al. In situ learning using intrinsic memristor variability via Markov chain Monte Carlo sampling. Nat. Electron. 4, 151–161 (2021).
doi: 10.1038/s41928-020-00523-3
Kim, J. et al. First Demonstration of Innovative 3D AND-Type Fully-Parallel Convolution Block with Ultra-High Area-and Energy-Efficiency. IEEE International Electron Devices Meeting (IEDM). IEEE (2023).
Hopfield, J. J. Neural networks and physical systems with emergent collective computational abilities. Proc. Natl Acad. Sci. USA 79, 2554–2558 (1982).
pubmed: 6953413
pmcid: 346238
doi: 10.1073/pnas.79.8.2554
Verstraeten, D. et al. An experimental unification of reservoir computing methods. Neural Netw. 20, 391–403 (2007).
pubmed: 17517492
doi: 10.1016/j.neunet.2007.04.003
Appeltant, L. et al. Information processing using a single dynamical node as complex system. Nat. Commun. 2, 468 (2011).
pubmed: 21915110
doi: 10.1038/ncomms1476
Lukoševičius, M. & Jaeger, H. Reservoir computing approaches to recurrent neural network training. Comput. Sci. Rev. 3, 127–149 (2009).
doi: 10.1016/j.cosrev.2009.03.005
Dambre, J. et al. Information processing capacity of dynamical systems. Sci. Rep. 2, 514 (2012).
pubmed: 22816038
pmcid: 3400147
doi: 10.1038/srep00514
Jang, Y. H. et al. Time-varying data processing with nonvolatile memristor-based temporal kernel. Nat. Commun. 12, 5727 (2021).
pubmed: 34593800
pmcid: 8484437
doi: 10.1038/s41467-021-25925-5
Qi, Z. et al. Physical reservoir computing based on nanoscale materials and devices. Adv. Funct. Mater. 33, 2306149 (2023).
doi: 10.1002/adfm.202306149
Zhong, Y. et al. A memristor-based analogue reservoir computing system for real-time and power-efficient signal processing. Nat. Electron. 5, 672–681 (2022).
doi: 10.1038/s41928-022-00838-3
Moon, J. et al. Temporal data classification and forecasting using a memristor-based reservoir computing system. Nat. Electron. 2, 480–487 (2019).
doi: 10.1038/s41928-019-0313-3
Milano, G. et al. In material reservoir computing with a fully memristive architecture based on self-organizing nanowire networks. Nat. Mater. 21, 195–202 (2022).
pubmed: 34608285
doi: 10.1038/s41563-021-01099-9
Zhong, Y. et al. Dynamic memristor-based reservoir computing for high-efficiency temporal signal processing. Nat. Commun. 12, 408 (2021).
pubmed: 33462233
pmcid: 7814066
doi: 10.1038/s41467-020-20692-1
Du, C. et al. Reservoir computing using dynamic memristors for temporal information processing. Nat. Commun. 8, 2204 (2017).
pubmed: 29259188
pmcid: 5736649
doi: 10.1038/s41467-017-02337-y
Zhu, X., Wang, Q. & Lu, W. D. Memristor networks for real-time neural activity analysis. Nat. Commun. 11, 2439 (2020).
pubmed: 32415218
pmcid: 7228921
doi: 10.1038/s41467-020-16261-1
Park, S. O. et al. Experimental demonstration of highly reliable dynamic memristor for artificial neuron and neuromorphic computing. Nat. Commun. 13, 2888 (2022).
pubmed: 35660724
pmcid: 9166790
doi: 10.1038/s41467-022-30539-6
John, R. A. et al. Reconfigurable halide perovskite nanocrystal memristors for neuromorphic computing. Nat. Commun. 13, 2074 (2022).
pubmed: 35440122
pmcid: 9018677
doi: 10.1038/s41467-022-29727-1
Sun, L. et al. In-sensor reservoir computing for language learning via two-dimensional memristors. Sci. Adv. 7, eabg1455 (2022).
doi: 10.1126/sciadv.abg1455
Choi, S. et al. 3D-integrated multilayered physical reservoir array for learning and forecasting time-series information. Nat. Commun. 15, 2044 (2024).
pubmed: 38448419
pmcid: 10917743
doi: 10.1038/s41467-024-46323-7
Chen, Z. et al. All-ferroelectric implementation of reservoir computing. Nat. Commun. 14, 3585 (2023).
pubmed: 37328514
pmcid: 10275999
doi: 10.1038/s41467-023-39371-y
Liu, Z. et al. Interface-type tunable oxygen ion dynamics for physical reservoir computing. Nat. Commun. 14, 7176 (2023).
pubmed: 37935751
pmcid: 10630289
doi: 10.1038/s41467-023-42993-x
Liu, K. et al. Multilayer reservoir computing based on ferroelectric α-In2Se3 for hierarchical information processing. Adv. Mater. 34, 2108826 (2022).
doi: 10.1002/adma.202108826
Nako, E. et al. Experimental demonstration of novel scheme of HZO/Si FeFET reservoir computing with parallel data processing for speech recognition. 2022 IEEE Symposium on VLSI Technology and Circuits (VLSI Technology and Circuits). IEEE (2022).
Yu, J. et al. Energy efficient and robust reservoir computing system using ultrathin (3.5 nm) ferroelectric tunneling junctions for temporal data learning. 2021 Symposium on VLSI Technology. IEEE (2021).
Torrejon, J. et al. Neuromorphic computing with nanoscale spintronic oscillators. Nature 547, 428–431 (2017).
pubmed: 28748930
pmcid: 5575904
doi: 10.1038/nature23011
Cucchi, M. et al. Reservoir computing with biocompatible organic electrochemical networks for brain-inspired biosignal classification. Sci. Adv. 7, eabh0693 (2021).
pubmed: 34407948
pmcid: 8373129
doi: 10.1126/sciadv.abh0693
Usami, Y. et al. Inmaterio reservoir computing in a sulfonated polyaniline network. Adv. Mater. 33, 2102688 (2021).
pubmed: 34533867
pmcid: 11469268
doi: 10.1002/adma.202102688
Kan, S. et al. Physical implementation of reservoir computing through electrochemical reaction. Adv. Sci. 9, 2104076 (2022).
doi: 10.1002/advs.202104076
Vandoorne, K. et al. Experimental demonstration of reservoir computing on a silicon photonics chip. Nat. Commun. 5, 3541 (2014).
pubmed: 24662967
doi: 10.1038/ncomms4541
Pierangeli, D., Marcucci, G. & Conti, C. Photonic extreme learning machine by free-space optical propagation. Photon Res 9, 1446–1454 (2021).
doi: 10.1364/PRJ.423531
McCaul, G., Jacobs, K. & Bondar, D. I. Towards single atom computing via high harmonic generation. Eur. Phys. J. 138, 123 (2023).
Fujii, K. & Nakajima, K. Harnessing disordered-ensemble quantum dynamics for machine learning. Phys. Rev. Appl. 8, 024030 (2017).
doi: 10.1103/PhysRevApplied.8.024030
Cartier, E. et al. Fundamental aspects of HfO 2-based high-k metal gate stack reliability and implications on t inv-scaling. 2011 International Electron Devices Meeting (IEDM). IEEE (2011).
Böscke, T. S. et al. Ferroelectricity in hafnium oxide thin films. Appl. Phys. Lett. 99, 102903 (2011).
doi: 10.1063/1.3634052
Wei, Y. et al. A rhombohedral ferroelectric phase in epitaxially strained Hf0.5Zr0.5O2 thin films. Nat. Mater. 17, 1095–1100 (2018).
pubmed: 30349031
doi: 10.1038/s41563-018-0196-0
Noheda, B., Nukala, P. & Acuautla, M. Lessons from hafnium dioxide-based ferroelectrics. Nat. Mater. 22, 562–569 (2023).
pubmed: 37138006
doi: 10.1038/s41563-023-01507-2
Luo, Z. et al. High-precision and linear weight updates by subnanosecond pulses in ferroelectric tunnel junction for neuroinspired computing. Nat. Commun. 13, 699 (2022).
pubmed: 35121735
pmcid: 8816951
doi: 10.1038/s41467-022-28303-x
Li, J. et al. Reproducible ultrathin ferroelectric domain switching for high‐performance neuromorphic computing. Adv. Mater. 32, 1905764 (2020).
doi: 10.1002/adma.201905764
Chuang, C. H. et al. Sharp Transformation across Morphotropic Phase Boundary in Sub-6 nm Wake-Up-Free Ferroelectric Films by Atomic Layer Technology. Adv. Sci. 10, 2302770 (2023).
doi: 10.1002/advs.202302770
Jung, M., Gaddam, V. & Jeon, S. A review on morphotropic phase boundary in fluorite-structure hafnia towards DRAM technology. Nano Converg. 9, 44 (2022).
pubmed: 36182997
pmcid: 9526780
doi: 10.1186/s40580-022-00333-7
Farronato, M. et al. Reservoir computing with charge‐trap memory based on a MoS2 channel for neuromorphic engineering. Adv. Mater. 35, 2205381 (2023).
doi: 10.1002/adma.202205381
Zhang, Z. et al. In-sensor reservoir computing system for latent fingerprint recognition with deep ultraviolet photo-synapses and memristor array. Nat. Commun. 13, 6590 (2022).
pubmed: 36329017
pmcid: 9633641
doi: 10.1038/s41467-022-34230-8
Jang, Y. H. et al. A high-dimensional in-sensor reservoir computing system with optoelectronic memristors for high-performance neuromorphic machine vision. Mater. Horiz. 11, 499–509 (2024).
pubmed: 37966888
doi: 10.1039/D3MH01584J
Kim, D. et al. Ferroelectric synaptic devices based on CMOS-compatible HfAlO x for neuromorphic and reservoir computing applications. Nanoscale 15, 8366–8376 (2023).
pubmed: 37092534
doi: 10.1039/D3NR01294H
Chen, C. et al. Bio-inspired neurons based on novel leaky-FeFET with ultra-low hardware cost and advanced functionality for all-ferroelectric neural network. 2019 symposium on VLSI technology. IEEE (2019).
Zheng, Z. et al. First Demonstration of Work Function-Engineered BEOL-Compatible IGZO Non-Volatile MFMIS AFeFETs and Their Co-Integration with Volatile-AFeFETs. 2023 IEEE Symposium on VLSI Technology and Circuits (VLSI Technology and Circuits). IEEE (2023).
Sun, C. et al. Novel a-IGZO anti-ferroelectric FET LIF neuron with co-integrated ferroelectric FET synapse for spiking neural networks. 2022 International Electron Devices Meeting (IEDM). IEEE (2022).
Kim, J. et al. Toward Optimized In-Memory Reinforcement Learning: Leveraging 1/f Noise of Synaptic Ferroelectric Field-Effect-Transistors for Efficient Exploration. Advanced Intelligent Systems 2300763 (2024).
Mulaosmanovic, H. et al. Ferroelectric transistors with asymmetric double gate for memory window exceeding 12 V and disturb-free read. Nanoscale 13, 16258–16266 (2021).
pubmed: 34549741
doi: 10.1039/D1NR05107E
Jeong, S. et al. All-Sputter-Deposited Hf 0.5 Zr 0.5 O 2 Double-Gate Ferroelectric Thin-Film Transistor with Amorphous Indium–Gallium–Zinc Oxide Channel. IEEE Electron Device Letters (2023).
Paquot, Y. et al. Optoelectronic reservoir computing. Sci. Rep. 2, 287 (2012).
pubmed: 22371825
pmcid: 3286854
doi: 10.1038/srep00287
Riou, M. et al. Neuromorphic computing through time-multiplexing with a spin-torque nano-oscillator. 2017 IEEE International Electron Devices Meeting (IEDM) 36.33.31–36.33.34 (IEEE, 2017).
Hénon, M. The Theory of Chaotic Attractors (eds. Hunt, B. R., Li, T.-Y., Kennedy, J. A. & Nusse, H. E.) 94–102 (Springer, New York, NY, 2004).
Dong, E., Du, H. & Gardner, L. An interactive web-based dashboard to track COVID-19 in real time. Lancet Infect. Dis. 20, 533–534 (2020).
pubmed: 32087114
pmcid: 7159018
doi: 10.1016/S1473-3099(20)30120-1
Kim, J. et al. Hardware-based spiking neural network architecture using simplified backpropagation algorithm and homeostasis functionality. Neurocomputing 428, 153–165 (2021).
doi: 10.1016/j.neucom.2020.11.016
Kim, J. et al. Vertical AND-Type Flash Synaptic Cell Stack for High-Density and Reliable Binary Neural Networks. IEEE Electron Device Lett. 45, 1369–1372 (2024).
doi: 10.1109/LED.2024.3401399
Rodan, A. & Tino, P. Minimum complexity echo state network. IEEE Trans. Neural Netw. 22, 131–144 (2011).
pubmed: 21075721
doi: 10.1109/TNN.2010.2089641
Lukosevicius, M. & Jaeger, H. Survey: reservoir computing approaches to recurrent neural network training. Comput. Sci. Rev. 3, 127–149 (2009).
doi: 10.1016/j.cosrev.2009.03.005