Neuro-Inspired Computing With Emerging Nonvolatile Memorys
The DOI matches its Crossref record; 134 of the 141 references it cites were found in a registry or an index.
Abstract
This comprehensive review summarizes state of the art, challenges, and prospects of the neuro-inspired computing with emerging nonvolatile memory devices. First, we discuss the demand for developing neuro-inspired architecture beyond today's von-Neumann architecture. Second, we summarize the various approaches to designing the neuromorphic hardware (digital versus analog, spiking versus nonspiking, online training versus offline training) and discuss why emerging nonvolatile memory is attractive for implementing the synapses in the neural network. Then, we discuss the desired device characteristics of the synaptic devices (e.g., multilevel states, weight update nonlinearity/asymmetry, variation/noise), and survey a few representative material systems and device prototypes reported in the literature that show the analog conductance tuning. These candidates include phase change memory, resistive memory, ferroelectric memory, floating-gate transistors, etc. Next, we introduce the crossbar array architecture to accelerate the weighted sum and weight update operations that are commonly used in the neuro-inspired machine learning algorithms, and review the recent progresses of array-level experimental demonstrations for pattern recognition tasks. In addition, we discuss the peripheral neuron circuit design issues and present a device-circuit-algorithm codesign methodology to evaluate the impact of nonideal device effects on the system-level performance (e.g., learning accuracy). Finally, we give an outlook on the customization of the learning algorithms for efficient hardware implementation.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“To implement neural network computing hardware with a high learning accuracy, a low nonlinearity of synaptic weights with repetitive input pulses and a large on/off synapse conductance ratio are required 36 .”
From Enhanced analog synaptic behavior of SiNx/a-Si bilayer memristors through Ge implantation (2020) · cites this paper as [36]
In the citing paper
“The achieved learning accuracy is very comparable to the state-of-the-art results in the literature 36,46,49 .”
From Enhanced analog synaptic behavior of SiNx/a-Si bilayer memristors through Ge implantation (2020) · cites this paper as [36]
In the citing paper
“A promising solution to this problem is the use of memristor-based systems, which can drastically reduce the energy consumption of AI5,6, making it even conceivable to create self-powered edge AI systems that do not require batteries and can instead harvest energy from the environment.”
From Powering AI at the edge: A robust, memristor-based binarized neural network with near-memory computing and miniaturized solar cell (2024) · cites this paper as [5]
Citations
Cites
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.90 · Cited by 235,474 · cited 1×
“For example, Microsoft’s Res-Net (which won the ImageNet 2015 image classification competition [5]) has more than 100 of layers [6].”
MethodVery Deep Convolutional Networks for Large-Scale Image Recognition
Simonyan, K., & Zisserman, A. (2014) · arXiv · doi:10.48550/arxiv.1409.1556 · Cited by 114,148 · cited 1×
“The adoption of low-precision weight is most suitable for the feedforward inference stage of the CNN models, including LeNet5 [127], AlexNet [3], and VGG [128] in an order of complexity.”
MethodImageNet classification with deep convolutional neural networks
Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2017) · Communications of the ACM · doi:10.1145/3065386 · Cited by 112,155 · cited 2×
“In particular, convolutional neural network (CNN) [3] and recurrent neural network (RNN) [4] algorithms and their variants have proved their efficacy in a wide range of image, video, speech, and biomedical applications.”
BackgroundMethodLeCun, Y., Bengio, Y., & Hinton, G. (2015) · Nature · doi:10.1038/nature14539 · Cited by 84,126
Gradient-based learning applied to document recognition
Lecun, Y., Bottou, L., Bengio, Y., & Haffner, P. (1998) · Proceedings of the IEEE · doi:10.1109/5.726791 · Cited by 58,805 · cited 1×
“The adoption of low-precision weight is most suitable for the feedforward inference stage of the CNN models, including LeNet5 [127], AlexNet [3], and VGG [128] in an order of complexity.”
MethodMastering the game of Go with deep neural networks and tree search
Silver, D., Huang, A., Maddison, C. J., Guez, A., Sifre, L., van den Driessche, G., Schrittwieser, J., Antonoglou, I., Panneershelvam, V., Lanctot, M., et al. (2016) · Nature · doi:10.1038/nature16961 · Cited by 15,612 · cited 1×
“, Google’s AlphaGo [1]).”
Speech recognition with deep recurrent neural networks
Graves, A., Mohamed, A.-R., & Hinton, G. (2013) · 2013 IEEE International Conference on Acoustics, Speech and Signal Processing · doi:10.1109/icassp.2013.6638947 · Cited by 8,893 · cited 1×
“In particular, convolutional neural network (CNN) [3] and recurrent neural network (RNN) [4] algorithms and their variants have proved their efficacy in a wide range of image, video, speech, and biomedical applications.”
BackgroundRedox‐Based Resistive Switching Memories – Nanoionic Mechanisms, Prospects, and Challenges
Waser, R., Dittmann, R., Staikov, G., & Szot, K. (2009) · Advanced Materials · doi:10.1002/adma.200900375 · Cited by 5,080 · cited 1×
“RRAM has two subcategories [44]: one is anion-based oxide random access memory (OxRAM) and the other one is cation-based conductive bridge random access memory (CBRAM) [45].”
BackgroundIn-Datacenter Performance Analysis of a Tensor Processing Unit
Jouppi, N. P., Young, C., Patil, N., Patterson, D., Agrawal, G., Bajwa, R., Bates, S., Bhatia, S., Boden, N., Borchers, A., et al. (2017) · Proceedings of the 44th Annual International Symposium on Computer Architecture · doi:10.1145/3079856.3080246 · Cited by 4,537
XNOR-Net: ImageNet Classification Using Binary Convolutional Neural Networks
Rastegari, M., Ordonez, V., Redmon, J., & Farhadi, A. (2016) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-46493-0_32 · Cited by 4,408 · cited 1×
“A similar work that constraints the weights and neurons to be (+1, −1), namely XNOR-Net [130], has been demonstrated for the classification of ImageNet data set with slight degradation of accuracy.”
Background
Research works printed but not linked: 9
- jouppi, 2016, Google Supercharges Machine Learning Tasks with TPU Custom Chip
- manan, 2012, CBRAM devices as binary synapses for low-power stochastic neuromorphic systems: Auditory (cochlea) and visual (retina) cognitive processing applications, IEDM Tech Dig
- 0, The MNIST dataset of handwritten digits
- 0, Image
- liu, 2013, A 130.7 mm $^{2}~2$ -layer 32 Gb ReRAM memory device in 24nm technology, IEEE Int Solid-State Circuits Conf (ISSCC) Dig Tech Papers, 31.6.1
- 0, Theano
- govoreanu, 2011, $10\times 10$ nm2 Hf/HfOx crossbar resistive RAM with excellent performance, reliability and low-energy operation, IEDM Tech Dig
- 0, Yale Face Database
- 0, NeuroSim
Cited by
Items 301–400 of 1,001
An Organic Flexible Artificial Bio-Synapses with Long-Term Plasticity for Neuromorphic Computing
Wang, T.-Y., He, Z., Chen, L., Zhu, H., Sun, Q., Ding, S., Zhou, P., & Zhang, D. W. (2018) · Micromachines · doi:10.3390/mi9050239 · Cited by 41
“Gradual modulated conductance is important for a synaptic device towards neuromorphic computing [30].”
BackgroundComputing-in-Memory with SRAM and RRAM for Binary Neural Networks
Sun, X., Liu, R., Peng, X., & Yu, S. (2018) · IEEE International Conference on Solid-State and Integrated Circuit Technology · doi:10.1109/icsict.2018.8565811 · Cited by 47
“Meanwhile, researchers have also proposed using emerging non-volatile memories (eNVMs) with much less area (than SRAM at the same technology node) such as resistive random access memory (RRAM) [9] and phase change memory (PCM) [10] to implement synaptic weights, where the computations are naturally performed in a true…”
BackgroundSelf-citationLee, H., Jin, M., Na, H., Im, C., Lee, J., Kim, J., Gong, Y. J., Lee, C. Y., Lee, E., & Kim, Y. S. (2021) · Advanced Functional Materials · doi:10.1002/adfm.202110591 · Cited by 41
Nanowire-based synaptic devices for neuromorphic computing
Chen, X., Chen, B., Zhao, P., Roy, V. A. L., Han, S., & Zhou, Y. (2023) · Materials Futures · doi:10.1088/2752-5724/acc678 · Cited by 41
“…devices need to meet the following performance indicators: high linearity of conductance, the ratio of maximum conductivity and minimum conductivity should be larger than 10, the data levels should be larger than 32, and small variation of cycle-to-cycle/device-to-device performance [65, 66].”
BackgroundRealizing In-Memory Baseband Processing for Ultrafast and Energy-Efficient 6G
Zeng, Q., Liu, J., Jiang, M., Lan, J., Gong, Y., Wang, Z., Li, Y., Li, C., Ignowski, J., & Huang, K. (2023) · IEEE Internet of Things Journal · doi:10.1109/jiot.2023.3307405 · Cited by 43
“It is expressed as the percentage of the entire conductance range in the existing literature [59], [60], [61], [62].”
BackgroundIslam, R., Shi, Y., Silva, G. V. D. O., Sachdev, M., & Miao, G. (2024) · ACS Nano · doi:10.1021/acsnano.4c05137 · Cited by 43
Eom, D., Kim, H., Lee, W., Park, C., Park, J., Lee, H.-S., Kim, T., Nam, S., Kim, Y.-H., & Kim, H. (2025) · Nano Energy · doi:10.1016/j.nanoen.2025.110837 · Cited by 40
Unsupervised Learning to Overcome Catastrophic Forgetting in Neural Networks
Muñoz-Martín, I., Bianchi, S., Pedretti, G., Melnic, O., Ambrogio, S., & Ielmini, D. (2019) · IEEE Journal on Exploratory Solid-State Computational Devices and Circuits · doi:10.1109/jxcdc.2019.2911135 · Cited by 40
“7 and 9) [29], neural networks with supervised training also can take advantage of PCM, thanks to its excellent scaling and multilevel state operation [32]–[34].”
BackgroundA Two-way SRAM Array based Accelerator for Deep Neural Network On-chip Training
Jiang, H., Huang, S., Peng, X., Su, J.-W., Chou, Y.-C., Huang, W.-H., Liu, T.-W., Liu, R., Chang, M., & Yu, S. (2020) · ACM/IEEE Design Automation Conference (DAC) · doi:10.1109/dac18072.2020.9218524 · Cited by 44
“On the other hand, CIM is an efficient paradigm to address the memory wall problem [5].”
BackgroundSelf-citationJing, Z., Yan, B., Yang, Y., & Huang, R. (2022) · IEEE Transactions on Circuits and Systems I Regular Papers · doi:10.1109/tcsi.2022.3186024 · Cited by 44
Brain-inspired computing systems: a systematic literature review
Zolfagharinejad, M., Alegre-Ibarra, U., Chen, T., Kinge, S., & van der Wiel, W. G. (2024) · The European Physical Journal B · doi:10.1140/epjb/s10051-024-00703-6 · Cited by 39
Pedretti, G., Ambrosi, E., & Ielmini, D. (2021) · 2021 IEEE International Reliability Physics Symposium (IRPS) · doi:10.1109/irps46558.2021.9405130 · Cited by 39
“Since MVM is conducted simultaneously in one shot, it allows a significant acceleration of complex tasks, such as neural network training and inference [6], [7].”
BackgroundNeuromorphic Floating-Gate Memory Based on 2D Materials
Hu, C., Liang, L., Yu, J., Cheng, L., Zhang, N., Wang, Y., Wei, Y., Fu, Y., Wang, Z. L., & Sun, Q. (2025) · Cyborg and Bionic Systems · doi:10.34133/cbsystems.0256 · Cited by 43
“Furthermore, FG transistors incorporating 2D materials have prominent advantages in realizing certain types of synaptic behaviors and functions due to the nonvolatile nature, especially LTP and LTD involving long-term information storage and learning capabilities of neural synapses [ 194 , 195 ].”
Indium–Gallium–Zinc–Oxide Schottky Synaptic Transistors for Silent Synapse Conversion Emulation
He, Y., Nie, S., Liu, R., Shi, Y., & Wan, Q. C. (2018) · IEEE Electron Device Letters · doi:10.1109/led.2018.2883442 · Cited by 40
Analog switching characteristics in TiW/Al2O3/Ta2O5/Ta RRAM devices
Song, W., Wang, W., Lee, H. K., Li, M., Zhuo, V. Y.-Q., Chen, Z., Chui, K. J., Liu, J.-C., Wang, I., Zhu, Y. H., et al. (2019) · Applied Physics Letters · doi:10.1063/1.5100075 · Cited by 41
Liu, B., Wei, T., Hu, J., Li, W., Ling, Y. H., Liu, Q., Cheng, M., & Song, Z. (2021) · Chinese Physics B · doi:10.1088/1674-1056/abeedf · Cited by 39
Iqbal, S., Duy, L. T., Kang, H., Singh, R., Kumar, M., Park, J., & Seo, H. (2021) · Advanced Functional Materials · doi:10.1002/adfm.202102567 · Cited by 39
Ismail, M., Mahata, C., & Kim, S. (2022) · Applied Surface Science · doi:10.1016/j.apsusc.2022.153906 · Cited by 39
Wang, J., Bai, Y., Wang, H., Hao, Z., Wang, G., Zhang, K., Zhang, Y., Lv, W., & Zhang, Y. (2022) · IEEE Transactions on Circuits and Systems I Regular Papers · doi:10.1109/tcsi.2022.3192165 · Cited by 43
“Therefore, in the Von Neuman architecture separating the memory and processor, the limited throughput and large energy of the date bus communication between memory and processor become the major constraints for the processing performance of massive data [4], [5].”
BackgroundBasnet, P., Pahinkar, D. G., West, M. P., Perini, C. J., Graham, S., & Vogel, E. M. (2020) · Journal of Materials Chemistry C · doi:10.1039/c9tc06736a · Cited by 38
Luo, Y., Han, X., Ye, Z., Barnaby, H., Seo, J.-S., & Yu, S. (2020) · IEEE Transactions on Electron Devices · doi:10.1109/ted.2020.3015940 · Cited by 40
“with emerging nonvolatile memory are proposed [1], which reduce the excessive data movement between computing and storage units.”
BackgroundSelf-citationChen, Z., Wu, M., Zhou, Y., Li, R., Tan, J., & Ding, D. (2023) · IEEE Transactions on Very Large Scale Integration (VLSI) Systems · doi:10.1109/tvlsi.2023.3277517 · Cited by 37
Ferroelectric capacitive memories: devices, arrays, and applications
Zhou, Z., Jiao, L., Zheng, Z., Chen, Y., Han, K., Kang, Y., Zhang, D., Wang, X., Kong, Q., Sun, C., et al. (2025) · Nano Convergence · doi:10.1186/s40580-024-00463-0 · Cited by 39
Li, J., Yang, Y., Chen, Q., Zhu, W., & Zhang, J. (2020) · Journal of Materials Chemistry C · doi:10.1039/c9tc05765j · Cited by 37
Brivio, S., Ly, D. R. B., Vianello, E., & Spiga, S. (2021) · Frontiers in Neuroscience · doi:10.3389/fnins.2021.580909 · Cited by 39
“These considerations are completely independent from the effect of the noise and variability that unavoidably affect any real memristive device (Yu et al., 2013; Frascaroli et al., 2015, 2018; Covi et al., 2016; Brivio et al., 2017, 2019b).”
BackgroundAguirre, F. L., Pazos, S. M., Palumbo, F., Sune, J., & Miranda, E. (2020) · IEEE Access · doi:10.1109/access.2020.3035638 · Cited by 36
“Therefore, the limitation is not in the CPA implementation but in the Neural Network itself, i.e. for this kind of datasets more complex networks are required, as shown in [90], [100], where a Deep Neural Network comprising 6 Convolutional Layers and 2 Fully Connected layers are considered.”
MethodThe Role of Vacancy Dynamics in Two‐Dimensional Memristive Devices
Spetzler, B., Abdel, D., Schwierz, F., Ziegler, M., & Farrell, P. (2023) · Advanced Electronic Materials · doi:10.1002/aelm.202300635 · Cited by 38
A Review of Recent Developments in Neuromorphic Computing Based on Emerging Memory Devices
Sun, J., Sun, Y., Li, X., Sun, Y., Hong, Q., & Wang, C. (2025) · Nonlinear Dynamics · doi:10.1007/s11071-025-11727-7 · Cited by 38
“Meanwhile, as complementary metal oxide semiconductor (CMOS) technology approaches its physical limits, the failure of Dennard scaling will lead to stagnation in improvements in energy efficiency [2].”
Review of applications of 2D materials in memristive neuromorphic circuits
Wang, L., Shen, X., Gao, Z., Fu, J., Yao, S., Cheng, L., & Lian, X. (2022) · Journal of Materials Science · doi:10.1007/s10853-022-06954-x · Cited by 37
“V curves measured during the set/reset processes deviate from this requirement, thereby reducing the application prospects of ANNs [46, 47].”
BackgroundInfluentialElectrochemical Analysis of Ion Effects on Electrolyte-Gated Synaptic Transistor Characteristics
Lee, H., Cho, J., Jin, M., Lee, J., Lee, C. Y., Kim, J., Lee, J., Shin, J. C., Yoo, J., Lee, E., et al. (2024) · ACS Nano · doi:10.1021/acsnano.3c10082 · Cited by 35
Safari, M. M., & Pourrostam, J. (2024) · Signal Processing · doi:10.1016/j.sigpro.2024.109446 · Cited by 36
Resistive memory-based zero-shot liquid state machine for multimodal event data learning
Lin, N., Wang, S., Li, Y., Wang, B., Shi, S., He, Y., Zhang, W., Yu, Y., Zhang, Y., Zhang, X., et al. (2025) · Nature Computational Science · doi:10.1038/s43588-024-00751-z · Cited by 41
PIMBALL: Binary Neural Networks in Spintronic Memory
Resch, S., Khatamifard, S. K., Chowdhury, Z. I., Zabihi, M., Zhao, Z., Wang, J., Sapatnekar, S. S., & Karpuzcu, U. R. (2019) · ACM Transactions on Architecture and Code Optimization · doi:10.1145/3357250 · Cited by 38
“st 2018. PIMBALL: Binary Neural Networks in Spintronic Memory 111:23 cannot support BNN acceleration without modification. A review of neuro-inspired computing on non-volatile memories is provided in [43]. 7 CONCLUSION In this paper, we explored the design space of binary neural network (BNN) (forward propagation) acc…”
BackgroundIon-gating synaptic transistors with long-term synaptic weight modulation
Park, Y., Kim, M., & Lee, J. (2021) · Journal of Materials Chemistry C · doi:10.1039/d1tc00048a · Cited by 36
Ferroelectric Tunnel Junction Based Crossbar Array Design for Neuro-Inspired Computing
Luo, Y.-C., Hur, J. H., & Yu, S. (2021) · IEEE Transactions on Nanotechnology · doi:10.1109/tnano.2021.3066319 · Cited by 35
“To address this problem, researchers have proposed using crossbar memory arrays to perform neuro-inspired computing efficiently [3].”
BackgroundMethodSelf-citationCao, T., Liu, C., Wang, W., Zhang, T., Lee, H. K., Li, M. H., Song, W., Chen, Z. X., Zhuo, V. Y.-Q., Wang, N., et al. (2022) · IEEE Journal on Emerging and Selected Topics in Circuits and Systems · doi:10.1109/jetcas.2022.3214334 · Cited by 34
“Furthermore, by applying input voltage vector and sense the output current, the vector-matrix multiplication (VMM) operation can be implemented in a parallel manner naturally, leading to significant computation acceleration [9], [10], [11].”
MethodMultielement Filament Memristor Enabling Multifunctional Neuromorphic Device
Jang, M., Song, H., Kim, H. J., Yoon, J. H., & Kim, K. M. (2025) · Advanced Functional Materials · doi:10.1002/adfm.202423273 · Cited by 35
Memristor-based adaptive analog-to-digital conversion for efficient and accurate compute-in-memory
Hong, H., Du, Z., Jiang, M., Mao, R., Ren, Y., Li, F., Mao, W., Peng, M., Zhang, W., Liu, Z., et al. (2025) · Nature Communications · doi:10.1038/s41467-025-65233-w · Cited by 37
“This integration overcomes the von Neumann bottleneck and enables ef fi cient vector-matrix multi-plications (VMMs) for deep learning operations 15,20 – 23 .”
Cross-point Resistive Memory: Nonideal Properties and Solutions
Wang, C., Feng, D., Tong, W., Liu, J., Li, Z., Chang, J., Zhang, Y., Wu, B., Xu, J., Zhao, W. J., et al. (2019) · ACM Transactions on Design Automation of Electronic Systems · doi:10.1145/3325067 · Cited by 40
“, ferroelectric FET [78, 79], similarly to the floating-gate FET-based flash memory cell [22, 77, 178, 208].”
BackgroundLinearity improvement of HfOx-based memristor with multilayer structure
Jiang, Y., Zhang, K., Hu, K., Zhang, Y., Liang, A., Song, Z., Song, S., & Wang, F. (2021) · Materials Science in Semiconductor Processing · doi:10.1016/j.mssp.2021.106131 · Cited by 34
SNR: S queezing N umerical R ange Defuses Bit Error Vulnerability Surface in Deep Neural Networks
Ozen, E., & Orailoğlu, A. (2021) · ACM Transactions on Embedded Computing Systems · doi:10.1145/3477007 · Cited by 39
“Moreover, the error resilience of deep neural networks can facilitate novel computation paradigms [73], and novel communication fabrics through photonics, wireless, or 3D interconnects [46] when the inherent inaccuracy and manufacturing issues for such emerging technologies can be endured through the algorithmic resil…”
BackgroundSecure XOR-CIM Engine: Compute-In-Memory SRAM Architecture With Embedded XOR Encryption
Huang, S., Jiang, H., Peng, X., Li, W., & Yu, S. (2021) · IEEE Transactions on Very Large Scale Integration (VLSI) Systems · doi:10.1109/tvlsi.2021.3120296 · Cited by 36
Self-citationAjayan, J., Nirmal, D., I.V, B. K. J., & Sreejith, S. (2022) · Microelectronics Journal · doi:10.1016/j.mejo.2022.105634 · Cited by 41
Using Memristors for Robust Local Learning of Hardware Restricted Boltzmann Machines
Ernoult, M., Grollier, J., & Querlioz, D. (2019) · Scientific Reports · doi:10.1038/s41598-018-38181-3 · Cited by 38
ITT-RNA: Imperfection Tolerable Training for RRAM-Crossbar-Based Deep Neural-Network Accelerator
Song, Z., Sun, Y., Chen, L., Li, T., Jing, N., Liang, X., & Jiang, L. (2020) · IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems · doi:10.1109/tcad.2020.2989373 · Cited by 36
“The mapping scheme we use is a proportional mapping scheme, which makes the weights being proportional to conductances [24].”
MethodINCA: Input-stationary Dataflow at Outside-the-box Thinking about Deep Learning Accelerators
Kim, B., Li, S., & Li, H. H. (2023) · IEEE International Symposium on High-Performance Computer Architecture (HPCA) · doi:10.1109/hpca56546.2023.10070992 · Cited by 37
Ahn, W., Jeong, H. B., Oh, J., Hong, W., Cha, J., Jeong, H. Y., & Choi, S. (2023) · Small · doi:10.1002/smll.202300223 · Cited by 33
Xiang, Y., Huang, P. C., Han, R., Li, C., Wang, K., Liu, X., & Kang, J. (2020) · IEEE Transactions on Electron Devices · doi:10.1109/ted.2020.2987439 · Cited by 33
“Hence, researchers are exploring strategies to improve the computing speed and the energy efficiency of the CNN based on von Neumann processors [7]–[9].”
BackgroundMethodNiu, J., Fang, Z., Liu, G., Zhao, Z., & Yan, X. (2022) · Science China Materials · doi:10.1007/s40843-022-2237-2 · Cited by 32
“In the training of neural network computing systems, online training of the conductance of synaptic devices is frequently updated, so a large number of conductance states make the training more efficient [31].”
BackgroundWang, J., Pan, X., Zhao, Z., Xie, Y., Luo, W., Xie, Q., Zeng, H., Shuai, Y., Song, Z., Wu, C., et al. (2023) · Advanced Science · doi:10.1002/advs.202307359 · Cited by 32
Jin, M., Cheng, L., Li, Y., Hu, S., Lu, K., Chen, J., Duan, N., Wang, Z., Zhou, Y., Chang, T., et al. (2018) · Nanotechnology · doi:10.1088/1361-6528/aacf84 · Cited by 32
Spike-driven threshold-based learning with memristive synapses and neuromorphic silicon neurons
Covi, E., George, R., Frascaroli, J., Brivio, S., Mayr, C., Mostafa, H., Indiveri, G., & Spiga, S. (2018) · Journal of Physics D Applied Physics · doi:10.1088/1361-6463/aad361 · Cited by 32
Perspective: Uniform switching of artificial synapses for large-scale neuromorphic arrays
Tan, S. H., Lin, P., Yeon, H., Choi, S., Park, Y., & Kim, J. (2018) · APL Materials · doi:10.1063/1.5049137 · Cited by 33
Nath, S. K., Nandi, S. K., Li, S., & Elliman, R. G. (2020) · Nanotechnology · doi:10.1088/1361-6528/ab7889 · Cited by 32
Chang, L.-Y., Simanjuntak, F. M., Hsu, C.-L., Chandrasekaran, S., & Tseng, T. (2020) · Applied Physics Letters · doi:10.1063/5.0014829 · Cited by 32
Resistive Neural Hardware Accelerators
Smagulova, K., Fouda, M. E., Kurdahi, F. J., Salama, K. N., & Eltawil, A. M. (2023) · Proceedings of the IEEE · doi:10.1109/jproc.2023.3268092 · Cited by 35
“Nonlinear and asymmetric update dynamics in some RRAM devices hinder large-scale deployment in neural networks [122].”
BackgroundThe Impact of Thermal Enhance Layers on the Relaxation Effect in Analog RRAM
Xi, Y., Tang, J., Gao, B., Xu, F., Li, X., Lu, Y., Qian, H., & Wu, H. (2022) · IEEE Transactions on Electron Devices · doi:10.1109/ted.2022.3183958 · Cited by 33
Electrical Performance of Large-Area Y2O3 Memristive Crossbar Array With Ultralow C2C Variability
Kumar, S., Agarwal, A., & Mukherjee, S. (2022) · IEEE Transactions on Electron Devices · doi:10.1109/ted.2022.3172400 · Cited by 32
Inversion-Type Ferroelectric Capacitive Memory and Its 1-Kbit Crossbar Array
Zhou, Z., Jiao, L., Zhou, J., Zheng, Z., Chen, Y., Han, K., Kang, Y., & Gong, X. (2023) · IEEE Transactions on Electron Devices · doi:10.1109/ted.2023.3243556 · Cited by 32
“While the endurance performance can satisfy the requirement for long-term data storage and some neuromorphic computing tasks [3], further improvement is required and can be realized by optimizing the FE”
BackgroundKwon, D., Park, E. C., Shin, W., Koo, R., Hwang, J., Bae, J., Kwon, D., & Lee, J. (2023) · Advanced Intelligent Systems · doi:10.1002/aisy.202300125 · Cited by 34
Hybrid Optical/Electric Memristor for Light-Based Logic and Communication
Cai, S., Tzou, C.-Y., Liou, Y., Chen, D., Jiang, C.-Y., Ma, J.-M., Chang, C., Tseng, C.-Y., Liao, Y., Hsieh, Y., et al. (2019) · ACS Applied Materials & Interfaces · doi:10.1021/acsami.8b19424 · Cited by 31
Benchmarking Delay and Energy of Neural Inference Circuits
Nikonov, D. E., & Young, I. A. (2019) · IEEE Journal on Exploratory Solid-State Computational Devices and Circuits · doi:10.1109/jxcdc.2019.2956112 · Cited by 35
“We are cognizant of the importance of the accuracy of inferencing, and indeed, prior studies discovered that this accuracy can be degraded compared to the algorithm-limited ‘‘maximum accuracy’’ due to device nonidealities [15].”
ResultDesign of Non-volatile Capacitive Crossbar Array for In-Memory Computing
Luo, Y.-C., Lu, A., Hur, J. H., Li, S., & Yu, S. (2021) · IEEE International Memory Workshop (IMW) · doi:10.1109/imw51353.2021.9439603 · Cited by 31
“In-memory computing [1] is proposed to accelerate the intensive vector-matrix multiplication in deep learning algorithms, where the operations of multiplication and sum are performed in parallel.”
BackgroundSelf-citationMatsui, C., Toprasertpong, K., Takagi, S., & Takeuchi, K. (2021) · Symposium on VLSI Circuits · doi:10.23919/vlsicircuits52068.2021.9492448 · Cited by 31
Moazzeni, A., Madvar, H. R., Hamedi, S., & Kordrostami, Z. (2023) · ACS Applied Nano Materials · doi:10.1021/acsanm.2c05497 · Cited by 31
Siannas, N., Zacharaki, C., Tsipas, P., Kim, D. J., Hamouda, W., Istrate, M. C., Pintilie, L., Schmidbauer, M., Dubourdieu, C., & Dimoulas, A. (2023) · Advanced Functional Materials · doi:10.1002/adfm.202311767 · Cited by 31
Mitigate Parasitic Resistance in Resistive Crossbar-based Convolutional Neural Networks
Zhang, F., & Hu, M. (2020) · ACM Journal on Emerging Technologies in Computing Systems · doi:10.1145/3371277 · Cited by 31
“usually inevitable, which lead to significant delay and energy cost. To overcome the memory bottleneck, many researchers show interest in resistive crossbar arrays for the computing-in-memory feature [1, 8, 14, 21, 25, 41]. The resistive crossbar is defined as a circuit structure with vertical and horizontal metal lin…”
BackgroundGiovinazzo, C., Sandrini, J., Shahrabi, E., Celik, O. T., Leblebici, Y., & Ricciardi, C. (2019) · ACS Applied Electronic Materials · doi:10.1021/acsaelm.9b00094 · Cited by 30
Kim, D., Jang, J. T., Yu, E., Park, J., Min, J., Kim, D. M., Choi, S., Mo, H.-S., Cho, S., Roy, K., et al. (2020) · ACS Applied Electronic Materials · doi:10.1021/acsaelm.0c00341 · Cited by 30
Reliable Memristive Synapses Based on Parylene-MoOx Nanocomposites for Neuromorphic Applications
Minnekhanov, A. A., Matsukatova, A. N., Trofimov, A. D., Несмелов, А. А., Zavyalov, S. A., Demin, V. A., & Emelyanov, A. V. (2023) · ACS Applied Materials & Interfaces · doi:10.1021/acsami.3c13956 · Cited by 30
Engineered high endurance in WO 3 -based resistive switching devices via a guided filament approach
Yuan, Z., Bakhit, B., Liu, Y., Sun, Z., Lampronti, G. I., Li, X., Fairclough, S. M., Tsai, B. K., Choudhury, A., Ducati, C., et al. (2025) · Science Advances · doi:10.1126/sciadv.adt9789 · Cited by 30
Suppress variations of analog resistive memory for neuromorphic computing by localizing Vo formation
Wu, W., Wu, H., Gao, B., Deng, N., & Qian, H. (2018) · Journal of Applied Physics · doi:10.1063/1.5037896 · Cited by 29
Investigating Ferroelectric Minor Loop Dynamics and History Effect—Part I: Device Characterization
Wang, P., Wang, Z., Sun, X., Hur, J. H., Datta, S., Khan, A. I., & Yu, S. (2020) · IEEE Transactions on Electron Devices · doi:10.1109/ted.2020.3009623 · Cited by 30
“This demand has been motivating the research and development for emerging nonvolatile memory (NVM) technologies over the last decade [1]–[3].”
BackgroundSelf-citationKim, S., Lee, Y., Kim, H., & Choi, S. (2020) · NPG Asia Materials · doi:10.1038/s41427-020-00258-9 · Cited by 29
Fontanini, R., Barbot, J., Segatto, M., Lancaster, S., Duong, Q. T., Driussi, F., Grenouillet, L., Triozon, F., Coignus, J., Mikolajick, T., et al. (2022) · IEEE Journal of the Electron Devices Society · doi:10.1109/jeds.2022.3171217 · Cited by 29
Interface barrier-induced conversion of resistive switching mechanism in Mn-doped BiFeO3 memristor
Su, R., Cheng, M., Dong, A., Zhao, Y., Cheng, W., Yang, R., Yan, J., & Miao, X. (2022) · Applied Physics Letters · doi:10.1063/5.0127006 · Cited by 29
A memristor-based associative memory neural network circuit with emotion effect
Wang, C., Xu, C., Sun, J., & Deng, Q. (2023) · Neural Computing and Applications · doi:10.1007/s00521-023-08275-9 · Cited by 29
Desai, T. R., Kundale, S. S., Dongale, T. D., & Gurnani, C. (2023) · ACS Applied Bio Materials · doi:10.1021/acsabm.2c01073 · Cited by 29
Bio-inspired artificial synapse for neuromorphic computing based on NiO nanoparticle thin film
Hadiyal, K., Ganesan, R., Rastogi, A., & Thamankar, R. (2023) · Scientific Reports · doi:10.1038/s41598-023-33752-5 · Cited by 32
Kwon, D., Woo, S. Y., Lee, K.-H., Hwang, J., Kim, H., Park, S., Shin, W., Bae, J., Kim, J., & Lee, J. (2023) · Science Advances · doi:10.1126/sciadv.adg9123 · Cited by 29
“However, the increasing area and power overhead of von Neumann computing architectures, mainly induced by the data communication between processing units and memory, have also become very critical issues in DNNs ( 10 – 14 ).”
Enhanced analog synaptic behavior of SiNx/a-Si bilayer memristors through Ge implantation
Kim, K., Park, S., Hu, S. M., Song, J., Lim, W., Jeong, Y., Kim, J., Lee, S., Kwak, J. Y., Park, J., et al. (2020) · NPG Asia Materials · doi:10.1038/s41427-020-00261-0 · Cited by 28
Kim, J., Im, J., Shin, W., Lee, S., Oh, S., Kwon, D., Jung, G., Choi, W. Y., & Lee, J. (2024) · Advanced Science · doi:10.1002/advs.202308460 · Cited by 28
Lee, K. H., Baek, Y., Lin, Q., Chen, J. M., Park, M., Lee, D., Kim, S., & Lee, K. (2020) · Advanced Intelligent Systems · doi:10.1002/aisy.202000202 · Cited by 28
Memristor-Based Image Enhancement: High Efficiency and Robustness
Zhu, R., Tang, Z., Ye, S., Huang, Q., Guo, L., & Chang, S. (2020) · IEEE Transactions on Electron Devices · doi:10.1109/ted.2020.3045684 · Cited by 29
“Moreover, memristors have appropriate write energy and standby power, where the write energy of most resistive random access memory (RRAM) and pulse-code modulation (PCM) devices [1] are around 100 ∼ 10 and 10 ∼ 100 pJ, respectively.”
BackgroundSong, M., Lee, H., Yoon, J. H., Song, Y., Namgung, S. D., Sung, T., Lee, Y., Lee, J., Nam, K. T., & Kwon, J. (2022) · Journal of Material Science and Technology · doi:10.1016/j.jmst.2021.12.016 · Cited by 28
Wang, J., Pan, X., Wang, Q., Luo, W., Shuai, Y., Xie, Q., Zeng, H., Niu, G., Wu, C., & Zhang, W. (2022) · Applied Surface Science · doi:10.1016/j.apsusc.2022.153653 · Cited by 28
Proton-Assisted Redox-Based Three-Terminal Memristor for Synaptic Device Applications
Liu, L., Dananjaya, P. A., Chee, M. Y., Lim, G. J., Lee, C. X. X., & Lew, W. S. (2023) · ACS Applied Materials & Interfaces · doi:10.1021/acsami.3c03974 · Cited by 28
Artificial neural networks based on memristive devices
Ravichandran, V., Li, C., BanaGozar, A., Yang, J. J., & Xia, Q. (2018) · Science China Information Sciences · doi:10.1007/s11432-018-9425-1 · Cited by 29
Ryu, S., Kang, M., Cho, K., & Kim, S. (2024) · Advanced Materials Technologies · doi:10.1002/admt.202302209 · Cited by 27
Multifunctional MEMS, NEMS, micro/nano-structures enabled by piezoelectric and ferroelectric effects
Xiao, M., Xu, A., Sui, Z., Zhang, W., Liu, H., & Lee, C. (2025) · Nanoscale Horizons · doi:10.1039/d5nh00386e · Cited by 28
Kim, J., Kwon, D., Woo, S. Y., Kang, W.-M., Lee, S., Oh, S., Kim, C.-H., Bae, J., Park, B., & Lee, J. (2020) · Neurocomputing · doi:10.1016/j.neucom.2020.11.016 · Cited by 27
Wang, Z., Guan, Z., Sun, H., Luo, Z. L., Zhao, H., Wang, H., Yin, Y., & Li, X. (2022) · ACS Applied Materials & Interfaces · doi:10.1021/acsami.2c04441 · Cited by 27
Electroforming-Free Y2O3Memristive Crossbar Array with Low Variability
Kumar, S., Das, M., Htay, M. T., Sriram, S., & Mukherjee, S. (2022) · ACS Applied Electronic Materials · doi:10.1021/acsaelm.2c00472 · Cited by 27
Cao, T., Liu, C., Gao, Y., & Goh, W. L. (2022) · IEEE Journal on Emerging and Selected Topics in Circuits and Systems · doi:10.1109/jetcas.2022.3172170 · Cited by 27
Evaluation of Radiation Effects in RRAM-Based Neuromorphic Computing System for Inference
Ye, Z., Liu, R., Taggart, J., Barnaby, H., & Yu, S. (2018) · IEEE Transactions on Nuclear Science · doi:10.1109/tns.2018.2886793 · Cited by 28
“further speeding up computation for matrix operations [3].”
BackgroundSelf-citationMAX2: An ReRAM-Based Neural Network Accelerator That Maximizes Data Reuse and Area Utilization
Mao, M., Peng, X., Liu, R., Li, J., Yu, S., & Chakrabarti, C. (2019) · IEEE Journal on Emerging and Selected Topics in Circuits and Systems · doi:10.1109/jetcas.2019.2908937 · Cited by 27
“So in this paper, we consider the 1T1R structure, where the bit-lines (BLs) and the source-lines (SLs) are perpendicular to form a “pseudo-crossbar” [23].”
BackgroundSelf-citationFeng, Y., Huang, P. C., Zhou, Z., Ding, X., Liu, L., Liu, X., & Kang, J. (2019) · Nanoscale Research Letters · doi:10.1186/s11671-019-2885-2 · Cited by 26
Multiscale Modeling for Application-Oriented Optimization of Resistive Random-Access Memory
Torraca, P. L., Puglisi, F. M., Padovani, A., & Larcher, L. (2019) · Materials · doi:10.3390/ma12213461 · Cited by 29
“Metric NVM 1 [26] DNN 2 [39] SNN 3 [40]”
BackgroundMethodNguyen, M.-C., Lee, K., Kim, S., Youn, S., Hwang, Y., Kim, H., Choi, R., & Kwon, D. (2021) · IEEE Electron Device Letters · doi:10.1109/led.2021.3127927 · Cited by 26
3D AND-Type Ferroelectric Transistors for Compute-in-Memory and the Variability Analysis
Choe, G., Lu, A., & Yu, S. (2021) · IEEE Electron Device Letters · doi:10.1109/led.2021.3139574 · Cited by 28
Self-citation
Metadata
- Authors
- Yu, S.
- Affiliations
- Arizona State University (US)
- Corresponding author
- Yu, Shimeng
- ORCID
- Yu, Shimeng
- Venue
- Proceedings of the IEEE
- Published
- 2018-02
- Volume
- 106
- Issue
- 2
- Pages
- 260-285
- ISSN
- 0018-9219 (ISSN-L)
- 1558-2256
- OpenAlex
- W2785141883
- Cited by
- 1,170
- References
- 141
- Citations by year
- 2026: 96 · 2025: 139 · 2024: 138 · 2023: 148 · 2022: 177 · 2021: 146 · 2020: 162 · 2019: 117 · 2018: 47
- FWCI
- 45.15
- Type
- journal article
- Language
- en
- Open access
- closed
- Licence
- Locations
- Proceedings of the IEEE (publishedVersion)
- Funders
- NSF-CCF (NSF-CCF-1552687)
- NSFCCF (NSFCCF-1715443)
- NSF-ECCS (NSF-ECCS-1701565)
- HDTRA (HDTRA1-17-1-0038)
- NSF/SRC (NSF/SRC E2CDA)
- ASCENT (one of the six SRC/DARPA JUMP Centers)
- Qualcomm
- Samsung
- Topics
- Physical Sciences › Engineering › Electrical and Electronic Engineering › Advanced Memory and Neural Computing
- Physical Sciences › Engineering › Electrical and Electronic Engineering › Ferroelectric and Negative Capacitance Devices
- Physical Sciences › Computer Science › Artificial Intelligence › Neural Networks and Reservoir Computing
- Keywords
- neuromorphic computing, neuromorphic hardware, non-volatile memory, artificial synapses, phase-change memory, resistive random access memory, ferroelectric memory, floating-gate transistors, pattern recognition
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.