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 101–200 of 1,001
Kim, I., Kim, M., & Lee, J. (2023) · Nature Communications · doi:10.1038/s41467-023-36270-0 · Cited by 120
Reservoir Computing with Charge‐Trap Memory Based on a MoS 2 Channel for Neuromorphic Engineering
Farronato, M., Mannocci, P., Melegari, M., Ricci, S., Compagnoni, C. M., & Ielmini, D. (2022) · Advanced Materials · doi:10.1002/adma.202205381 · Cited by 122
Back-End, CMOS-Compatible Ferroelectric Field-Effect Transistor for Synaptic Weights
Halter, M., Bégon‐Lours, L., Bragaglia, V., Sousa, M., Offrein, B. J., Abel, S., Luisier, M., & Fompeyrine, J. (2020) · ACS Applied Materials & Interfaces · doi:10.1021/acsami.0c00877 · Cited by 116
A Low-Power Si:Hfo2 Ferroelectric Tunnel Memristor for Spiking Neural Networks
Yan, X., Jia, X., Zhang, Y., Shi, S., Wang, L., Shao, Y., Sun, Y., Sun, S., Zhao, Z., Zhao, J., et al. (2022) · Nano Energy · doi:10.1016/j.nanoen.2022.108091 · Cited by 109
Oh, S., Cho, J., Lee, B. H., Seo, S., Lee, J.-H., Choo, H., Heo, K., Lee, S. Y., & Park, J. (2021) · Science Advances · doi:10.1126/sciadv.abg9450 · Cited by 108
“Therefore, to map the synaptic weights of the designed fully connected HW-NN, a synaptic array of at least 15 × 8 × 2 is required.”
BackgroundInfluentialReconfigurable field effect transistors: A technology enablers perspective
Mikolajick, T., Galderisi, G., Rai, S., Simon, M., Böckle, R., Sistani, M., Çakırlar, Ç., Bhattacharjee, N., Mauersberger, T., Heinzig, A., et al. (2022) · Solid-State Electronics · doi:10.1016/j.sse.2022.108381 · Cited by 108
“For example, the XNOR operation, which can be implemented very efficiently in RFET technology, represents the matrix – vector multiplication of binary neural networks (BNN) capable of simplifying computation and network complexity [129].”
MethodDomains and domain dynamics in fluorite-structured ferroelectrics
Lee, D. H., Lee, Y. H., Yang, K., Park, J. Y., Kim, S. H., Reddy, P. R. S., Materano, M., Mulaosmanovic, H., Mikolajick, T., Jones, J. L., et al. (2021) · Applied Physics Reviews · doi:10.1063/5.0047977 · Cited by 112
Recent Progress on Emerging Transistor‐Based Neuromorphic Devices
He, Y., Zhu, L. Q., Zhu, Y., Chen, C., Jiang, S., Liu, R., Shi, Y., & Wan, Q. C. (2021) · Advanced Intelligent Systems · doi:10.1002/aisy.202000210 · Cited by 110
Applications and Techniques for Fast Machine Learning in Science
Deiana, A. M., Tran, N. V., Agar, J., Blott, M., Guglielmo, G. D., Duarte, J. M., Harris, P. C., Hauck, S., Liu, M., Neubauer, M. S., et al. (2022) · Frontiers in Big Data · doi:10.3389/fdata.2022.787421 · Cited by 126
Two-Dimensional Materials for Brain-Inspired Computing Hardware
Hadke, S. S., Kang, M., Sangwan, V. K., & Hersam, M. C. (2025) · Chemical Reviews · doi:10.1021/acs.chemrev.4c00631 · Cited by 112
A van der Waals Synaptic Transistor Based on Ferroelectric Hf0.5Zr0.5O2 and 2D Tungsten Disulfide
Chen, L., Wang, L., Peng, Y., Feng, X., Sarkar, S., Li, S., Li, B., Liu, L., Han, K., Gong, X., et al. (2020) · Advanced Electronic Materials · doi:10.1002/aelm.202000057 · Cited by 109
Ferroelectric-based synapses and neurons for neuromorphic computing
Covi, E., Mulaosmanovic, H., Max, B., Slesazeck, S., & Mikolajick, T. (2022) · Neuromorphic Computing and Engineering · doi:10.1088/2634-4386/ac4918 · Cited by 110
In-Memory Computing with Resistive Memory Circuits: Status and Outlook
Pedretti, G., & Ielmini, D. (2021) · Electronics · doi:10.3390/electronics10091063 · Cited by 112
“This property is extremely difficult to achieve with resistive memory technologies due to the tendency for abrupt increase/decrease of conductivity, followed by a saturating change of conductance [3,92].”
BackgroundZhong, G., Zi, M., Ren, C., Xiao, Q., Tang, M., Wei, L., An, F., Xie, S., Wang, J., Zhong, X., et al. (2020) · Applied Physics Letters · doi:10.1063/5.0013638 · Cited by 103
Peng, X., Liu, R., & Yu, S. (2019) · IEEE Transactions on Circuits and Systems I Regular Papers · doi:10.1109/tcsi.2019.2958568 · Cited by 108
“With the mature one-transistor-one-resistor (1T1R) pseudo-crossbar structure, the analog vector-matrix multiplication can be efficiently performed by exploiting the multilevel states of RRAM devices as “analog” synapses [9].”
MethodSelf-citationLow‐Power Computing with Neuromorphic Engineering
Liu, D., Yu, H., & Chai, Y. (2020) · Advanced Intelligent Systems · doi:10.1002/aisy.202000150 · Cited by 113
Sun, Y., Ding, Y., & Xie, D. (2021) · Advanced Functional Materials · doi:10.1002/adfm.202105625 · Cited by 103
Yan, B., Li, B., Qiao, X., Xue, C.-X., Chang, M., Chen, Y., & Li, H. (. (2019) · Advanced Intelligent Systems · doi:10.1002/aisy.201900068 · Cited by 95
In-Memory and Error-Immune Differential RRAM Implementation of Binarized Deep Neural Networks
Bocquet, M., Hirztlin, T., Klein, J.-O., Nowak, E., Vianello, E., Portal, J.-M., & Querlioz, D. (2018) · 2018 IEEE International Electron Devices Meeting (IEDM) · doi:10.1109/iedm.2018.8614639 · Cited by 99
Soft eSkin: distributed touch sensing with harmonized energy and computing
Soni, M., & Dahiya, R. (2019) · Philosophical Transactions of the Royal Society A Mathematical Physical and Engineering Sciences · doi:10.1098/rsta.2019.0156 · Cited by 107
“The state-of-the-art memristor feature size reported is around 10 nm, while in theory, it can be scaled to the atomic level [55, 77, 82, 83, 85, 108, 113, 138, 175].”
BackgroundMethodInfluentialTimely: Pushing Data Movements And Interfaces In Pim Accelerators Towards Local And In Time Domain
Li, W., Xu, P., Zhao, Y., Li, H., Xie, Y., & Lin, Y. (2020) · 2020 ACM/IEEE 47th Annual International Symposium on Computer Architecture (ISCA) · doi:10.1109/isca45697.2020.00073 · Cited by 89
“Specifically, the average energy of one high-cost memory access in PRIME is about 9× and 33× higher than that of P-subBufs and X-subBufs [79] in TIMELY, respectively.”
BackgroundArtificial synapses enabled neuromorphic computing: From blueprints to reality
Li, J., Shen, Z., Cao, Y., Tu, X., Zhao, C., Liu, Y., & Wen, Z. (2022) · Nano Energy · doi:10.1016/j.nanoen.2022.107744 · Cited by 94
Manufacturing of graphene based synaptic devices for optoelectronic applications
Zhou, K., Jia, Z., Ma, X., Niu, W., Zhou, Y. D., Huang, N., Ding, G., Yan, Y., Han, S., Roy, V. A. L., et al. (2023) · International Journal of Extreme Manufacturing · doi:10.1088/2631-7990/acee2e · Cited by 97
Hirtzlin, T., Bocquet, M., Penkovsky, B., Klein, J.-O., Nowak, E., Vianello, E., Portal, J.-M., & Querlioz, D. (2020) · Frontiers in Neuroscience · doi:10.3389/fnins.2019.01383 · Cited by 93
“This analog approach can be transposed directly to binarized neural networks (Tang et al., 2017; Sun et al., 2018a,b; Yu, 2018).”
BackgroundMethodInfluentialMoS2 Synapses with Ultra-low Variability and Their Implementation in Boolean Logic
Krishnaprasad, A., Dev, D., Han, S. S., Shen, Y., Chung, H., Bae, T., Yoo, C., Jung, Y., Lanza, M., & Roy, T. (2022) · ACS Nano · doi:10.1021/acsnano.1c09904 · Cited by 94
Memristive Devices and Networks for Brain‐Inspired Computing
Zhang, T., Ke, Y., Xu, X., Cai, Y., Yang, Y., & Huang, R. (2019) · physica status solidi (RRL) - Rapid Research Letters · doi:10.1002/pssr.201900029 · Cited by 95
Huang, C., Chang, H., Yang, T., Wang, Y., Chueh, Y., & Nomura, K. (2021) · ACS Applied Materials & Interfaces · doi:10.1021/acsami.1c18329 · Cited by 91
Nanoengineering of Tin Monosulfide (SnS)‐Based Structures for Emerging Applications
Zi, Y., Zhu, J., Hu, L., Wang, M., & Huang, W. (2021) · Small Science · doi:10.1002/smsc.202100098 · Cited by 90
MemTorch: An Open-source Simulation Framework for Memristive Deep Learning Systems
Lammie, C., Xiang, W., Linares-Barranco, B., & Azghadi, M. R. (2022) · Neurocomputing · doi:10.1016/j.neucom.2022.02.043 · Cited by 107
“Therefore, deterministic discretization [48] can be used to represent a finite number of electrically switchable conductance states, as depicted in Fig.”
Nonvolatile Capacitive Crossbar Array for In‐Memory Computing
Hur, J. H., Luo, Y.-C., Lu, A., Wang, T.-H., Li, S., Khan, A. I., & Yu, S. (2022) · Advanced Intelligent Systems · doi:10.1002/aisy.202100258 · Cited by 89
Self-citationLow-Power Resistive Switching Characteristic in HfO2/TiOx Bi-Layer Resistive Random-Access Memory
Ding, X., Feng, Y., Huang, P. C., Liu, L., & Kang, J. (2019) · Nanoscale Research Letters · doi:10.1186/s11671-019-2956-4 · Cited by 87
Compute-in-Memory with Emerging Nonvolatile-Memories: Challenges and Prospects
Yu, S., Sun, X., Peng, X., & Huang, S. (2020) · Custom Integrated Circuits Conference · doi:10.1109/cicc48029.2020.9075887 · Cited by 87
“Therefore, it is more attractive to embed the MAC computation into the memory array itself, namely compute-in-memory (CIM) [2], to minimize the data transfer.”
Self-citationJain, S., Li, S., Zheng, H., Li, L., Fong, X., & Ang, K. (2025) · Nature Communications · doi:10.1038/s41467-025-58039-3 · Cited by 93
“3b), where the programming of a selected cell inadvertently affects half-selected and non-selected cells in CBA withoutadequatecontrolovertheleakagecurrent(Fig.3c) 36 .”
Echo state graph neural networks with analogue random resistive memory arrays
Wang, S., Li, Y., Wang, D., Zhang, W., Chen, X., Dong, D., Wang, S., Zhang, X., Lin, P., Gallicchio, C., et al. (2023) · Nature Machine Intelligence · doi:10.1038/s42256-023-00609-5 · Cited by 84
Testability and Dependability of AI Hardware: Survey, Trends, Challenges, and Perspectives
Su, F., Liu, C., & Stratigopoulos, H. (2023) · IEEE Design and Test · doi:10.1109/mdat.2023.3241116 · Cited by 97
“There are several emerging nonvolatile memory (NVM) devices that can be used to implement the memristive device, including resistive random access memory (ReRAM), phase change memory (PCM), and spin transfer torque magnetic random access memory (STT-MRAM) [30].”
BackgroundInfluentialEmerging memory technologies for neuromorphic computing
Kim, C.-H., Lim, S., Woo, S. Y., Kang, W.-M., Seo, Y.-T., Lee, S., Lee, S., Kwon, D., Oh, S., Noh, Y., et al. (2018) · Nanotechnology · doi:10.1088/1361-6528/aae975 · Cited by 91
Gating-induced reversible HxVO2 phase transformations for neuromorphic computing
Ge, C., Li, G., Zhou, Q., Du, J., Guo, E., He, M., Wang, C., Yang, G., & Jin, K. (2019) · Nano Energy · doi:10.1016/j.nanoen.2019.104268 · Cited by 81
Baek, J. H., Kwak, K. J., Kim, S. J., Kim, J., Kim, J. Y., Im, I. H., Lee, S., Kang, K., & Jang, H. W. (2023) · Nano-Micro Letters · doi:10.1007/s40820-023-01035-3 · Cited by 86
“The evaluations of non-linearity, symmetricity, and dynamic range, which have a substantial impact on the performance of neuromorphic computing, were also accompanied [7, 10].”
BackgroundHow to Evaluate Deep Neural Network Processors: TOPS/W (Alone) Considered Harmful
Sze, V., Chen, Y.-H., Yang, T.-J., & Emer, J. S. (2020) · IEEE Solid-State Circuits Magazine · doi:10.1109/mssc.2020.3002140 · Cited by 80
“In addition, advanced device and memory technologies can be used to reduce the switching capacitance between compute and memory, for instance, by enabling inmemory computing [28], [29].”
Goh, Y., Hwang, J., Kim, M., Lee, Y., Jung, M., & Jeon, S. (2021) · ACS Applied Materials & Interfaces · doi:10.1021/acsami.1c14952 · Cited by 80
Two-Dimensional Near-Atom-Thickness Materials for Emerging Neuromorphic Devices and Applications
Ko, T., Li, H., Mofid, S. A., Yoo, C., Okogbue, E., Han, S. S., Shawkat, M. S., Krishnaprasad, A., Islam, M. M., Dev, D., et al. (2020) · iScience · doi:10.1016/j.isci.2020.101676 · Cited by 88
“A broad dynamic range (>100) is imperative, which allows superior mapping capability of the synaptic weights to the conductance states in an algorithm (Yu, 2018).”
BackgroundBiodegradable Materials for Transient Organic Transistors
Stephen, M., Nawaz, A., Lee, S. Y., Sonar, P. M., & Leong, W. L. (2022) · Advanced Functional Materials · doi:10.1002/adfm.202208521 · Cited by 80
Oxide semiconductor-based ferroelectric thin-film transistors for advanced neuromorphic computing
Kim, M., Kim, I., & Lee, J. (2021) · Applied Physics Letters · doi:10.1063/5.0035741 · Cited by 80
Seo, S., Kim, B., Kim, D., Park, S., Kim, T. R., Park, J.-K., Jeong, H., Park, S., Park, T., Shin, H. K., et al. (2022) · Nature Communications · doi:10.1038/s41467-022-34178-9 · Cited by 79
“Figure 5c presents the resulting accuracy graphs of MNIST classi fi cation by each epoch with the GIFET, the software baseline with ideal device, the device with ideal linearity and symmetry, and the device with deteriorated linearity (see Supplementary Fig.18).”
BackgroundMethodLi, W., Sun, X., Huang, S., Jiang, H., & Yu, S. (2022) · IEEE Journal of Solid-State Circuits · doi:10.1109/jssc.2022.3163197 · Cited by 77
“Compute-in-memory (CIM) has been widely recognized as a promising paradigm to alleviate the von Neumann bottleneck [7], [8], due to its highly parallel nature of compute and potential to suppress data movements.”
BackgroundSelf-citationIGZO-based floating-gate synaptic transistors for neuromorphic computing
He, Y., Liu, R., Jiang, S., Chen, C., Zhu, L. Q., Shi, Y., & Wan, Q. C. (2020) · Journal of Physics D Applied Physics · doi:10.1088/1361-6463/ab7bb4 · Cited by 78
Neural sampling machine with stochastic synapse allows brain-like learning and inference
Dutta, S., Detorakis, G., Khanna, A., Grisafe, B., Neftci, E., & Datta, S. (2022) · Nature Communications · doi:10.1038/s41467-022-30305-8 · Cited by 82
“Such hybrid synapses can be integrated within the prevailing crossbar array architecture for CIM that provides a promising energy-efficiency pathway for building neuromorphic hardware by reducing data-movement[26].”
BackgroundOn the Accuracy of Analog Neural Network Inference Accelerators
Xiao, T. P., Feinberg, B., Bennett, C. H., Prabhakar, V., Saxena, P., Agrawal, V., Agarwal, S., & Marinella, M. J. (2022) · IEEE Circuits and Systems Magazine · doi:10.1109/mcas.2022.3214409 · Cited by 76
Artificial synapse based on a tri-layer AlN/AlScN/AlN stacked memristor for neuromorphic computing
Dai, X., Hua, Q., Jiang, C., Long, Y., Dong, Z., Shi, Y., Huang, T., Li, H., Meng, H., Yang, Y., et al. (2024) · Nano Energy · doi:10.1016/j.nanoen.2024.109473 · Cited by 75
Kim, K., Song, M. S., Hwang, H., Hwang, S., & Kim, H. (2024) · Frontiers in Neuroscience · doi:10.3389/fnins.2024.1279708 · Cited by 81
“The following are the required performance metrics that synaptic devices should exhibit, as depicted in Figure 2 (Misra and Saha, 2010; Chen et al., 2017; Yu, 2018).”
BackgroundApproximate Computing: Concepts, Architectures, Challenges, Applications, and Future Directions
Dalloo, A. M., Humaidi, A. J., Mhdawi, A. K. A., & Al-Raweshidy, H. S. (2024) · IEEE Access · doi:10.1109/access.2024.3467375 · Cited by 86
Narrow Heater Bottom Electrode‐Based Phase Change Memory as a Bidirectional Artificial Synapse
Barbera, S. L., Ly, D. R. B., Navarro, G., Castellani, N., Cueto, O., Bourgeois, G., de Salvo, B., Nowak, E., Querlioz, D., & Vianello, E. (2018) · Advanced Electronic Materials · doi:10.1002/aelm.201800223 · Cited by 76
Reduced Graphene Oxide‐Based Artificial Synapse Yarns for Wearable Textile Device Applications
Park, Y., Park, M., & Lee, J. (2018) · Advanced Functional Materials · doi:10.1002/adfm.201804123 · Cited by 76
Yoon, J. H., Song, Y.-W., Ham, W., Park, J.-M., & Kwon, J.-Y. (2023) · APL Materials · doi:10.1063/5.0149393 · Cited by 74
MLP+NeuroSimV3.0: Improving On-chip Learning Performance with Device to Algorithm Optimizations
Luo, Y., Peng, X., & Yu, S. (2019) · International Conference on Neuromorphic Systems (ICONS) · doi:10.1145/3354265.3354266 · Cited by 92
“…memory bottleneck, which is caused by the insufficient memory bandwidth during the frequent data transfer between memory and computing unit when doing matrix multiplication, one promising solution is to perform computation inside the memory, which is referred to as compute-in-memory (CIM) [1]-[6].”
BackgroundSelf-citationEmerging memory devices for artificial synapses
Park, Y., Kim, M., & Lee, J. (2020) · Journal of Materials Chemistry C · doi:10.1039/d0tc01500h · Cited by 74
Opto-electronic memristors: Prospects and challenges in neuromorphic computing
Emboras, A., Alabastri, A., Lehmann, P., Portner, K., Weilenmann, C., Ma, P., Cheng, B., Lewerenz, M., Passerini, E., Koch, U., et al. (2020) · Applied Physics Letters · doi:10.1063/5.0028539 · Cited by 78
Fully UV Modulated Artificial Synapses with Integrated Sensing, Storage and Computation
Sun, S., Zhang, T., Jin, S., Pan, X., Lü, J., Ye, Z., & Lu, B. (2024) · Advanced Functional Materials · doi:10.1002/adfm.202401403 · Cited by 74
Li, S., Liu, X., Nandi, S. K., Nath, S. K., & Elliman, R. G. (2019) · Advanced Functional Materials · doi:10.1002/adfm.201905060 · Cited by 74
Efficient AI System Design With Cross-Layer Approximate Computing
Venkataramani, S., Sun, X. N., Wang, N., Chen, C., Choi, J., Kang, M., Agarwal, A., Oh, J., Jain, S., Babinsky, T., et al. (2020) · Proceedings of the IEEE · doi:10.1109/jproc.2020.3029453 · Cited by 82
“The in-memory computing can be applied for SRAM [116]–[119] or nonvolatile memories, such as RRAM, MRAM, or PCM [120], [121].”
MethodIn-memory computing to break the memory wall*
Huang, X., Liu, C., Jiang, Y., & Zhou, P. (2020) · Chinese Physics B · doi:10.1088/1674-1056/ab90e7 · Cited by 79
Impact of Read Operation on the Performance of HfO2-Based Ferroelectric FETs
Mulaosmanovic, H., Dünkel, S., Müller, J., Trentzsch, M., Beyer, S., Breyer, E. T., Mikolajick, T., & Slesazeck, S. (2020) · IEEE Electron Device Letters · doi:10.1109/led.2020.3007220 · Cited by 73
“neuromorphic devices [3]–[5].”
Interfacial Ion‐Trapping Electrolyte‐Gated Transistors for High‐Fidelity Neuromorphic Computing
Jin, M., Lee, H., Im, C., Na, H., Lee, J., Lee, W. H., Han, J., Lee, E., Park, J., & Kim, Y. S. (2022) · Advanced Functional Materials · doi:10.1002/adfm.202201048 · Cited by 75
HfO x /AlO y Superlattice‐Like Memristive Synapse
Wang, C., Mao, G., Huang, M., Huang, E., Zhang, Z., Yuan, J., Cheng, W., Xue, K., Wang, X., & Miao, X. (2022) · Advanced Science · doi:10.1002/advs.202201446 · Cited by 91
Recent advances in 2D organic−inorganic heterostructures for electronics and optoelectronics
Khan, J., Ahmad, R. T. M., Tan, J., Zhang, R., Khan, U., & Liu, B. (2022) · SmartMat · doi:10.1002/smm2.1156 · Cited by 75
“The human brain consists of 10(11) neurons with 10(15) synapses responsible for neural signal transmission and power consumption of only 20W power with operation consumption for each stimulus around 1–100 fJ.(246) Short‐term plasticity (STP) and long‐term plasticity (LTP) are considered important parameters to optimiz…”
BackgroundPark, Y., Kim, M., & Lee, J. (2021) · Journal of Materials Chemistry C · doi:10.1039/d0tc04250a · Cited by 74
Park, J. Y., Yang, K., Lee, D. H., Kim, S. H., Lee, Y. H., Reddy, P. R. S., Jones, J. L., & Park, M. H. (2020) · Journal of Applied Physics · doi:10.1063/5.0035542 · Cited by 73
Multi-state MRAM cells for hardware neuromorphic computing
Rzeszut, P., Chęciński, J., Brzozowski, I., Ziętek, S., Skowroński, W., & Stobiecki, T. (2022) · Scientific Reports · doi:10.1038/s41598-022-11199-4 · Cited by 78
In-Memory Logic Operations and Neuromorphic Computing in Non-Volatile Random Access Memory
Ou, Q., Xiong, B.-S., Yu, L., Wen, J., Wang, L., & Tong, Y. (2020) · Materials · doi:10.3390/ma13163532 · Cited by 72
Analog Nanoscale Electro-Optical Synapses for Neuromorphic Computing Applications
Portner, K., Schmuck, M., Lehmann, P., Weilenmann, C., Haffner, C., Ma, P., Leuthold, J., Luisier, M., & Emboras, A. (2021) · ACS Nano · doi:10.1021/acsnano.1c04654 · Cited by 71
Ye, W., Wang, L., Zhou, Z., An, J., Li, W., Gao, H., Li, Z., Yue, J., Hu, H., Xu, X., et al. (2023) · IEEE Journal of Solid-State Circuits · doi:10.1109/jssc.2023.3280357 · Cited by 71
“…with a high EF by accommodating the weight data on-chip and performing multiply-and-accumulate (MAC) operations directly inside the memory arrays [7], [8], [9], [10], [11], which minimizes the power and latency due to the data movement between the computing and memory units as well as that…”
BackgroundStrategic Development of Memristors for Neuromorphic Systems: Low‐Power and Reconfigurable Operation
Lee, J. W., Han, J., Kang, B., Hong, Y. J., Lee, S., & Jeon, I. (2025) · Advanced Materials · doi:10.1002/adma.202413916 · Cited by 81
Neuromorphic Time‐Dependent Pattern Classification with Organic Electrochemical Transistor Arrays
Pecqueur, S., Talamo, M. M., Guérin, D., Blanchard, P., Roncali, J., Vuillaume, D., & Alibart, F. (2018) · Advanced Electronic Materials · doi:10.1002/aelm.201800166 · Cited by 70
Low‐Voltage Oscillatory Neurons for Memristor‐Based Neuromorphic Systems
Hua, Q., Wu, H., Gao, B., Zhang, Q., Wu, W., Li, Y., Wang, X., Hu, W., & Qian, H. (2019) · Global Challenges · doi:10.1002/gch2.201900015 · Cited by 70
Saleem, A., Kumar, D., Singh, A., Rajasekaran, S., & Tseng, T. (2022) · Advanced Materials Technologies · doi:10.1002/admt.202101208 · Cited by 71
Chandrasekaran, S., Simanjuntak, F. M., Panda, D., & Tseng, T. (2019) · IEEE Transactions on Electron Devices · doi:10.1109/ted.2019.2941764 · Cited by 71
“THE biological brain is the most efficient computing systems which are capable of carrying out complex computations with ultralow energy consumption and ultradense space [1], [2].”
BackgroundSynergistic Modulation of Synaptic Plasticity in IGZO-Based Photoelectric Neuromorphic TFTs
Zhu, L. Q., He, Y., Chen, C., Zhu, Y., Shi, Y., & Wan, Q. C. (2021) · IEEE Transactions on Electron Devices · doi:10.1109/ted.2021.3060687 · Cited by 70
Experimental Demonstration of Non-volatile Capacitive Crossbar Array for In-memory Computing
Luo, Y.-C., Hur, J. H., Wang, T.-H., Lu, A., Li, S., Khan, A. I., & Yu, S. (2021) · Technical digest - International Electron Devices Meeting/Technical digest · doi:10.1109/iedm19574.2021.9720508 · Cited by 68
Self-citationNeuromorphic-computing-based adaptive learning using ion dynamics in flexible energy storage devices
Zhao, S., Ran, W., Lou, Z., Li, L., Poddar, S., Wang, L., Fan, Z., & Shen, G. (2022) · National Science Review · doi:10.1093/nsr/nwac158 · Cited by 68
“LTSP is a key component of memory control in hippocampal neurons and is primarily composed of the long-term potentiation and depression (LTP and LTD) of the synaptic weights [25].”
Chen, Y., Zhang, M., Li, D., Tang, Y., Ren, H., Li, J., Liang, K., Wang, Y., Wen, L., Li, W., et al. (2023) · ACS Nano · doi:10.1021/acsnano.3c02167 · Cited by 68
Large‐Scale and Robust Multifunctional Vertically Aligned MoS 2 Photo‐Memristors
Ranganathan, K., Fiegenbaum‐Raz, M., & Ismach, A. F. (2020) · Advanced Functional Materials · doi:10.1002/adfm.202005718 · Cited by 67
Peng, H., Chan, C.-Y., Chen, K.-Y., & Wu, Y. (2021) · Applied Physics Letters · doi:10.1063/5.0036824 · Cited by 67
Byun, K., Choi, I., Kwon, S., Kim, Y., Kang, D., Cho, Y. W., Yoon, S. K., & Kim, S. (2022) · Advanced Materials Technologies · doi:10.1002/admt.202200884 · Cited by 68
Conductive-bridging random-access memories for emerging neuromorphic computing
Cha, J., Yang, S. Y., Oh, J., Choi, S., Park, S., Jang, B. C., Ahn, W., & Choi, S. (2020) · Nanoscale · doi:10.1039/d0nr01671c · Cited by 67
A ZnO micro/nanowire-based photonic synapse with piezo-phototronic modulation
Hu, G., An, H., Xi, J., Lu, J., Hua, Q., & Peng, Z. (2021) · Nano Energy · doi:10.1016/j.nanoen.2021.106282 · Cited by 65
Lin, Y., Zhang, Q., Gao, B., Tang, J., Yao, P., Li, C., Huang, S., Liu, Z., Zhou, Y., Liu, Y., et al. (2023) · Nature Machine Intelligence · doi:10.1038/s42256-023-00680-y · Cited by 74
“The neuro-inspired approach relies on Ohm’s law (for multiplication) and Kirchhoff’s current law (in regard to summation) to perform in situ VMM 25 .”
MethodInfluentialPiezotronic Synapse Based on a Single GaN Microwire for Artificial Sensory Systems
Hua, Q., Cui, X. Y., Liu, H., Pan, C., Hu, W., & Wang, Z. L. (2020) · Nano Letters · doi:10.1021/acs.nanolett.0c00733 · Cited by 66
Shim, W., & Yu, S. (2020) · IEEE Electron Device Letters · doi:10.1109/led.2020.3048101 · Cited by 64
“Many types of nonvolatile memory (NVM) devices [1]–[4] are proposed as a synaptic device for CIM.”
BackgroundSelf-citationAnalog-to-Digital Converter Design Exploration for Compute-in-Memory Accelerators
Jiang, H., Li, W., Huang, S., Cosemans, S., Catthoor, F., & Yu, S. (2021) · IEEE Design and Test · doi:10.1109/mdat.2021.3050715 · Cited by 70
Self-citationSaleem, A., Simanjuntak, F. M., Chandrasekaran, S., Rajasekaran, S., Tseng, T., & Prodromakis, T. (2021) · Applied Physics Letters · doi:10.1063/5.0041808 · Cited by 64
Electronic synapses with near-linear weight update using MoS2/graphene memristors
Krishnaprasad, A., Choudhary, N., Das, S., Dev, D., Kalita, H., Chung, H., Aina, O., Jung, Y., & Roy, T. (2019) · Applied Physics Letters · doi:10.1063/1.5108899 · Cited by 64
Simulation of Inference Accuracy Using Realistic RRAM Devices
Mehonic, A., Joksas, D., Ng, W. H., Buckwell, M., & Kenyon, A. J. (2019) · Frontiers in Neuroscience · doi:10.3389/fnins.2019.00593 · Cited by 64
“This is the simplest approach being considered by others (Yu, 2018) because it minimizes the complexity of required circuitry for mapping.”
BackgroundFrom Molecular Electronics to Molecular Intelligence
Yan, C., Fang, C., Gan, J., Wang, J., Zhao, X. Z., Wang, X., Li, J., Zhang, Y., Liu, H., Li, X., et al. (2024) · ACS Nano · doi:10.1021/acsnano.4c10389 · Cited by 62
Trends and challenges in the circuit and macro of RRAM-based computing-in-memory systems
Wei, S.-T., Gao, B., Wu, D. M., Tang, J., Qian, H., & Wu, H. (2022) · Chip · doi:10.1016/j.chip.2022.100004 · Cited by 61
Open-loop analog programmable electrochemical memory array
Chen, P., Liu, F., Lin, P., Li, P., Xiao, Y., Zhang, B., & Pan, G. (2023) · Nature Communications · doi:10.1038/s41467-023-41958-4 · Cited by 67
“Despite tremendous progresses in using these emerging device arrays for computing applications 14 – 17 , precisely programming a device towards a speci fi c analog state is still a non-trivial task 18,19 .”
Recent Progress in Neuromorphic Computing from Memristive Devices to Neuromorphic Chips
Xiao, Y., Gao, C., Jin, J., Sun, W., Wang, B., Bao, Y., Liu, C., Huang, W., Zeng, H., & Yu, Y. (2024) · Advanced Devices & Instrumentation · doi:10.34133/adi.0044 · Cited by 68
Fault-Tolerant Training Enabled by On-Line Fault Detection for RRAM-Based Neural Computing Systems
Xia, L., Liu, M., Ning, X., Chakrabarty, K., & Wang, Y. (2019) · IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems · doi:10.1109/tcad.2018.2855145 · Cited by 61
“For the write latency, related architectural designs [2], [22] set the clock frequency to 500 MHz; however, chip demonstrations typically use 10–100 MHz clock frequencies [19], [38], [39].”
BackgroundNeuromorphic devices based on fluorite‐structured ferroelectrics
Lee, D. H., Park, G. H., Kim, S. H., Park, J. Y., Yang, K., Slesazeck, S., Mikolajick, T., & Park, M. H. (2022) · InfoMat · doi:10.1002/inf2.12380 · Cited by 63
Luo, Y., & Yu, S. (2020) · IEEE Transactions on Computers · doi:10.1109/tc.2020.3000218 · Cited by 66
“To further reduce the energy consumption of data movement and improve the throughput, it is proposed to conduct the VMM inside the memory array to accelerate DNN processing, which is termed as compute-in-memory (CIM) paradigm [3].”
MethodSelf-citationPCM-Based Analog Compute-In-Memory: Impact of Device Non-Idealities on Inference Accuracy
Sun, X., Khwa, W.-S., Chen, Y. S., Lee, C. H., Lee, H. Y., Yu, S. M., Naous, R., Wu, J. Y., Chen, T., Bao, X., et al. (2021) · IEEE Transactions on Electron Devices · doi:10.1109/ted.2021.3113300 · Cited by 64
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.