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 701–800 of 1,001
A Versatile ReRAM-based Accelerator for Convolutional Neural Networks
Mao, M., Sun, X., Peng, X., Yu, S., & Chakrabarti, C. (2018) · SiPS ... design and implementation - IEEE Workshop on Signal Processing Systems · doi:10.1109/sips.2018.8598372 · Cited by 7
“Figure 2: “Pseudo-crossbar” array is a modified 1T1R array [16].”
BackgroundSelf-citationSpiking Sensory Neurons for Analyzing Electrophysiological Data
Calvet, L. E., Renard, O., & Hepburn, C. (2020) · ECS Journal of Solid State Science and Technology · doi:10.1149/2162-8777/ab9e9f · Cited by 7
Ion-Movement-Based Synaptic Device for Brain-Inspired Computing
Yoon, C., Oh, G., & Park, B. H. (2022) · Nanomaterials · doi:10.3390/nano12101728 · Cited by 8
“Even for sparse coding algorithms for on-chip learning and backpropagation algorithms with emerging nonvolatile memory, the learning accuracy decreases when the precision is smaller than 6 bits [67,72].”
BackgroundLee, H. J., Kim, D., Choi, W. S., Kim, C., Choi, S., Bae, J., Kim, D. M., Kim, S., & Kim, D. H. (2022) · Materials Science in Semiconductor Processing · doi:10.1016/j.mssp.2022.107183 · Cited by 7
Massarotto, M., Driussi, F., Affanni, A., Lancaster, S., Slesazeck, S., Mikolajick, T., & Esseni, D. (2022) · Solid-State Electronics · doi:10.1016/j.sse.2022.108569 · Cited by 7
A Multimode Hybrid Memristor-CMOS Prototyping Platform Supporting Digital and Analog Projects
Harabi, K.-E., Turck, C., Drouhin, M., Renaudineau, A., Bersani--Veroni, T., Querlioz, D., Hirtzlin, T., Vianello, E., Bocquet, M., & Portal, J. (2023) · Asia and South Pacific Design Automation Conference (ASP-DAC) · doi:10.1145/3566097.3567944 · Cited by 7
“, as artificial synapses in machine learning or neuromorphic circuits [4].”
BackgroundA physics-based compact model of thermal resistance in RRAMs
Pande, S. R., Balanethiram, S., Chakrabarti, B., & Chakravorty, A. (2023) · Solid-State Electronics · doi:10.1016/j.sse.2023.108636 · Cited by 7
Power-Aware Quantization in Analog In-Memory Computing With STT-MRAM Macro
Zhou, M., Du, H., Guo, Y., & Cai, H. (2023) · IEEE Transactions on Magnetics · doi:10.1109/tmag.2023.3286467 · Cited by 8
“Over the past few years, numerous explorations of this emerging computing paradigm have been made to break the bottleneck of memory-processor communication of the traditional von Neumann architecture [1], [2], [3], [4].”
BackgroundAhmed, S. T., Danouchi, K., Hefenbrock, M., Prenat, G., Anghel, L., & Tahoori, M. B. (2023) · ACM Transactions on Embedded Computing Systems · doi:10.1145/3609116 · Cited by 8
“To achieve more conductance levels, it is possible to use multiple multi-level cells jointly for the storage of quantized weights (Q-bit) [40].”
Symmetric Linear Rise and Fall of Conductance in a Trilayer Stack Engineered ReRAM-Based Synapse
Vishwakarma, K., Kishore, R., & Datta, A. (2020) · ACS Applied Electronic Materials · doi:10.1021/acsaelm.0c00585 · Cited by 7
A Quantized Training Framework for Robust and Accurate ReRAM-based Neural Network Accelerators
Zhang, C., & Zhou, P. (2021) · Asia and South Pacific Design Automation Conference (ASP-DAC) · doi:10.1145/3394885.3431528 · Cited by 10
Emulation of Synaptic Scaling Based on MoS2 Neuristor for Self‐Adaptative Neuromorphic Computing
Wu, L., Bao, L., Wang, Z., Yu, Z., Wang, B., Chen, Q., Ling, Y., Qin, Y., Tang, K., Cai, Y., et al. (2021) · Advanced Electronic Materials · doi:10.1002/aelm.202001104 · Cited by 7
Multinary Data Processing Based on Nonlinear Synaptic Devices
Kim, M.-J., Lee, J.-E., Lee, C., Song, Y., Han, G., Seo, J., Kim, D., Seo, Y.-H., Hwang, H., & Lee, D. (2021) · Journal of Electronic Materials · doi:10.1007/s11664-021-08841-8 · Cited by 7
Single RRAM Cell-based In-Memory Accelerator Architecture for Binary Neural Networks
Oh, H., Kim, H., Kang, N., Kim, Y., Park, J., & Kim, J. (2021) · IEEE International Conference on Artificial Intelligence Circuits and Systems (AICAS) · doi:10.1109/aicas51828.2021.9458444 · Cited by 7
“It has been reported that the α may vary from 1.17 to 3 depending on the RRAM cell characteristics [5].”
BackgroundInfluentialSpintronic Memristor-Based Binarized Ensemble Convolutional Neural Network Architectures
Tchendjou, G. T., Danouchi, K., Prenat, G., & Anghel, L. (2022) · IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems · doi:10.1109/tcad.2022.3213612 · Cited by 7
“Mimicking the brain functionality, the hardware co-design of computing functions, and weight mem-orization has been studied as a potential solution resulting in non von-Neumann architectures [8].”
MethodPan, X., Shuai, Y., Wu, C., Luo, W., Sun, X., Zeng, H., Guo, H., Yuan, Y., Zhou, S., Böttger, R., et al. (2019) · Solid State Ionics · doi:10.1016/j.ssi.2019.01.026 · Cited by 7
Modeling of RRAM With Embedded Tunneling Barrier and Its Application in Logic in Memory
Lee, J.-W., & Chiang, M. (2020) · IEEE Journal of the Electron Devices Society · doi:10.1109/jeds.2020.3008172 · Cited by 7
“RRAM with the aforementioned advantages has been studied for neuromorphic computing application [2]–[4].”
BackgroundStochastic STT-MRAM Spiking Neuron Circuit
Liang, F.-X., Sahu, P. P., Wu, M.-H., Wei, J., Sheu, S.-S., & Hou, T. (2020) · International Symposium on VLSI Technology, Systems and Applications (VLSI-TSA) · doi:10.1109/vlsi-tsa48913.2020.9203701 · Cited by 7
Modeling-Based Design of Memristive Devices for Brain-Inspired Computing
Zhao, Y., Chen, R., Huang, P. C., & Kang, J. (2021) · Frontiers in Nanotechnology · doi:10.3389/fnano.2021.654418 · Cited by 7
“Due to the unique characteristics, RRAM has been suggested for use as building blocks for brain-inspired computing systems (Yang et al., 2013; Philip Wong and Salahuddin, 2015; Chi et al., 2016; Jeong et al., 2016; Yu, 2018).”
MethodModelling and design of FTJs as high reading-impedance synaptic devices
Fontanini, R., Massarotto, M., Specogna, R., Driussi, F., Loghi, M., & Esseni, D. (2021) · IEEE Electron Devices Technology & Manufacturing Conference (EDTM) · doi:10.1109/edtm50988.2021.9420863 · Cited by 7
Low-Rank Training of Deep Neural Networks for Emerging Memory TechnologyPreprint
Gural, A., Nadeau, P., Tikekar, M., & Murmann, B. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2009.03887 · Cited by 7
“Correspondence to: Albert Gural <agural@stanford.edu>. for energy and area-efficient inference (Yu, 2018).”
BackgroundZhang, X., Sui, N., Li, M., Wang, S., Shao, S., Liu, W., Sun, J. Y., Yang, J., & Zhao, J. (2025) · Nano Research · doi:10.26599/nr.2025.94907350 · Cited by 6
Cai, D., Wang, J., Zhao, T., Shen, M., Liu, Y., Zhang, T., Zhang, F., Wang, Y., Jiang, Y., & Gu, D. (2025) · Advanced Science · doi:10.1002/advs.202511168 · Cited by 6
Jiang, D., Cao, C., Zhang, J., Zhang, O., Zhu, C., Xu, J., Zhang, Q., Li, W., Da, Y., Miao, X., et al. (2026) · ACS Applied Electronic Materials · doi:10.1021/acsaelm.5c02703 · Cited by 6
Thermal Crosstalk Analysis in ReRAM Passive Crossbar Arrays
Pande, S. R., Chakrabarti, B., & Chakravorty, A. (2024) · International Conference on VLSI Design · doi:10.1109/vlsid60093.2024.00071 · Cited by 6
“In this respect, resistive random access memory (ReRAM) is a serious contender, along with other non-volatile memories such as phase change memories, ferroelectric memories, and spin-transfer torque RAMs [1, 2].”
BackgroundQiao, L., Ke, S., Shi, K., Zhu, Y., Mao, H., Sun, J., Wan, Q., & Wan, C. (2024) · IEEE Electron Device Letters · doi:10.1109/led.2024.3424516 · Cited by 6
“Such energy consumption is higher than some CMOS-based oscillating neurons (typically lower than 1 pJ/spike), which is due to longer duration (t spike ) of a generated spike by our device [25].”
BackgroundAn Extensive Analysis of Neuromorphic Computing
Vajpayee, A., Kaur, P. P., Sharma, A., & Varshney, S. (2024) · IEEE International Conference on Advances in Computing Research on Science Engineering and Technology (ACROSET) · doi:10.1109/acroset62108.2024.10743880 · Cited by 6
“We explore hardware representations, learning methods, and possible uses for SNN-based learning systems in this study [3].”
MethodField-free spin–orbit torque devices for logic and neural network applications
Lin, C., Hsieh, J.-Y., Wang, P., Tsai, C.-C., & Pai, C. (2024) · APL Machine Learning · doi:10.1063/5.0226135 · Cited by 6
ML-Driven Compact Models for RRAMs: Addressing Variability and Simulation Efficiency
Hong, G., Huh, I., You, J. H., Choe, J. M., Kim, Y.-G., & Jeong, C. (2025) · IEEE Electron Device Letters · doi:10.1109/led.2025.3545909 · Cited by 6
“R ESISTIVE Random Access Memory (RRAM) devices have been extensively researched for their potential to physically implement artificial synapses in neuromorphic systems, making them a promising candidate for next-generation memory and neuromorphic computing [1], [2], [3], [4], [5], [6], [7].”
Efficient and Robust Resistive Switching Behaviour of MoS$_{2}$ Based Memristor
Ranjan, H., Singh, C. P., Singh, V. P., & Pandey, S. K. (2025) · IEEE Transactions on Materials for Electron Devices · doi:10.1109/tmat.2025.3559871 · Cited by 6
“V curves, is effective for mimicking synaptic functions and implementing spike-timing dependent plasticity (STDP), a key mechanism in biological learning [36], [37].”
Lee, Y.-H., Lee, S.-W., Choi, J., Ghenzi, N., Han, J., & Hwang, C. S. (2025) · physica status solidi (RRL) - Rapid Research Letters · doi:10.1002/pssr.202500131 · Cited by 6
Memristor-Based Circuits and Architectures Enabling Next-Generation Neuromorphic RFID Systems
Colella, R., Arciello, A., Grassi, G., & Merenda, M. (2025) · IEEE Journal of Radio Frequency Identification · doi:10.1109/jrfid.2025.3579260 · Cited by 6
Implementation of RRAM based Swish Activation Function and its Derivative on 28nm FD-SOI
Fatima, A., & Pethe, A. J. (2022) · International Electrical Engineering Congress (iEECON) · doi:10.1109/ieecon53204.2022.9741701 · Cited by 6
“The process of applying non-linearity at the end of a linear signal just after computing the dot product operation of a neuron is typically termed as the ‘inference’ or forward -propagation process [3,4] as defined in eqn.”
MethodYu, J., Lee, C., Han, J., Lee, S., Kim, M., Im, S. G., & Choi, Y. (2022) · IEEE Transactions on Electron Devices · doi:10.1109/ted.2022.3179460 · Cited by 6
Spin Orbit Torque-based Crossbar Array for Error Resilient Binary Convolutional Neural Network
Danouchi, K., Prenat, G., & Anghel, L. (2022) · IEEE Latin American Test Symposium (LATS) · doi:10.1109/lats57337.2022.9936951 · Cited by 7
Bourgeois, G., Meli, V., Antonelli, R., Socquet-Clerc, C., Magis, T., Laulagnet, F., Hemard, B., Bernard, M., Fellouh, L., Dezest, P., et al. (2023) · IEEE Electron Devices Technology & Manufacturing Conference (EDTM) · doi:10.1109/edtm55494.2023.10102961 · Cited by 6
Enabling High-Speed, High-Resolution Space-based Focal Plane Arrays with Analog In-Memory Computing
Xiao, T. P., Wahby, W. S., Bennett, C. H., Hays, P., Agrawal, V., Marinella, M. J., & Agarwal, S. (2023) · IEEE Symposium on VLSI Technology and Circuits (VLSI Technology and Circuits) · doi:10.23919/vlsitechnologyandcir57934.2023.10185348 · Cited by 7
A review of in-memory computing for machine learning: architectures, options
Snåšel, V., Dang, T. K., Kueng, J., & Kong, L. (2023) · International Journal of Web Information Systems · doi:10.1108/ijwis-08-2023-0131 · Cited by 7
Chang, J. H., Woo, J. S., Sung, S., Song, K., & Choi, W. Y. (2024) · IEEE Transactions on Electron Devices · doi:10.1109/ted.2024.3390651 · Cited by 6
“In particular, neuromorphic hardware with quantized neural networks (QNNs) has been highlighted for its energy-efficient vector matrix multiplication [4], [5], [6], [7].”
BackgroundA Novel Verification Method of Minimizing Verification Error in AND-Type Flash Arrays
Yu, J., Ryu, D., & Choi, W. Y. (2024) · IEEE Electron Device Letters · doi:10.1109/led.2024.3416185 · Cited by 6
“Recently, for edge AI applications, the offline learning has gained more attention where software-trained weights are transferred to hardware [15].”
BackgroundPark, T., Kim, J., Kwon, Y. J., Kim, H., Yim, S., Shin, D. H., Kim, Y. R., Kim, H. J., & Hwang, C. S. (2024) · Advanced Materials Technologies · doi:10.1002/admt.202400965 · Cited by 6
ZnO@ZIF-8 heteronanostructures for advanced neuromorphic synaptic devices
Yeom, C.-M., Kumar, D., Eadi, S. B., Lee, H.-S., Thallapally, P. K., Kwon, H.-M., Fischer, R. A., Lee, H., & Jayaramulu, K. (2024) · Cell Reports Physical Science · doi:10.1016/j.xcrp.2024.102219 · Cited by 6
A Review of Nanowire Devices Applied in Simulating Neuromorphic Computing
Huang, T., Wang, Y., Jin, Z., Liu, H., Wang, K., Tan, C. L., Shi, Y., & Yan, S. (2025) · Nanomaterials · doi:10.3390/nano15100724 · Cited by 6
“Researchers have proposed that neuromorphic synaptic devices must meet the following performance criteria: high linearity of conductance, a ratio of maximum to minimum conductance greater than 10, data levels greater than 32, and small variations in performance over time/between devices [60,61].”
Hu, Q., Dong, B., Wang, L., Huang, E., Tong, H., He, Y., Xu, M., & Miao, X. (2020) · Chinese Physics B · doi:10.1088/1674-1056/ab892a · Cited by 6
Optimization Strategy for Accelerating Multi-Bit Resistive Weight Programming on the RRAM Array
Chen, J.-R., Wu, H., Gao, B., Tang, J., Zhang, W., & Qian, H. (2019) · doi:10.1109/iwofc48002.2019.9078447 · Cited by 6
“INTRODUCTION Analog Resistive Random-Access Memory (RRAM) has attracted great interests as one of the most promising artificial electric synapses for future neuromorphic computing [1, 2].”
BackgroundArchitecting for Artificial Intelligence with Emerging Nanotechnology
Kulkarni, S., Bhat, S., & Moritz, C. A. (2021) · ACM Journal on Emerging Technologies in Computing Systems · doi:10.1145/3445977 · Cited by 7
“There have been several survey papers which review use of emerging technology for neuromorphic and neural network architectures and frameworks [27][28][29].”
BackgroundAhmed, S. T., Hefenbrock, M., Münch, C., & Tahoori, M. B. (2022) · IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems · doi:10.1109/tcad.2022.3205872 · Cited by 6
“Digital Object Identifier 10.1109/TCAD.2022.3205872 system [2] as it requires numerous vector-matrix multiplication and memory accesses.”
BackgroundMethodInfluentialWang, M., Huang, M., Wang, C., Sun, H., Miao, X., & Wang, X. (2023) · IEEE Transactions on Electron Devices · doi:10.1109/ted.2023.3294352 · Cited by 6
Yılmaz, Y. (2023) · Neural Computing and Applications · doi:10.1007/s00521-023-08995-y · Cited by 6
“Forming analogue synapses, i.e. eNVM in crossbar arrays, is the most effective way of obtaining weight matrices [27].”
BackgroundBenchmark of RRAM based Architectures for Dot-Product Computation
Peng, X., & Yu, S. (2018) · IEEE Asia Pacific Conference on Circuits and Systems (APCCAS) · doi:10.1109/apccas.2018.8605606 · Cited by 6
“1 shows the basic functional unit of a RRAM-based accelerator, which is called pseudo-crossbar array [11].”
BackgroundSelf-citationRebooting Our Computing Models
Cadareanu, P., C, N. R., Almudéver, C. G., Khanna, A., Raychowdhury, A., Datta, S., Bertels, K., Narayanan, V., Ventra, M. D., & Gaillardon, P.-E. (2019) · Design, Automation, and Test in Europe · doi:10.23919/date.2019.8715167 · Cited by 6
“For instance, neuromorphic computing is an innovative computing paradigm inspired by the feedback system present in brain function [10; 11; 12; 13; 14].”
MethodNonsilicon, Non-von Neumann Computing—Part II
Basu, S., Bryant, R. E., Micheli, G. D., Theis, T., & Whitman, L. J. (2020) · Proceedings of the IEEE · doi:10.1109/jproc.2020.3001748 · Cited by 6
Understanding Security Threats in Emerging Neuromorphic Computing Architecture
Rajamanikkam, C., Rajesh, J. S., Roy, S., & Chakraborty, K. (2021) · Journal of Hardware and Systems Security · doi:10.1007/s41635-021-00110-8 · Cited by 7
Terasa, M.-I., Holtz, P., Carstens, N., Kaps, S., Faupel, F., Vahl, A., & Adelung, R. (2022) · PLoS ONE · doi:10.1371/journal.pone.0264846 · Cited by 6
“The application potential ranges from non-volatile memory [3] over bio-inspired neural networks as a promising approach to overcome the von-Neumann bottleneck [4] to the concept of a “memsensor” joining memristive with sensitive functionality, allowing for unique features such as habituation to a permanent background…”
BackgroundVersatile experimental setup for FTJ characterization
Massarotto, M., Driussi, F., Affanni, A., Lancaster, S., Slesazeck, S., Mikolajick, T., & Esseni, D. (2022) · Solid-State Electronics · doi:10.1016/j.sse.2022.108364 · Cited by 6
Triple-Node FinFET With Non-Ohmic Schottky Junctions for Synaptic Devices
Yu, J., Kim, S., Kim, J., Han, J., Jeon, S., & Choi, Y. (2022) · IEEE Electron Device Letters · doi:10.1109/led.2022.3223048 · Cited by 6
“The classification accuracy as evaluated by the pattern recognition rate is improved via the optimization of synaptic weights by training with a given dataset [4], [5].”
MethodPan, X., Luo, W., Shuai, Y., Hu, S. G., Luo, W., Qiao, G., Zhou, T. H., Wang, J., Xie, Q., Huang, S., et al. (2023) · IEEE Sensors Journal · doi:10.1109/jsen.2023.3248123 · Cited by 6
“The memristor exhibits resistance plasticity, which makes the memristor can be used as electronic synapse [10], [11], [12], [13].”
MethodToward Efficient System-on-Module for Design-Space Exploration of Analog Spiking Neural Networks
El-Masry, M., Werner, T., Zjajo, A., & Weigel, R. (2024) · IEEE Transactions on Circuits and Systems I Regular Papers · doi:10.1109/tcsi.2024.3406522 · Cited by 5
“Table I provides a benchmark of various memory concepts based on metrics proposed in [42].”
BackgroundWoo, J. S., Jung, C. L., Chang, J. H., Ryu, M., & Choi, W. Y. (2024) · Advanced Electronic Materials · doi:10.1002/aelm.202400606 · Cited by 5
Reliability-Enhanced Reverse Forming Operation Scheme for Analog Resistive Random-Access Memory
Jiang, Z., Xi, Y., Lu, Y., Tang, J., Hu, R., Du, Y., Gao, B., Qian, H., & Wu, H. (2024) · IEEE Electron Device Letters · doi:10.1109/led.2024.3521924 · Cited by 5
“Resistive random-access memory (RRAM), characterized by its non-volatility, multi-bit storage capability, and high switching speed, has emerged as a prominent contender within the realm of CIM technology [4], [5], [6].”
BEOL-compatible Te-TeOx p-FETs with channel length down to 50 nm at cryogenic temperatures
Xu, Y., Sun, Y., Zheng, Z., Wang, Y., Kang, Y., Han, K., Chen, X., Zheng, G., & Gong, X. (2025) · Applied Physics Letters · doi:10.1063/5.0243792 · Cited by 5
Ye, W., Gao, H., Zhou, Z., Wang, L., Li, W., Li, Z., Yue, J., Xu, X., Yang, J., Hu, H., et al. (2025) · IEEE Transactions on Very Large Scale Integration (VLSI) Systems · doi:10.1109/tvlsi.2025.3545866 · Cited by 5
“New paradigms and technologies that can minimize data movement are being intensively studied [2], [3].”
Ultrahigh-precision analog computing using memory-switching geometric ratio of transistors
Yangdong, X.-J., Wang, C., Zhao, Y., Wang, Z.-C., Yang, Z., Liu, Z., Yu, W., Zeng, Z., Wang, S., Wei, W., et al. (2025) · Science Advances · doi:10.1126/sciadv.ady4798 · Cited by 6
Low-Power Ionically Tunable Bilayer MoS 2 Synaptic Transistors
Levit, O., Ber, E., Keller, Y., Minkovich, B., & Yalon, E. (2025) · Nano Letters · doi:10.1021/acs.nanolett.5c02372 · Cited by 5
Shen, Y., Zhong, Y., Ye, Y., Luo, Y.-Q., Xu, Z., He, S., Chen, J., Xue, S., Ding, G., Zhou, Y., et al. (2026) · International Journal of Extreme Manufacturing · doi:10.1088/2631-7990/ae5005 · Cited by 5
“…such as synaptic plasticity, neuromorphic systems can dynamically adjust synaptic weights in real time based on input events (such as changes in pixel intensity in an image or voltage fluctuations in an electroencephalogram), thereby enabling local learning updates directly on the device [30,31] .”
Kim, J., Woo, H. C., Jeong, T.-Y., Choi, J., & Hwang, C. S. (2021) · Advanced Intelligent Systems · doi:10.1002/aisy.202100174 · Cited by 5
Kwon, D., Park, M., Kang, W.-M., Hwang, J., Koo, R., Bae, J., & Lee, J. (2023) · IEEE Transactions on Electron Devices · doi:10.1109/ted.2023.3287824 · Cited by 6
“3287824 problems of von Neumann computing architectures [1], [2],”
BackgroundEnhanced regularization for on-chip training using analog and temporary memory weights
Singhal, R., Saraswat, V., Deshmukh, S., Subramoney, S., Somappa, L., Baghini, M. S., & Ganguly, U. (2023) · Neural Networks · doi:10.1016/j.neunet.2023.07.001 · Cited by 6
Silicon Nanowire Charge Trapping Memory for Energy-Efficient Neuromorphic Computing
Ansari, M. H. R., Mohanan, K. U., & El‐Atab, N. (2023) · IEEE Transactions on Nanotechnology · doi:10.1109/tnano.2023.3296673 · Cited by 5
Sequence learning in a spiking neuronal network with memristive synapses
Bouhadjar, Y., Siegel, S., Tetzlaff, T., Diesmann, M., Waser, R., & Wouters, D. J. (2023) · Neuromorphic Computing and Engineering · doi:10.1088/2634-4386/acf1c4 · Cited by 6
“Correcting for these nonidealities can be costly and may require additional circuitry (Chen et al., 2015; Agarwal et al., 2016; Hong et al., 2018; Yu, 2018; Ambrogio et al., 2018; Adnan et al., 2021).”
BackgroundReliable synaptic plasticity of InGaZnO transistor with TiO 2 interlayer
Jeong, S.-H., Oh, S., Kwon, O., Kim, D. H., Seo, H. Y., Park, W., & Cho, B. (2023) · Nanotechnology · doi:10.1088/1361-6528/ad1540 · Cited by 5
“This PPF behavior is one of the representative biological synaptic functions, in which the strong connectivity of the electrical signal leads to a non-volatile memory [ 40 ] .”
BackgroundKarimzadeh, F., & Raychowdhury, A. (2024) · IEEE Access · doi:10.1109/access.2024.3373709 · Cited by 5
“Memory capacity/access is the main bottleneck in the CMOS ASIC designs [9].”
BackgroundInfluentialHwang, J., Park, M., Kang, W.-M., Koo, R., Lee, K.-H., Kwon, D., Choi, W. Y., & Lee, J. (2024) · IEEE Electron Device Letters · doi:10.1109/led.2024.3388993 · Cited by 5
“N EUROMORPHIC systems with nonvolatile synaptic device arrays are arising as an effective hardware platform for neural networks [1], [2], [3].”
BackgroundA Novel Parallel In-Memory Logic Array Based on Programmable Diodes
Ye, J., Zhu, J., Cao, J., Bi, H., Ding, Y. S., & Chen, B. (2024) · IEEE Journal of the Electron Devices Society · doi:10.1109/jeds.2024.3457021 · Cited by 5
“In recent years, numerous studies have focused on exploring the implementation of vector-matrix multiplication and accumulation operations within arrays, aiming to provide acceleration support for artificial intelligence applications [6], [7], [8], [9], [10], [11], [12].”
BackgroundKim, H., An, Y., Kim, M.-C., Heo, G.-C., & Shim, Y. S. (2024) · IEEE Transactions on Circuits & Systems II Express Briefs · doi:10.1109/tcsii.2024.3485178 · Cited by 5
“We set resistance range and TMR ratio of the corresponding RRAM device model based on the previous research work [13].”
Comparing Short and Long-term Reliability of HfO 2 and Al: HfO 2 RRAM Devices
Baroni, A., Pérez, E., Reddy, K. D. S., Pechmann, S., Wenger, C., Ielmini, D., & Zambelli, C. (2024) · IEEE International Integrated Reliability Workshop final report · doi:10.1109/iirw62856.2024.10947134 · Cited by 5
Li, T., Zhong, H., Xu, Y., Narayanan, V., Ni, K., Yang, H., Kämpfe, T., & Li, X. (2024) · doi:10.1145/3676536.3676715 · Cited by 5
“To address this challenge, computing-in-memory (CiM) has emerged as a promising computational paradigm to reduce data movements through in-situ operations and highly parallel processing [5, 6].”
Xie, C., Shao, Z., Zhang, M., Du, Y., & Du, L. (2025) · IEEE Journal of Solid-State Circuits · doi:10.1109/jssc.2025.3563387 · Cited by 5
“Among CIM accelerators based on various memory technologies (DRAM [16], SRAM [17], and resistive random access memory (ReRAM) [18]), ReRAM-based and SRAM-based CIM have obtained widespread research interest due to their high density and reliability [19].”
StoX-Net: Stochastic Processing of Partial Sums for Efficient In-Memory Computing DNN Accelerators
Rogers, E. G., Mugdho, S. S., Gupte, K. K., & Wang, C. (2024) · IEEE International Conference on Rebooting Computing (ICRC) · doi:10.1109/icrc64395.2024.10937005 · Cited by 7
“Several emerging NVM technologies, including resistive memory (ReRAM) and magnetic random access memory (MRAM), have been explored for machine learning acceleration [13], [14].”
A Floating Gate Memory with U-Shape Recessed Channel for Neuromorphic Computing and MCU Applications
Gan, L., Wang, Y., Chen, L., Zhu, H., & Sun, Q. (2019) · Micromachines · doi:10.3390/mi10090558 · Cited by 5
“However, the slow operation speed of traditional embedded floating-gate memory and its limited miniaturization ability hinder its further development in neuromorphic computing [14].”
BackgroundModeling Electrical Switching Behavior of Carbon Resistive Memory
Ou, Q., Wang, L., & Xiong, B.-S. (2020) · IEEE Access · doi:10.1109/access.2020.2964601 · Cited by 5
“In spite of their ability to provide ultra-high density, high data rate, and non-volatility, these emerging memories are inevitably subjected to their respective physical limits [9], [10], thus making them far away”
BackgroundA Neural Network implemented on NAND memory
Minucci, U., Santis, L. D., Vali, T., & Irrera, F. (2020) · IEEE International Memory Workshop (IMW) · doi:10.1109/imw48823.2020.9108138 · Cited by 5
“Inputs are applied to more synapses, each one having different weight ( h coefficient of the weight matrix Mjxi) computed during the learning phase [6].”
MethodComputing with nonvolatile memories for artificial intelligence
Pedretti, G., & Ielmini, D. (2022) · Elsevier eBooks · doi:10.1016/b978-0-12-820758-1.00009-1 · Cited by 7
Synaptic mechanisms of four W/WO x /ITO memristors with different WO x structures
Liu, Y., Wang, Y., Wang, C., Sun, N., Cheng, C., Dai, J., & Huang, H. (2022) · Journal of Physics D Applied Physics · doi:10.1088/1361-6463/ac848d · Cited by 5
“The large range of electric conductance can be used to construct high-precision synapses, which is ideal for neuromorphological calculation [6].”
Effect of Plasma Treatment on the Long-term Plasticity of Synaptic Transistor
Qiu, H., Miao, G., Hui, L. I., Qi, L. U. A. N., Liu, A., & Shan, F. (2022) · Journal of Inorganic Materials · doi:10.15541/jim20220675 · Cited by 5
Fuse Devices for Pruning in Memristive Neural Network
Kim, T., Hong, K., Kim, S., Park, J., Youn, S., Lee, J., Park, B., Kim, H., & Choi, W. Y. (2023) · IEEE Electron Device Letters · doi:10.1109/led.2023.3237651 · Cited by 5
“Furthermore, for applying the fuse to various synaptic devices other than RRAM [25], [26], its blow voltage and current must be adjustable.”
BackgroundXie, Q., Pan, X., Luo, W., Shuai, Y., Zeng, H., Wang, J., Liu, Y., Yang, X., Lv, L., Xu, J., et al. (2023) · Nanoscale · doi:10.1039/d3nr02395h · Cited by 5
Device-circuit co-design of memristor-based on niobium oxide for large-scale crossbar memory
Gupta, A. K., Yadav, M. S., & Rawat, B. (2023) · Memories - Materials Devices Circuits and Systems · doi:10.1016/j.memori.2023.100080 · Cited by 5
Ultralow Voltage Resistive Switching in Hafnium–Zirconium Oxide
Asif, M., Rakshit, R. K., & Kumar, A. (2024) · Advanced Physics Research · doi:10.1002/apxr.202300123 · Cited by 5
Doevenspeck, J., Degraeve, R., Fantini, A., Debacker, P., Verkest, D., Lauwereins, R., & Dehaene, W. (2018) · Technical digest - International Electron Devices Meeting/Technical digest · doi:10.1109/iedm.2018.8614489 · Cited by 5
Reshaping Future Computing Systems With Emerging Nonvolatile Memory Technologies
Chen, Y. (2019) · IEEE Micro · doi:10.1109/mm.2018.2885588 · Cited by 5
“The latter is indeed the basic operation of neuromorphic computing models.(14) Neuromorphic computing systems mimic biological neural behaviors in order to efficiently process cognitive applications.”
BackgroundReview of candidate devices for neuromorphic applications
Lee, J., Woo, S. Y., Lee, S., Lim, S., Kang, W.-M., Seo, Y.-T., Lee, S., Kwon, D., Oh, S., Noh, Y., et al. (2019) · European Solid-State Device Research Conference · doi:10.1109/essderc.2019.8901694 · Cited by 5
Luo, Q., Chen, B., Cao, R., Xue, X., Zhou, K., Yang, J., Zheng, X., Yu, H., Yu, J., Gong, T., et al. (2019) · Technical digest - International Electron Devices Meeting/Technical digest · doi:10.1109/iedm19573.2019.8993545 · Cited by 5
Accurate Emulation of Memristive Crossbar Arrays for In-Memory Computing
Πετρόπουλος, Α., Boybat, I., Gallo, M. L., Eleftheriou, E. S., Sebastian, A., & Antonakopoulos, T. A. (2020) · IEEE International Symposium on Circuits and Systems proceedings · doi:10.1109/iscas45731.2020.9181021 · Cited by 7
Theoretical Study of Bilayer Composite Barrier Based Ferroelectric Tunnel Junction Memory
Duan, H., Fang, W., Liu, L., & Chen, W. (2020) · IEEE MTT-S International Conference on Numerical Electromagnetic and Multiphysics Modeling and Optimization · doi:10.1109/nemo49486.2020.9343600 · Cited by 5
Mitigating Adversarial Attack for Compute-in-Memory Accelerator Utilizing On-chip Finetune
Huang, S., Jiang, H., & Yu, S. (2021) · IEEE Non-Volatile Memory Systems and Applications Symposium (NVMSA) · doi:10.1109/nvmsa53655.2021.9628739 · Cited by 5
Self-citationA Multi-Memristive Unit-Cell Array With Diagonal Interconnects for In-Memory Computing
Khaddam-Aljameh, R., Martemucci, M., Kersting, B., Gallo, M. L., Bruce, R. L., BrightSky, M. J., & Sebastian, A. (2021) · IEEE Transactions on Circuits & Systems II Express Briefs · doi:10.1109/tcsii.2021.3078614 · Cited by 5
“Achieving at least O ( N ) -complexity for carrying out programming operations on memristive crossbars is desirable to accelerate the import of pre-trained weights for DNN inference [4] and is essential to enable applications such as DNN training [12]–[14].”
BackgroundReliable Resistive Switching Behaviour of Ag/Ta2O5/Al2O3/p++-Si Memory Device
Tian, W., Ilyas, N., Li, D., Li, C., Jiang, X., & Li, W. (2020) · Journal of Physics Conference Series · doi:10.1088/1742-6596/1637/1/012021 · Cited by 5
FPRA: A Fine-grained Parallel RRAM Architecture
Liu, X., Zhou, M., Ausavarungnirun, R., Eilert, S., Akel, A., Rosing, T., Narayanan, V., & Zhao, J. (2021) · International Symposium on Low Power Electronics and Design (ISLPED) · doi:10.1109/islped52811.2021.9502474 · Cited by 6
“One representative NVRAM – Resistive RAM (RRAM), or memristor, enables not only data storage ability, but also computation ability [31].”
BackgroundMitigating State-Drift in Memristor Crossbar Arrays for Vector Matrix Multiplication
Amirsoleimani, A., Liu, T., Alibart, F., Eccofey, S., Chang, Y., Drouin, D., & Genov, R. (2021) · IntechOpen eBooks · doi:10.5772/intechopen.100246 · Cited by 6
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.