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 901–1,000 of 1,001
Chung, W. Y., Barkam, H. E., Das, T., & Imani, M. (2025) · ACM Great Lakes Symposium on VLSI (GLSVLSI) · doi:10.1145/3716368.3735241 · Cited by 2
“…multiplications using electrical properties (Ohm’s law and Kirchhoff’s law) of the devices, but often requires analog-to-digital conversion [33, 39]; (2) Digital CIM , which performs Boolean logic operations using resistive switching of memory bitcells to avoid data conversion overhead, at the…”
Marshall, A. D., Goul, R. W., Dodson, B., Sakidja, R., Peelaers, H., Seacat, S., Bray, K. R., Ewing, D., Walsh, M. J., & Wu, J. Z. (2025) · ACS Applied Materials & Interfaces · doi:10.1021/acsami.5c04654 · Cited by 2
Han, C., Qin, H., Shao, W., Fang, H., Zhang, H., Wang, X., Wang, Y., Liu, Y., & Tong, Y. (2025) · Materials · doi:10.3390/ma18184352 · Cited by 2
“Then a synaptic response test on this device was conducted by an electrical pulse scheme [33,34], with the results shown in Figure 3d.”
Improved Memristor Control using Device Physics and Deep Reinforcement Learning
Yang, M.-J., Yu, Z., Pedretti, G., Neftci, E., & Strachan, J. P. (2025) · IEEE International Conference on Artificial Intelligence Circuits and Systems (AICAS) · doi:10.1109/aicas64808.2025.11173161 · Cited by 3
“These WV techniques are widely adopted in memristive hardware accelerators and neuromorphic computing architectures [6], [7], [12].”
Woo, J. S., Choi, K. M., Park, G. T., Chang, J. H., & Choi, W. Y. (2025) · Advanced Intelligent Systems · doi:10.1002/aisy.202500547 · Cited by 2
Gated logic controlled 10T-SRAM for low-power bidirectional ring oscillators
Maheshwari, N., Shah, A. P., & Vishvakarma, S. K. (2025) · Integration · doi:10.1016/j.vlsi.2025.102588 · Cited by 2
Bi-Modal Synapse Based on a Short-Channel Ferroelectric van der Waals Heterostructure
Ram, A., Fusil, S., Masood, S. B., Rajak, N. K., Samanta, G., Soliman, M., Taniguchi, T., Watanabe, K., Doudin, B., Ouerghi, A., et al. (2025) · ACS Applied Materials & Interfaces · doi:10.1021/acsami.5c16593 · Cited by 2
Xu, W., & Zhu, S. (2025) · Neural Networks · doi:10.1016/j.neunet.2025.108266 · Cited by 2
Lee, Y., Kim, S.-M., Kim, S., Shim, W., Kim, S., & Cho, S. (2025) · ACS Omega · doi:10.1021/acsomega.5c08019 · Cited by 2
Tan, L.-P., Hu, X., Li, A.-L., Qing, W.-W., Zhou, M., Yu, D., Zhang, G., Mu, Q.-Q., Wang, Z., Wang, X.-L., et al. (2025) · Chemical Engineering Journal · doi:10.1016/j.cej.2025.171951 · Cited by 2
Zhou, R., Do, H.-S., & Lee, J. (2026) · International Journal of Extreme Manufacturing · doi:10.1088/2631-7990/ae366f · Cited by 2
“Figure 3 outlines the key device requirements and performance metrics essential for scalable neuromorphic computing [63,64] .”
MoF-LoRA: Mixture of Low-Rank Fault-Tolerant Experts for RRAM-Based In-Memory Computing
Ahmed, S. T., Ortega, E., Xiao, P., Feinberg, B., Bennett, C. H., Marinella, M. J., & Chakrabarty, K. (2026) · IEEE Journal on Emerging and Selected Topics in Circuits and Systems · doi:10.1109/jetcas.2026.3655242 · Cited by 3
“In an R-IMC architecture, RRAM cells are arranged as crossbar arrays that have the ability to perform MAC operations in the analog domain, utilizing Ohm’s law and Kirchho ff ’s current summation law [28].”
Synaptic κ‐Ga 2 O 3 Photodetectors for Privacy‐Enhancing Neuromorphic Computing
Jia, Y., Lin, H., Chang, H., Niu, W., Wang, Y., Lu, H., Alquwayzani, A., Banda, Y., Chen, L., Wang, Q., et al. (2026) · Advanced Science · doi:10.1002/advs.75160 · Cited by 2
Min, J., Kwon, Y. A., Kim, H., Kim, J., Jung, M., Heo, J., Kim, G. Y., Mazánek, V., Sofer, Z., Kim, I. S., et al. (2026) · Advanced Functional Materials · doi:10.1002/adfm.75703 · Cited by 2
“Normalized synaptic weights, represented by conductance values scaled between 0 and 1, benefit from a wide dynamic range that enables finer weight tuning and improved learning accuracy [49].”
Yu, Z., Zhao, Z., Han, Q., Wang, Q., Zeng, T., Zeng, Y., Xing, Y., Fang, B., Lv, W., Zhao, C., et al. (2026) · Advanced Materials · doi:10.1002/adma.74005 · Cited by 2
STM Tip-Induced Switching in Molybdenum Disulfide-Based Atomristors
Thompson, J. E., Blue, B. T., Smalley, D., Torres-Davila, F. E., Tétard, L., Robinson, J. T., & Ishigami, M. (2019) · MRS Advances · doi:10.1557/adv.2019.322 · Cited by 2
Susi, G., Bartolacci, F., & Massarelli, M. (2019) · International Journal on Advanced Science Engineering and Information Technology · doi:10.18517/ijaseit.9.4.9438 · Cited by 2
“…solutions in the field of machine learning [36, 42-43] is the emblem of the continuously growing similarities between biological systems and computer science that are characterizing the last few years (computing techniques (e.g., [44]), communication networks (e.g., [45-46]) and so on).”
BackgroundNeuro-inspired computing with emerging memories: where device physics meets learning algorithms
Li, H., Raina, P., & Wong, H. ‐. P. (2019) · Spintronics · doi:10.1117/12.2529916 · Cited by 2
Embracing the Unreliability of Memory Devices for Neuromorphic Computing
Bocquet, M., Hirtzlin, T., Klein, J., Nowak, E., Vianello, E., Portal, J., & Querlioz, D. (2020) · IEEE International Reliability Physics Symposium proceedings · doi:10.1109/irps45951.2020.9128346 · Cited by 2
“tive, phase change and spin torque magnetoresistive memories offer considerable opportunities to advance microelectronics, as these memories are faster than flash memories, while being compact and compatible with the integration in the backend-of-line of modern CMOS processes [1], [2].”
BackgroundNano-polycrystalline Ag-doped ZnO layer for steep-slope threshold switching selectors
Sahota, A., Kim, H. S., Mohan, J., Le, D. N., Jung, Y. C., Kim, S. J., Lee, J., Ahn, J., Hernandez‐Arriaga, H., & Kim, J. (2021) · AIP Advances · doi:10.1063/5.0066311 · Cited by 3
Improved the voltage hysteresis window and endurance in NbOx threshold device by Ti doping
Chen, A., Ma, G., Xiong, R., Wang, H., & Liu, Q. (2024) · Vacuum · doi:10.1016/j.vacuum.2024.113039 · Cited by 2
Adaptive Mixed MLC-SLC FeFET Mapping for CIM AI Applications Through Simulated Annealing
Vardar, A., Müller, F., Geçin, İ., Laleni, N., & Kämpfe, T. (2024) · IEEE International Conference on Artificial Intelligence Circuits and Systems (AICAS) · doi:10.1109/aicas59952.2024.10595943 · Cited by 2
“Edge devices are inherently constrained in terms of area and power, thereby necessitating innovative hardware solutions to execute complex AI algorithms efficiently while maintaining acceptable accuracies[2][3][4].”
BackgroundNeuromorphic Computing and Its Application
Thakral, T., Lamba, L., Singh, M., Chaudhary, T., & Singh, M. (2024) · Wiley eBooks · doi:10.1002/9781394205158.ch9 · Cited by 2
Implementation of Boolean Logic Functions Through Double Gate FD-SOI MOSFET
Ansari, M. H. R., & El‐Atab, N. (2024) · IEEE Access · doi:10.1109/access.2024.3456477 · Cited by 2
“As a result, the in-memory computing architecture provides high bandwidth, massive parallelism, and high energy efficiency by eliminating the overhead of data movement between the CPU and memory unit [11], [12], [13], [14], [27], [28].”
BackgroundNeural network for in-sensor time series recognition based on optoelectronic memristor
Zhang, Z., Wang, Q., Shi, G., & Liu, G. (2025) · Microelectronic Engineering · doi:10.1016/j.mee.2025.112329 · Cited by 2
Temperature-Dependent Two-Phase Switching of the HfO₂-Based Ferroelectric Polarization
Jiao, L., Zhou, Z., Zheng, Z., Wang, X., Xie, J., Zhang, D., Kong, Q., Feng, Y., Sun, C., Liang, G., et al. (2025) · IEEE Transactions on Electron Devices · doi:10.1109/ted.2025.3543157 · Cited by 3
“W ITH the increasing demand for high-density and high-performance nonvolatile memories (NVMs), HfO 2 -based ferroelectric (FE) materials are emerging as strong candidates for both data storage and data-centric computing applications [1], [2], [3], [4], [5], [6], [7].”
Evaluation of FONOS FDSOI FET for Synapse-Inspired Artificial Neural Network
Shaik, R. R., & Pradhan, K. P. (2025) · IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems · doi:10.1109/tcad.2025.3552664 · Cited by 2
“NeuroSim is one of a kind multilayer perceptron/MLP simulator that is quite popular among device/circuit researchers for testing and benchmarking efficiency using MNIST data in ANNs with realistic devices/circuits [35], [36].”
Stack Optimization of TiO x -Based Resistive Switching Devices Through Interface Engineering
Shi, Y., Sachdev, M., & Miao, G. (2025) · IEEE Transactions on Electron Devices · doi:10.1109/ted.2025.3561703 · Cited by 2
“RRAM-based CIM has been demonstrated to be energy-efficient in various deep learning applications such as voice recognition and image processing [4], [5], [6].”
CMOS‐Compatible Protonic Three‐Terminal Memristor for Analog Synapse in Neuromorphic Computing
Liu, L., Dananjaya, P. A., Koh, E. K., Tan, F., Chen, Z., Lim, G. J., Lee, C. X. X., Yang, J., & Lew, W. S. (2025) · Small Methods · doi:10.1002/smtd.202500445 · Cited by 2
Kim, D., Pyo, W. J., Youn, S., 소재희, Kim, Y., Kim, H., & Kim, F. S. (2025) · Device · doi:10.1016/j.device.2025.100940 · Cited by 2
An Enhanced Floating Gate Memory for the Online Training of Analog Neural Networks
Gan, L., Wang, C., Chen, L., Zhu, H., Sun, Q., & Zhang, D. W. (2020) · IEEE Journal of the Electron Devices Society · doi:10.1109/jeds.2020.2964820 · Cited by 2
“But the high erasing voltage and the long operation time (100μs∼1ms) restrict the online training capability [1].”
BackgroundMethodInfluentialRu-based Oxide Resistive Random Access Memory for BEOL-Compatible Novel NVM Applications
Feng, Y., Huang, P. C., Zhou, Z., Zhu, D., Han, R., Ding, X., Liu, L., Liu, X., & Kang, J. (2018) · IEEE International Conference on Solid-State and Integrated Circuit Technology · doi:10.1109/icsict.2018.8564908 · Cited by 2
The Effect of Kr/O2 Sputtering on the Ferroelectric Properties of SrBi2Ta2O9 Thin Film Formation
Zeng, B., Liao, J., Peng, Q., Liao, M., Zhou, Y., & Ohmi, S.-I. (2019) · IEICE Transactions on Electronics · doi:10.1587/transele.2018fup0005 · Cited by 2
Doevenspeck, J., Degraeve, R., Fantini, A., Debacker, P., Verkest, D., Lauwereins, R., & Dehaene, W. (2019) · IEEE Transactions on Electron Devices · doi:10.1109/ted.2019.2957067 · Cited by 3
“This proves to be challenging and has led to a search for the “holy grail” synaptic device, which has hundreds of stable and linearly spaced low-conductance levels that can be reached by blind pulsing [3].”
BackgroundCo-Design of Highly Uniform ReRAM Arrays in 180nm CMOS Technology for Neuromorphic Systems
Zhuo, V. Y.-Q., Wang, W., Chen, Z., Lee, H. K., Li, M., & Song, W. (2019) · IEEE International System-on-Chip Conference (SOCC) · doi:10.1109/socc46988.2019.1570553076 · Cited by 2
“On the other hand, the uniform or non-filamentary ReRAM are still in the early research stage and face fundamental issues such as variability, non-linearity and asymmetry [8].”
BackgroundSynaptic devices based on field-effect transistors
Dai, S., Hao, D., Chen, S., & Huang, J. D. (2020) · Elsevier eBooks · doi:10.1016/b978-0-12-819717-2.00006-0 · Cited by 2
Carbon resistive probe memory designed for ultra-high storage density
Liu, Z., & Wang, L. (2020) · Nanotechnology · doi:10.1088/1361-6528/ab99f4 · Cited by 2
Edge-Etched Al2O3 Dielectric as Charge Storage Region in a Coupled MIS Tunnel Diode Sensor
Chen, B.-J., & Hwu, J. (2020) · IEEE Journal of the Electron Devices Society · doi:10.1109/jeds.2020.3011996 · Cited by 2
“The on/off ratio is 105 which is larger than most of the resistive synaptic device candidates [18].”
BackgroundCoupled Oscillator Networks for von Neumann and Non-von Neumann Computing
Bonnin, M., Traversa, F. L., & Bonani, F. (2021) · Learning and analytics in intelligent systems · doi:10.1007/978-3-030-80571-5_11 · Cited by 2
Ahmed, S. T., Hefenbrock, M., Münch, C., & Tahoori, M. B. (2021) · IEEE European Test Symposium (ETS) · doi:10.1109/ets50041.2021.9465446 · Cited by 2
A Reliability-Concerned Compute-in-Memory Behavior Model for Convolutional Neural Network
Cheng, K., Song, J., Zhang, X., He, Y., Wang, R., & Wang, Y. (2021) · IEEE International Symposium on the Physical and Failure Analysis of Integrated Circuits (IPFA) · doi:10.1109/ipfa53173.2021.9617344 · Cited by 3
Two‐Terminal Neuromorphic Memristors
He, H., Huang, H., & Yang, R. (2021) · Wiley eBooks · doi:10.1002/9783527835317.ch1 · Cited by 5
Periodic Analysis of Resistive Random Access Memory (RRAM)-Based Swish Activation Function
Fatima, A., & Pethe, A. J. (2022) · SN Computer Science · doi:10.1007/s42979-022-01059-3 · Cited by 3
Methods of controlling operation modes in Pt/TaO x /Ta 2 O 5 /Pt resistive switching cells
Miyatani, T., Nishi, Y., & Kimoto, T. (2022) · Japanese Journal of Applied Physics · doi:10.35848/1347-4065/ac6b12 · Cited by 2
Structural Assessment of Interfaces in Projected Phase-Change Memory
Bragaglia, V., Jonnalagadda, V. P., Sousa, M., Sarwat, S. G., Kersting, B., & Sebastian, A. (2022) · Nanomaterials · doi:10.3390/nano12101702 · Cited by 2
Investigation of Deep Spiking Neural Networks Utilizing Gated Schottky Diode as Synaptic Devices
Lee, S., & Bae, J. (2022) · Micromachines · doi:10.3390/mi13111800 · Cited by 2
Lenstra, D., Puts, L., & Yao, W. (2022) · Photonics · doi:10.3390/photonics9110860 · Cited by 2
Super-steep synapses based on positive feedback devices for reliable binary neural networks
Kwon, D., Kim, H., Lee, K.-H., Hwang, J., Shin, W., Bae, J., Woo, S. Y., & Lee, J. (2023) · Applied Physics Letters · doi:10.1063/5.0131235 · Cited by 2
Vardar, A., Munir, A., Laleni, N., De, S., & Kämpfe, T. (2023) · IEEE International Conference on Electronics, Circuits and Systems (ICECS) · doi:10.1109/icecs58634.2023.10382923 · Cited by 2
“Despite the appealing attributes and potential of SNNs, their real-world implementation often confronts hardware limitations, such as restricted computational resources and memory [3].”
BackgroundA Memcomputing Approach to Prime Factorization
Sharp, T. A., Khare, R., Pederson, E., & Traversa, F. L. (2023) · IEEE International Conference on Rebooting Computing (ICRC) · doi:10.1109/icrc60800.2023.10386235 · Cited by 2
“Moreover, there has been a revived interest in neuromorphic computing, where asynchronous digital or analog circuits [15], [16] emulate brain neural networks [17], [18], [19], [20].”
BackgroundThermal Crosstalk Analysis in RRAM Passive Crossbar ArraysPreprint
Pande, S. R., Chakrabarti, B., & Chakravorty, A. (2023) · arXiv (Cornell University) · doi:10.48550/arxiv.2304.01439 · Cited by 2
Amplification of Spin Waves in the Antiferromagnet through the Spin Hall Effect
Mitrofanova, A., Safin, A. R., & Kravchenko, O. V. (2021) · Photonics & Electromagnetics Research Symposium (PIERS) · doi:10.1109/piers53385.2021.9695048 · Cited by 1
Jiang, C.-M., Hsu, C.-A., & Wang, T. (2022) · Journal of Computational Electronics · doi:10.1007/s10825-022-01974-x · Cited by 1
“In each inference operation, an image of the MNIST dataset is randomly selected as the input data and the pixel values are encoded in a read pulse number [2].”
BackgroundMethodSynthesis of silicon-carbon films by induction-assisted plasma-chemical deposition
Темиров, А. А., Kubasov, I. V., Turutin, A. V., Ilina, Т. S., Kislyuk, A. M., Kiselev, D. A., Skryleva, E. A., Sobolev, N. A., Salimon, I. A., Batrameev, N. V., et al. (2023) · Modern Electronic Materials · doi:10.3897/j.moem.9.4.116552 · Cited by 1
Choi, H., Kim, H. W., Hong, E., Kim, N., Jeon, S., Kim, Y., & Woo, J. (2024) · AIP Advances · doi:10.1063/5.0189138 · Cited by 1
GaN-Based Charge Trapping Memory With an AlN Interfacial Layer for Multi-State Operation
Chen, T., Zheng, Z., Feng, S., Zhang, L., Ng, Y. H., & Chen, K. J. (2024) · IEEE Electron Device Letters · doi:10.1109/led.2024.3407118 · Cited by 1
“Beyond standard memory applications, alternative computing paradigms, such as in-memory computing, also require memory devices that exhibit analog conductance states and linear weight updates [21], [22].”
BackgroundExploring a Hybrid SRAM-RRAM Computing-In-Memory Architecture for DNNs Model Inference
Chen, Y., Liu, Z., & Tsai, Y.-J. (2024) · IEEE Computer Society Annual Symposium on VLSI · doi:10.1109/isvlsi61997.2024.00031 · Cited by 1
“A 1-transistor-1-resistor (1T1R) pseudo-crossbar-based CIM architecture with n columns and m rows for performing MAC operations [18].”
BackgroundMethodInfluentialA Novel High Speed Low Power Differential Circuit-Based FRAM Read Scheme
Tao, Q., Ye, J., Cui, X., Jiang, N., Cao, J., Chen, X., Yang, Z., Peng, D., Cai, X., Lian, X., et al. (2024) · IEEE International Conference on Solid-State and Integrated Circuit Technology · doi:10.1109/icsict62049.2024.10831211 · Cited by 1
Impact of Different MAC Schemes on Computing in Memory Based on 1T1R Array
Xie, R. H., Yang, G., Wang, Z., Shan, L., Li, J., Ban, C., Bao, L., Liang, L., Wang, C., Cai, Y., et al. (2024) · IEEE International Conference on Solid-State and Integrated Circuit Technology · doi:10.1109/icsict62049.2024.10831317 · Cited by 1
“…(MRAM), and Ferroelectric Random Access Memory (FERAM) are gaining increasing attention because they allow computations to be performed within memory units and results to be stored in situ due to their non-volatility, which can address the memory wall issue and improve energy efficiency [1-4].”
Adaptive silicon synapse and CMOS neuron for neuromorphic VLSI computing
El-Khatib, Z., Moussa, S., Kamalov, F., & YAGOUB, M. C. E. (2025) · IAES International Journal of Artificial Intelligence · doi:10.11591/ijai.v14.i2.pp1000-1021 · Cited by 1
Chen, Y., Lin, C., Lin, C., & Lin, C.-H. (2025) · ECS Journal of Solid State Science and Technology · doi:10.1149/2162-8777/adc3c1 · Cited by 1
Zhou, N., Yang, L., Zhang, L., Irfan, M., Mo, Y., Chu, P. K.-H., & Li, J. (2025) · Journal of Applied Physics · doi:10.1063/5.0241290 · Cited by 1
Liu, Z., Cao, J., Wang, Q., Hou, H., & Zhao, Y. (2025) · Small · doi:10.1002/smll.202502912 · Cited by 1
Kang, M., Kim, M., Kang, J., Won, J., Seo, H. J., Joe, C., Roh, Y., Park, Y., & Kim, S. (2025) · IEEE Journal of the Electron Devices Society · doi:10.1109/jeds.2025.3576795 · Cited by 1
“The synaptic memory must support linear and symmetric weight updates, high endurance, and fast programming speed for optimal on-chip training, while requiring long data retention at the same time for robust inference [4].”
Seo, H. J., Byun, K., Kang, M., Roh, Y., Joe, C., & Kim, S. (2025) · Advanced Intelligent Systems · doi:10.1002/aisy.202500139 · Cited by 1
Meng, F., Xu, X., Wu, T., Xu, X., Guo, X., Tang, Q., & Zhao, L. (2025) · International Symposium of Electronics Design Automation (ISEDA) · doi:10.1109/iseda65950.2025.11101657 · Cited by 1
“Processing-in-memory (PIM) architecture has emerged as an effective solution to overcome the aforementioned limitations of von Neumann architectures [2].”
Xiang, R., Dou, W., Liu, J., Liu, S., Xiao-dong, X., Chen, P., Peng, Y., Zhou, W., & Tang, D. (2025) · Applied Physics Letters · doi:10.1063/5.0282986 · Cited by 1
Memristor-Assisted Secure SRAM Architectures for Protection Against Data Imprinting Attacks
Singh, A., Chakraborty, S., Yin, Z., & Jaiswal, A. (2025) · IEEE International Conference on Omni-layer Intelligent Systems (COINS) · doi:10.1109/coins65080.2025.11125771 · Cited by 1
“This configuration effectively divides the device into two distinct regions with contrasting resistive properties: a high-resistance undoped section and a low-resistance doped section [13].”
Inner Gate Length Modulation of MFMIS Nanosheet FET Memory for Advanced Technology Nodes
Choi, K. M., Woo, J. S., & Choi, W. Y. (2025) · IEEE Access · doi:10.1109/access.2025.3602436 · Cited by 1
“Various types of non-volatile memories (NVMs) have been investigated as synaptic devices for in-memory computing [1], [2], [3].”
Demonstration of Chloride Ion Modulation- Doped InGaZnO Dual-Channel Synaptic Transistors
Chen, H.-W., Song, C.-Y., Wu, J.-Z., Chao, Y., Jiang, J.-F., Lin, Z.-D., & Liu, H.-Y. (2025) · IEEE Transactions on Electron Devices · doi:10.1109/ted.2025.3603794 · Cited by 1
Matsui, C., Yamada, A., Misawa, N., & TAKEUCHI, K. (2025) · IEICE Transactions on Fundamentals of Electronics Communications and Computer Sciences · doi:10.1587/transfun.2025vlp0011 · Cited by 1
Waghmare, V. P., Hati, A. J., Bansod, S., & Singh, S. K. (2025) · International Conference on Computing Technologies & Data Communication (ICCTDC) · doi:10.1109/icctdc64446.2025.11158731 · Cited by 1
“With the non-volatility and adaptive resistance of PCM, the resulting structures are configurable and low-power logic-in-memory systems that dynamically scale with computation needs [17].”
Low-dimensional silicon for neuromorphic computing
Malik, M., Wang, Y., Ni, Z., Anwar, M. A., Wang, C., Shehzad, K., Ali, A., Ali, N., Bodepudi, S. C., Pi, X., et al. (2025) · Chip · doi:10.1016/j.chip.2025.100169 · Cited by 2
Fault Tolerance in RRAM-based AI Accelerator with Guided Randomized Activation
Ahmed, S. T., Ortega, E., Depsey, R., Xiao, P., Feinberg, B., Bennett, C. H., Marinella, M. J., & Chakrabarty, K. (2025) · IEEE International Test Conference (ITC) · doi:10.1109/itc58126.2025.00039 · Cited by 2
“RRAM has emerged as a promising technology for energy-efficient neural network accelerators due to its ability to perform in-situ analog MVM within memory arrays [18].”
Yadav, M. S., Gupta, A. K., & Rawat, B. (2025) · ACS Applied Nano Materials · doi:10.1021/acsanm.5c04152 · Cited by 1
Maheshwari, N., Gupta, B. B., & Vishvakarma, S. K. (2025) · IEEE Internet of Things Journal · doi:10.1109/jiot.2025.3636998 · Cited by 1
“To overcome this challenge, the compute-in-memory (CIM) paradigm has gained significant attention, as it mitigates data movement by enabling in situ processing within the memory array itself [6].”
An, S., Shen, L., Liu, T., Wang, Y., Han, Q., & Liu, M. (2025) · ACS Applied Materials & Interfaces · doi:10.1021/acsami.5c20352 · Cited by 1
XBTorch: A unified framework for modeling and co-design of crossbar-based deep learning accelerators
Yousuf, O., Glasmann, A., Lueker-Boden, M., Najmaei, S., & Adam, G. C. (2026) · APL Machine Learning · doi:10.1063/5.0320632 · Cited by 2
A survey on analog memristor emulators and their applications
Shaheen, F., Azab, E., & Hassan, A. (2026) · AEU - International Journal of Electronics and Communications · doi:10.1016/j.aeue.2026.156223 · Cited by 1
Gate insulator stack engineering for fully CMOS-compatible reservoir computing
Hwang, J., Park, M.-K., Kim, J., Bae, J.-H., & Lee, J. (2026) · Nano Convergence · doi:10.1186/s40580-026-00533-5 · Cited by 1
RoboPIM: A ReRAM-Based Accelerator for LLM-Based Robotics Applications via Dynamic Task Slicing
Xiao, W., Wang, J., Chen, D., Li, H., Guizani, M., Chen, M., & Wu, T. (2026) · IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems · doi:10.1109/tcad.2026.3660201 · Cited by 1
“FPGAs and ASICs su ff er from high data movement [28] during memory-intensive LLM inference, and static / dynamic random access memory (SRAM) PIMs [29], [30] are limited by low density and significant leakage / refresh power, which are prohibitive for energy-constrained robotics.”
Matsui, C., Yamada, A., Suzuki, S., Misawa, N., & Takeuchi, K. (2026) · IEEE transactions on circuits and systems for artificial intelligence. · doi:10.1109/tcasai.2026.3661436 · Cited by 1
“In analog current-sensing CiM, errors in neural network weights and input/output are tolerable [13], [14], but IR drop due to interconnection resistance degrades MAC results [15], [16], [17], [18], [19], [20], [21].”
Scalable High-Fidelity Solver for Large-Scale ReRAM Crossbar Arrays Under I–V Nonlinearity
Chen, W., Xu, Q., Chen, S. J. H., Kang, Y., & Yu, B. (2026) · ACM Transactions on Design Automation of Electronic Systems · doi:10.1145/3797485 · Cited by 1
Prajapati, M., Solanki, M., Patel, K., Patel, K., Bhatt, G., Sharma, S. S., & Ray, J. (2026) · ChemistrySelect · doi:10.1002/slct.202505209 · Cited by 1
Sharma, K., Nayak, M., Bhatt, A., & Tiwari, S. K. (2026) · International Conference on Electronics and Renewable Systems (ICEARS) · doi:10.1109/icears67481.2026.11416558 · Cited by 1
“Memristors are considered suitable for neuromorphic computing since their gradual resistance changes behave similarly to biological synapses [4-5], [8] .”
Benmeziane, H., Lammie, C., Boybat, I., Rasch, M., Gallo, M. L., Vasilopoulos, A., Tsai, H.-S., Burr, G., Narayanan, V., Maghraoui, K. E., et al. (2026) · Nature Communications · doi:10.1038/s41467-026-71071-1 · Cited by 1
Kumar, L., Kurup, S., Bhatt, B. B., & Gupta, D. (2026) · Applied Materials Today · doi:10.1016/j.apmt.2026.103221 · Cited by 1
Calibration and Enhancement of Analytical IR-Drop Model for Resistive Crossbar Arrays
Rizzi, T., Lambertini, A., Zanotti, T., Lepri, N., Pavan, P., Puglisi, F. M., Ielmini, D., & Zambelli, C. (2026) · IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems · doi:10.1109/tcad.2026.3685531 · Cited by 1
Coupling atomic layer design with switching dynamics in sub-2 nanometer oxide memristors
Marshall, A. D., Seacat, S., Avalos, D. T., Tabassum, A., Goul, R. W., Dodson, B., Peelaers, H., Hernández, C. M., Sakidja, R., & Wu, J. Z. (2026) · Communications Materials · doi:10.1038/s43246-026-01116-x · Cited by 1
In-Memory Computing Enabled Deep MIMO Detection to Support Ultra-Low-Latency Communications
Ding, T., Zeng, Q., & Huang, K. (2026) · IEEE Transactions on Mobile Computing · doi:10.1109/tmc.2026.3699403 · Cited by 1
“The C2C variation σ Δ g quantifies the fluctuation in conductance change induced by each programming pulse, and is expressed as a percentage of the full conductance range [35]: where the coefficient γ typically falls within the interval (0, 0.05) [36].”
InfluentialA Memristor‐Based In‐Memory Computing System‐on‐Chip with Efficient Depthwise Convolution
Song, W., Cai, F., Park, S., Li, Z., 이희철, Rao, M., Choi, W.-H., Shin, S., Zhu, Y., Chae, S., et al. (2026) · Advanced Intelligent Systems · doi:10.1002/aisy.202501225 · Cited by 1
Field- and Temperature-Induced Drift in Multi-Level Al-Doped HfO 2 RRAM
Baroni, A., Wen, J., Pérez, E., Reddy, K. D. S., Uhlmann, M., Pechmann, S., Wenger, C., Ielmini, D., & Zambelli, C. (2026) · IEEE Transactions on Device and Materials Reliability · doi:10.1109/tdmr.2026.3700862 · Cited by 1
“In particular, filamentary RRAM arrays enable energy-e ffi cient vector-matrix multiplication (VMM) for arti-ficial neural networks (ANNs) by storing synaptic weights directly in the device conductance [5], [6], [7], [8].”
Marium, S. M., & Chen, S. (2026) · Microelectronics · doi:10.3390/microelectronics2020010 · Cited by 1
Self‐Powered Neuromorphic Systems Based on Tribotronics Synaptic Devices
Shrestha, K., Akbari, M. K., Anbari, A. P., Pandey, P., & Zhuiykov, S. (2026) · Small · doi:10.1002/smll.74180 · Cited by 1
Surface Acoustic Wave-Guided Reconfigurable Memristor
Kim, S. K., Lee, J. W., Ryu, H., Kim, T. H., Ko, H., Choi, S. H., Kim, Y. C., Qi, K., Novikov, I. V., Nam, J., et al. (2026) · ACS Nano · doi:10.1021/acsnano.6c01958 · Cited by 1
Thakur, V., More, V. N., & Bhatt, A. (2026) · Journal of Systems Architecture · doi:10.1016/j.sysarc.2026.103940 · Cited by 1
Singla, R., Pant, D., Nautiyal, P., & Painuly, A. (2026) · RSC Advances · doi:10.1039/d6ra05168e · Cited by 1
RRAM-based computing-in-memory: Devices, arrays, circuits, and applications
Lu, W., Yang, H., Li, Y., Luo, X., Li, Y., Fu, Y., Ye, W., Guo, X. F., Yu, L., Gao, H., et al. (2026) · Journal of Systems Architecture · doi:10.1016/j.sysarc.2026.103984 · Cited by 1
Resistance-Based Embedded Non-Volatile Memories as Synaptic Devices in Spiking Neural Networks
Koushan, F. S., & Kang, S.-M. S. (2019) · IEEE Workshop on Microelectronics and Electron Devices (WMED) · doi:10.1109/wmed.2019.8714149 · Cited by 1
“In addition, there have been some papers attempting to highlight the key characteristics of NVM devices for neural network applications [15], focusing on energy-efficient computation.”
BackgroundLinear Weight Update in MoS2/Graphene Memristive Synapses for Unsupervised Learning
Krishnaprasad, A., Das, S., Choudhary, N., Dev, D., Chung, H., Aina, O., Jung, Y., & Roy, T. (2019) · Conference digest · doi:10.1109/drc46940.2019.9046458 · Cited by 1
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.