Memristor‐Based Analog Computation and Neural Network Classification with a Dot Product Engine
The DOI matches its Crossref record; 38 of the 39 references it cites were found in a registry or an index.
Abstract
Using memristor crossbar arrays to accelerate computations is a promising approach to efficiently implement algorithms in deep neural networks. Early demonstrations, however, are limited to simulations or small‐scale problems primarily due to materials and device challenges that limit the size of the memristor crossbar arrays that can be reliably programmed to stable and analog values, which is the focus of the current work. High‐precision analog tuning and control of memristor cells across a 128 × 64 array is demonstrated, and the resulting vector matrix multiplication (VMM) computing precision is evaluated. Single‐layer neural network inference is performed in these arrays, and the performance compared to a digital approach is assessed. Memristor computing system used here reaches a VMM accuracy equivalent of 6 bits, and an 89.9% recognition accuracy is achieved for the 10k MNIST handwritten digit test set. Forecasts show that with integrated (on chip) and scaled memristors, a computational efficiency greater than 100 trillion operations per second per Watt is possible.
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
“A cost-effective recurrent solution has been to use a smaller number of DACs and share them among different rows by adding a layer of analogue multiplexors between the DACs and the wordline inputs93,95,221. With this approach (which we could refer to as On-chip time-multiplexed analogue input – Analogue/Multilevel weights), a given VMM operation is divided in n different sub-VMM operations and the”
From Hardware implementation of memristor-based artificial neural networks (2024) · cites this paper as [221]
In the citing paper
“The main weakness of that technology, however, is extremely large, of the order of 2500 µm2, size of 1T1R cell, and high (mS-scale) device conductance, which necessitates bulky and energy-hungry peripheral circuits.”
From 4K-memristor analog-grade passive crossbar circuit (2021) · cites this paper as [23]
In the citing paper
“Moreover, the demonstrated artificial neural network is close in complexity to the state-of-the-art neuromorphic prototypes based on (>10,000 sparser and 10× more conductive) 1T1R ReRAM devices23,33.”
From 4K-memristor analog-grade passive crossbar circuit (2021) · cites this paper as [23]
In the citing paper
“the memristive dot product engine (MDPE), which performs large-scale vector-matrix multiplication (VMM) operations using a memristive crossbar array6–13”
From Flexible self-rectifying synapse array for energy-efficient edge multiplication in electrocardiogram diagnosis (2025) · cites this paper as [7]
Citations
Cites
Training and operation of an integrated neuromorphic network based on metal-oxide memristors
Prezioso, M., Merrikh-Bayat, F., Hoskins, B. D., Adam, G. C., Likharev, K. K., & Strukov, D. B. (2015) · Nature · doi:10.1038/nature14441 · Cited by 3,001
Backus, J. (1978) · Communications of the ACM · doi:10.1145/359576.359579 · Cited by 2,609
Neuromorphic electronic systems
Mead, C. (1990) · Proceedings of the IEEE · doi:10.1109/5.58356 · Cited by 2,368
Memristors with diffusive dynamics as synaptic emulators for neuromorphic computing
Wang, Z., Joshi, S., Savel’ev, S. E., Jiang, H., Midya, R., Lin, P., Hu, M., Ge, N., Strachan, J. P., Li, Z., et al. (2017) · Nature Materials · doi:10.1038/nmat4756 · Cited by 2,358
Self-citationNeuromorphic Silicon Neuron Circuits
Indiveri, G., Linares-Barranco, B., Hamilton, T. J., Schaik, A. V., Etienne-Cummings, R., Delbruck, T., Liu, S.-C., Dudek, P., Häfliger, P., Renaud, S., et al. (2011) · Frontiers in Neuroscience · doi:10.3389/fnins.2011.00073 · Cited by 1,821
International Conference on Learning Representations (ICLR)
Abbas, M. Z. A., Kivinen, J., & Raiko, T. (2016) · Cited by 1,694
Analogue signal and image processing with large memristor crossbars
Li, C., Hu, M., Li, Y., Jiang, H., Ge, N., Montgomery, E., Zhang, J., Song, W., Dávila, N., Graves, C. E., et al. (2017) · Nature Electronics · doi:10.1038/s41928-017-0002-z · Cited by 1,292
Self-citationNeuromorphic computing using non-volatile memory
Burr, G. W., Shelby, R. M., Sebastian, A., Kim, S., Kim, S., Sidler, S., Virwani, K., Ishii, M., Narayanan, P., Fumarola, A., et al. (2017) · Advances in Physics: X · doi:10.1080/23746149.2016.1259585 · Cited by 1,107
Burr, G. W., Shelby, R. M., Sidler, S., di Nolfo, C., Jang, J., Boybat, I., Shenoy, R. S., Narayanan, P., Virwani, K., Giacometti, E. U., et al. (2015) · IEEE Transactions on Electron Devices · doi:10.1109/ted.2015.2439635 · Cited by 936
Kim, K.-H., Gaba, S., Wheeler, D., Cruz-Albrecht, J. M., Hussain, T., Srinivasa, N., & Lu, W. (2012) · Nano Letters · doi:10.1021/nl203687n · Cited by 924
Research works printed but not linked: 20
- Chen Y., 2014, Proc. 47th Annual IEEE/ACM Int. Symp. on Microarchitecture, 609
- Chen Y.‐H., 2016, Proc. 43rd Int. Symp. on Computer Architecture, 367
- Reagen B., 2016, Proc. 43rd Int. Symp. on Computer Architecture, 267
- Liu S., 2016, Proc. 43rd Int. Symp. on Computer Architecture, 393
- Chi P., 2016, Proc. 43rd Int. Symp. on Computer Architecture, 27
- Shafiee A., 2016, Proc. 43rd Int. Symp. on Computer Architecture, 14
- Steinbuch K., 1961, Biol. Cybern., 1, 36
- Chawla R., 2004, Proc. IEEE 2004 Custom Integrated Circuits Conf., 651
- Suri M., 2011, Proc. 2011 IEEE Int. Electron Devices Meeting (IEDM), 4
- Yu S., 2012, Proc. 2012 IEEE Int. Electron Devices Meeting (IEDM), 10
- Burr G. W., 2015, Proc. 2015 IEEE Int. Electron Devices Meeting (IEDM), 4
- Yu S., 2016, Proc. 2016 IEEE Int. Electron Devices Meeting (IEDM), 12
- Agarwal S., 2016, Proc. 2016 Int. Joint Conf. on Neural Networks, 929
- Rastegari M., 2016, Proc. European Conf. on Computer Vision, 525
- S.Zhou Y.Wu Z.Ni X.Zhou H.Wen Y.Zou arXiv Prepr. arXiv1606.061602016.
- LeCun Y., 1998, The MNIST Database of Handwritten Digits
- Hu M., 2016, Proc. 2016 53nd ACM/EDAC/IEEE Design Automation Conf., 1
- Hu M., 2016, Proc. IEEE Int. Conf. on Rebooting Computing (ICRC), 1
- Liu C., 2017, in 2017 54th ACM/EDAC/IEEE Design Automation Conference (DAC), 1
- Der Plas G., 2008, Proc. 2008 IEEE Int. Solid‐State Circuits Conf. (ISSCC) Dig. Tech. Pap., 242
Cited by
Items 701–751 of 751
A Memristor-Based Adaptive Pooling Network for Cnn OptimizationPreprint
Guo, W., Feng, Z., Zou, J., Shi, T., Wang, Z., Tan, S. E., Xu, Z., Zhu, Y., Dai, Y., & Wu, Z. (2023) · SSRN Electronic Journal · doi:10.2139/ssrn.4648000
Memristor-based Mixed Training Scheme with Multi-level Sparsification
Xiong, F., Hu, X., & Zhou, Y. (2023) · IEEE International Conference on Memristive Computing and Applications (ICMCA) · doi:10.1109/icmca59770.2023.10481481
Chee, M. Y. (2023) · DR-NTU (Nanyang Technological University) · doi:10.32657/10356/173840
Kim, K. M., Cheong, W. H., In, J. H., Jeon, J. B., & Kim, G. Y. (2024) · Research Square · doi:10.21203/rs.3.rs-4019510/v1
Lee, H. Y., Park, J. H., Choi, S. C., & Choi, B. J. (2024) · Applied Physics A · doi:10.1007/s00339-024-07641-1
Heo, D., Bang, H., & Ko, J. H. (2024) · ACM/IEEE Design Automation Conference (DAC) · doi:10.1145/3649329.3656535
Neuromorphic Computing in Autonomous Distributed Grid Control
Obert, J., Trevizan, R. D., & Chavez, A. (2024) · Conference on AI, Science, Engineering, and Technology (AIxSET) · doi:10.1109/aixset62544.2024.00025
“Specific FPAAs called field programmable neural arrays (FPNAs) [10] and NeuroFPAA [11] are designed for neuromorphic systems.”
Xiong, F., Zhou, Y., Hu, X., & Duan, S. (2024) · Applied Intelligence · doi:10.1007/s10489-024-05957-2
A simple interface circuit for edge inference kernels based on SC-LNO memristor crossbar
Wang, S.-C., Liu, Y., Liu, X., Liu, Y., Liu, Z., & Xing, Z. (2025) · Microelectronics Journal · doi:10.1016/j.mejo.2024.106537
Polarity dependent predictable and random resistive switching in forming-free unipolar memristors
Rayapati, V. R., Vegesna, S. V., Bhat, V. J., Blaschke, D., Diegel, M., Dellith, A., Dellith, J., Bürger, D., Skorupa, I., & Schmidt, H. (2025) · AIP Advances · doi:10.1063/5.0226262
Interconnection Tensor Rank and the Neural Network Storage Capacity
Kryzhanovsky, B. (2025) · Optical Memory and Neural Networks · doi:10.3103/s1060992x25600272
ReSMiPS: A ReRAM-based Sparse Mixed-precision Solver with Fast Matrix Reordering Algorithm
Fu, Y., Li, J., Chen, J., Zhou, Z., Zhou, H., Peng, W., Li, Y., & Miao, X. (2025) · ACM/IEEE Design Automation Conference (DAC) · doi:10.1109/dac63849.2025.11133301
“By enabling parallelized multiplication and accumulation (MAC) operations directly within the analog domain [2], this technology has demonstrated significant improvements in com-This article has received funding from the STI 2030—Ma-jor Projects (grant no. 2021ZD0201201), National Key Research and…”
Self-citationJiang, Z., Shi, H., Huang, Z., Bai, B. B., Zhang, G., & Hou, H. (2025) · IEEE International Symposium on Information Theory (ISIT) · doi:10.1109/isit63088.2025.11195392
Integrated Electroforming of Memristor Cells in Crossbar Arrays
Heinen, R., Zoche, J., Wunderlich, R., & Heinen, S. J. (2025) · IEEE Nordic Circuits and Systems Conference (NorCAS) · doi:10.1109/norcas66540.2025.11231282
Tun, T. T. T., Huo, J., & Ang, K. (2025) · Nanoscale Horizons · doi:10.1039/d5nh00675a · Cited by 1
On-Chip Row Pruning for One-Hot Encoded Snns in Memristive Dot Product Engines
Tushar, S. N. B., Buchanan, G., Sabrin, T., Das, H., & Rose, G. S. (2025) · IEEE International Midwest Symposium on Circuits and Systems (MWSCAS) · doi:10.1109/mwscas53549.2025.11244319
“The synapse in the MDPE is typically 1T1R (1 transistor, 1 Resistive RAM) [1], [3], [9], [13], although 0T1R, 2T1R and 3T1R configurations can also be utilized [2], [3], [11].”
InfluentialZhong, D. (2025) · Discover Electronics · doi:10.1007/s44291-025-00142-2
“This enables massively parallel multiply-accumulate operations and achieves energy efficiencies orders of magnitude higher than conventional GPUs [16–18].”
Neuromorphic Computing With Emerging Memories
Zhao, R., & Yang, J. J. (2025) · Computer · doi:10.1109/mc.2025.3615214
Self-citationA VHF memristor emulator for crossbar synaptic simulation
Dai, G., Liu, B., Yang, S., Li, W. H., Wu, D., & Yuefeng, H. (2025) · International Conference on Integrated Circuits and Microsystems (ICICM) · doi:10.1109/icicm66614.2025.11315923
“The in-memory computing implemented by memris-tors is different from the traditional computation, it can realize non-binary calculation based on the resistance variability of memristors [20], [32].”
Jiang, N., Xie, J., Li, D., Huang, H., & Zeng, Z. (2026) · Nonlinear Dynamics · doi:10.1007/s11071-025-11955-x · Cited by 1
Hybrid Memristor-CMOS System: Circuit Design Solutions for Control and Data Processing
Tokarev, A. A., & Khorin, I. A. (2025) · Russian Microelectronics · doi:10.1134/s1063739725601183
Study and analysis of memristor for analog and digital design
Pandya, J. D., & Gupta, R. (2026) · Analog Integrated Circuits and Signal Processing · doi:10.1007/s10470-026-02566-6
A generic compact model for resistive memories and switches
Jung, S., Kim, H., Park, J., Kim, S., & Kim, M.-H. (2026) · Scientific Reports · doi:10.1038/s41598-026-42077-y
“S9 50,51 .”
Bayesian neuromorphic computing based on resistive memory
Dalgaty, T. (2020) · theses.fr (ABES) · doi:10.70675/e5b4f3e2z44a5z4c41zbac6z4c933e86b101 · Cited by 1
Energy-Efficient Memristor-Based Artificial Intelligence Accelerators using In/Near Memory Computing
Harabi, K.-E. (2023) · theses.fr (ABES) · doi:10.70675/0d4bc45bzeef3z40b2z8ce9z8b08b84ee143 · Cited by 8
RRAM co-integration with OTS-based back-end selector : from devices to applications
Lopez, J. M. (2022) · theses.fr (ABES) · doi:10.70675/197a0071z4b82z48fdzad97zce487a71c1af
Alimisis, V., Papathanasiou, A., Moustakas, V., Mylona, A., Dimas, C., & Sotiriadis, P. P. (2026) · IEEE Open Journal of Circuits and Systems · doi:10.1109/ojcas.2026.3665625
“Hu et al. proposed a single-layer 128 × 64 crossbar array ANN that attained 89.9% accuracy on an image recognition task [50].”
InfluentialBiomimetic-voltage nitride-enhanced memristor arrays for femtojoule in-memory biosignal processing
Wang, Z., Zhang, Z., Zhang, G., Fan, X., Li, P., Zhu, B., Tong, Y., Zhang, P., Gao, D., Yu, B., et al. (2026) · Nature Communications · doi:10.1038/s41467-026-72740-x · Cited by 1
“Inputfeatures Y undergoparallelMACviamemristor array 73,74 : Memristor-based MAC accelerates inference by mapping computation directly onto hardware physics, reducing both power consumption and computational latency 75 .”
Ha, H., Kim, D., Kwon, O., Seo, Y., & Hwang, H. (2026) · IEEE Electron Device Letters · doi:10.1109/led.2026.3691110
“Resistive-array-based hardware neural networks (HNNs) enable in-memory analog vector-matrix multiplication (VMM), reducing data movement and improving energy e ffi ciency [3], [4], [5], [6].”
Unified matrix-parallel outer-product updates for pretrained deployment and on-device adaptationPreprint
Lee, J., Lee, I.-S., Lee, K. H., Koo, R., Im, J., Park, S., Ko, J., Hwang, J., Ryu, S., & Lee, K. H. (2026) · Research Square · doi:10.21203/rs.3.rs-9144413/v1
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].”
Husawi, A. (2026) · Engineering Technology & Applied Science Research · doi:10.48084/etasr.17793
“Non-volatile alternatives, including Resistive RAM (ReRAM) [11], Phase Change Memory (PCM) [12], Memristors [13], and Spin-Transfer Torque RAM (STTRAM) [14], provide data persistence and higher density but often face challenges with device variability and endurance.”
Low-Complexity Rule-Based Greedy Optimization of Refractory Periods for In-Memory SNN
Tushar, S. N. B., Alam, S. H., Chakraborty, N. N., Schuman, C. D., Das, H., & Rose, G. S. (2026) · IEEE Dallas Circuits and Systems Conference (DCAS) · doi:10.1109/dcas69364.2026.11544440
Non-idealities in artificial synapses
Hamid, S. B., Incorvia, J. A. C., & Liu, S. (2026) · Nature Reviews Physics · doi:10.1038/s42254-026-00957-2 · Cited by 1
“One technique to address device-to-device variability in RRAMs is to introduce a column-wise calibration 158 .”
Adaptive Redox Resistive Memory Programming for Efficient and Robust Class‐Incremental Learning
Li, Y., Yang, J., 侯群生, Wang, S., Liu, S., Zhang, H., Ye, Z., Jiang, J., Lin, N., Xu, X. X., et al. (2026) · Advanced Materials · doi:10.1002/adma.202600025
Self-citationFully Sputtered HfO y /HfO x RRAM: Improved Synaptic Behavior for Neuromorphic Training Accelerators
Kim, Y., Jeon, S., Lim, S., & Woo, J. (2026) · IEEE Transactions on Electron Devices · doi:10.1109/ted.2026.3714373
“Several studies have demonstrated successful chip-level implementations of neuromorphic systems using RRAM arrays containing these oxides, highlighting the practical viability of these systems [18], [19].”
Zhang, X., Ye, Y., Guan, N., Li, H., Yang, D., Wu, J., Xu, J., Li, F., & Li, H. (2026) · Journal of Materials Chemistry C · doi:10.1039/d6tc01692h
Van, T. N. (2026) · Kufa Journal of Engineering · doi:10.30572/2018/kje/170320
Flexible Neuromorphic Memristor with Copper Iodide Switching Layer
Klochko, N. P., Петрушенко, С. И., Fijałkowski, M., Fedonenko, D., & Сухов, Р. В. (2026) · Lecture notes in electrical engineering · doi:10.1007/978-3-032-23369-1_2
Ricci, S., Mannocci, P., Porzani, M., Bridarolli, D., Carletti, F., Farronato, M., & Ielmini, D. (2026) · Advanced Electronic Materials · doi:10.1002/aelm.202600012
“In this experiment, we focus on a simple neural network consisting of a single-layer perceptron to support the RRAM for AI applications [ 49–51 ].”
Shiksha, & Kumar, M. (2026) · Advanced Materials Technologies · doi:10.1002/admt.71267
Li, H., Lu, J., Zhou, J., Wen, Y., Wang, J., Cao, X., Xu, W., Chen, Q., Lu, Y., & Jiang, R. (2026) · Research Square · doi:10.21203/rs.3.rs-10809143/v1
A Water‐Resistant Bi‐Based Optoelectronic Synapse for Underwater Neuromorphic Vision
Bai, Y., Li, X., Yang, Y., Kuang, D., & Li, Y. (2026) · Advanced Optical Materials · doi:10.1002/adom.71784
“In recent years, significant progress has been made in the field of neuromorphic computing in the utilization of various opto-electronic material systems, such as oxides [ 20, 21 ], perovskites [ 22–25 ], organic semiconductors [ 26, 27 ], and two-dimensional materials [ 28–31 ].”
Self-citationHajiabadi, Z., Thomas, D. B., Chong, H. M. H., & Simanjuntak, F. M. (2026) · Advanced Electronic Materials · doi:10.1002/aelm.70558
Rossetti, D., Xu, Y., Asselta, L., Yang, J. J., Williams, R. S., & Corinto, F. (2026) · Advanced Electronic Materials · doi:10.1002/aelm.70580
Self-citation3D integration of 2D electronics for AI hardware
Seok, H., Son, S., Choi, H., Kim, G., Lee, D., Son, S., Lee, J.-H., Kim, G., & Kim, T. (2026) · InfoMat · doi:10.1002/inf2.70191
Dong, C., Xie, X., Chen, J., Tan, G., Huang, Y., & Cao, S. (2026) · Electronics · doi:10.3390/electronics15194512
Gül, F. (2026) · Computer Applications in Engineering Education · doi:10.1002/cae.70283
Analogue fast Fourier transforms for scalable and efficient signal processing
Xiao, T. P., Feinberg, B., Richardson, D. K., Cannon, M. J., Madsen, C., Medu, H., Agrawal, V. S., Marinella, M. J., Agarwal, S., & Bennett, C. H. (2026) · Nature Electronics · doi:10.1038/s41928-026-01725-x · Cited by 2
Lee, S., Yoo, S.-M., Jeong, Y., Kim, J., Jang, H. J., Park, J., Park, S., Lee, S., Ju, B., Park, J., et al. (2026) · Advanced Electronic Materials · doi:10.1002/aelm.70618
Metadata
- Authors
- Hu, M., Graves, C. E., Li, C., Li, Y., Ge, N., Montgomery, E., Davila, N., Jiang, H., Williams, R. S., Yang, J. J., Xia, Q., & Strachan, J. P.
- Affiliations
- Hewlett-Packard (United States) (US)
- University of Massachusetts Amherst (US)
- Hewlett Packard Labs Hewlett Packard Enterprise Palo Alto CA 94304 USA
- Corresponding author
- Yang, J. Joshua
- Xia, Qiangfei
- Strachan, John Paul
- ORCID
- Venue
- Advanced Materials
- Publisher
- Wiley
- Published
- 2018-01-10
- Volume
- 30
- Issue
- 9
- ISSN
- 0935-9648 (ISSN-L)
- 1521-4095
- OpenAlex
- W2782791387
- Cited by
- 751
- References
- 39
- Citations by year
- 2026: 41 · 2025: 80 · 2024: 85 · 2023: 102 · 2022: 114 · 2021: 105 · 2020: 117 · 2019: 72 · 2018: 33
- FWCI
- 31.28
- Type
- journal article
- Language
- en
- Open access
- closed
- Licence
- Locations
- Advanced Materials (publishedVersion)
- PubMed (publishedVersion)
- Funders
- Office of the Director of National Intelligence
- Intelligence Advanced Research Projects Activity (2014‐14080800008)
- 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 Applications
- Keywords
- memristors, memristor crossbar, analog computing, neural network inference, matrix-vector multiplication, MNIST handwritten digit recognition, energy-efficient computing
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.