Binary neural network with 16 Mb RRAM macro chip for classification and online training
The DOI matches its Crossref record; 13 of the 15 references it cites were found in a registry or an index.
Abstract
On-chip implementation of large-scale neural networks with emerging synaptic devices is attractive but challenging, primarily due to the pre-mature analog properties of today's resistive memory technologies. This work aims to realize a large-scale neural network using today's available binary RRAM devices for image recognition. We propose a methodology to binarize the neural network parameters with a goal of reducing the precision of weights and neurons to 1-bit for classification and <;8-bit for online training. We experimentally demonstrate the binary neural network (BNN) on Tsinghua's 16 Mb RRAM macro chip fabricated in 130 nm CMOS process. Even under finite bit yield and endurance cycles, the system performance on MNIST handwritten digit dataset achieves ~96.5% accuracy for both classification and online training, close to ~97% accuracy by the ideal software implementation. This work reports the largest scale of the synaptic arrays and achieved the highest accuracy so far.
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
“Some groups prefer to incorporate a transistor in series to each MIM cell to obtain a better control over the currents through the device (i.e., improve conductance controllability and minimize sneak path currents)53–55,60,61,102,113,167,194,218–222,).”
From Hardware implementation of memristor-based artificial neural networks (2024) · cites this paper as [218]
In the citing paper
“Then, analogue VMM has been demonstrated both for binary inputs and weights218–220, as well as for binary inputs and analogue/multilevel weights60,85,105,217.”
From Hardware implementation of memristor-based artificial neural networks (2024) · cites this paper as [218]
In the citing paper
“In off-chip learning, where training was performed using software, pattern recognition with 94% accuracy was achieved by utilizing the binary states achieved from the HfO2 RRAM based synapses, as shown in Fig. 6(b) [19].”
From Linking Conductive Filament Properties and Evolution to Synaptic Behavior of RRAM Devices for Neuromorphic Applications (2017) · cites this paper as [19]
Citations
Cites
LeCun, Y., Bengio, Y., & Hinton, G. (2015) · Nature · doi:10.1038/nature14539 · Cited by 84,126
A million spiking-neuron integrated circuit with a scalable communication network and interface
Merolla, P. A., Arthur, J. V., Alvarez-Icaza, R., Cassidy, A. S., Sawada, J., Akopyan, F., Jackson, B. L., Imam, N., Guo, C., Nakamura, Y., et al. (2014) · Science · doi:10.1126/science.1254642 · Cited by 4,147
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 · cited 2×
“Unfortunately, almost all the reported “analog” synapses [4-11] suffer from this nonlinear weight update.”
BackgroundBinaryConnect: Training Deep Neural Networks with binary weights during propagations
Courbariaux, M., Bengio, Y., & David, J.-P. (2015) · arXiv · doi:10.48550/arxiv.1511.00363 · Cited by 2,180
Suri, M., Bichler, O., Querlioz, D., Cueto, O., Perniola, L., Sousa, V., Vuillaume, D., Gamrat, C., & DeSalvo, B. (2011) · 2011 International Electron Devices Meeting · doi:10.1109/iedm.2011.6131488 · Cited by 314 · cited 5×
“Unfortunately, almost all the reported “analog” synapses [4-11] suffer from this nonlinear weight update.”
BackgroundInfluentialScaling-up resistive synaptic arrays for neuro-inspired architecture: Challenges and prospect
Yu, S., Chen, P.-Y., Cao, Y., Xia, L., Wang, Y., & Wu, H. (2015) · 2015 IEEE International Electron Devices Meeting (IEDM) · doi:10.1109/iedm.2015.7409718 · Cited by 219
Self-citationBurr, G. W., Shelby, R. M., di Nolfo, C., Jang, J. W., Shenoy, R. S., Narayanan, P., Virwani, K., Giacometti, E. U., Kurdi, B., & Hwang, H. (2014) · 2014 IEEE International Electron Devices Meeting · doi:10.1109/iedm.2014.7047135 · Cited by 208
Neuromorphic speech systems using advanced ReRAM-based synapse
Park, S., Sheri, A., Kim, J., Noh, J., Jang, J., Jeon, M., Lee, B., Lee, B. R., Lee, B. H., & Hwang, H. (2013) · 2013 IEEE International Electron Devices Meeting · doi:10.1109/iedm.2013.6724692 · Cited by 201
Kim, S., Ishii, M., Lewis, S., Perri, T., BrightSky, M., Kim, W., Jordan, R., Burr, G. W., Sosa, N., Ray, A., et al. (2015) · 2015 IEEE International Electron Devices Meeting (IEDM) · doi:10.1109/iedm.2015.7409716 · Cited by 194
Eryilmaz, S. B., Kuzum, D., Yu, S., & Wong, H. ‐. P. (2015) · Technical digest - International Electron Devices Meeting/Technical digest · doi:10.1109/iedm.2015.7409622 · Cited by 102
Self-citation
Cited by
Items 201–246 of 246
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
MVSTT: A Multi-Value Computation-in-Memory based on Spin-Transfer Torque Memories
Jafari, A., Mayahinia, M., Ahmed, S. T., Münch, C., & Tahoori, M. B. (2022) · Euromicro Conference on Digital System Design (DSD) · doi:10.1109/dsd57027.2022.00052 · Cited by 2
RRAM fabric for neuromorphic and reconfigurable compute-in-memory systems
Zidan, M. A., & Lu, W. D. (2019) · Custom Integrated Circuits Conference · doi:10.1109/cicc.2019.8780185 · Cited by 2
Graphene‐Based Synaptic Devices for Neuromorphic Applications
Tian, H., Wu, F., & Ren, T. (2019) · Wiley eBooks · doi:10.1002/9781119468455.ch116 · Cited by 2
eNVM based In-memory Computing for Intelligent and Secure Computing Systems
Huang, K., & Qin, C. (2019) · IEEE International System-on-Chip Conference (SOCC) · doi:10.1109/socc46988.2019.1570557582 · Cited by 2
Synaptic realizations based on memristive devices
Milo, V., Dalgaty, T., Ielmini, D., & Vianello, E. (2020) · Elsevier eBooks · doi:10.1016/b978-0-08-102782-0.00017-4 · Cited by 2
A Machine Learning Accelerator In-Memory for Energy HarvestingPreprint
Resch, S., Khatamifard, S. K., Chowdhury, Z. I., Zabihi, M., Zhao, Z., Wang, J., Sapatnekar, S. S., & Karpuzcu, U. R. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1908.11373 · Cited by 2
Le, H., Baig, M. A., Hong, W.-C., Tsai, C.-H., Yeh, C.-J., Liang, F.-X., Huang, I.-T., Tsai, W.-T., Cheng, T.-Y., De, S., et al. (2023) · arXiv (Cornell University) · doi:10.48550/arxiv.2306.14649 · Cited by 2
The Back-End Selector : From material development to device performances
Laguna, C. (2022) · theses.fr (ABES) · doi:10.70675/fa704edbzf63az4f5az99dfz598711465508 · Cited by 2
Bridging Synapses: A Comparative Review of Machine Learning Algorithms in Memristor Technology
Dhakal, P., Wu, X., Kim, J. G., Hou, A., & Wang, S. (2024) · Journal of Neuromorphic Intelligence · doi:10.63382/jni.v1i1.7 · Cited by 1
Improving the analog switching behavior in HfO2-based RRAM with simple 1T1R structure configuration
Xia, J. G., He, H., Shen, D., Jiang, X., & Yang, J. (2025) · Solid-State Electronics · doi:10.1016/j.sse.2025.109314 · Cited by 1
Emerging Technologies for Memory-Centric Computing
Matrangolo, P.-A., Marchand, C., Navarro, D., O’Connor, I., & Bosio, A. (2024) · Springer eBooks · doi:10.1007/978-3-031-42478-6_1 · Cited by 1
In-memory computing by RRAM for machine learning
Ni, L. (2018) · DR-NTU (Nanyang Technological University) · doi:10.32657/10356/73177 · Cited by 1
Bridging the Band Gap: What Device Physicists Need to Know About Machine LearningPreprint
Tye, N., Hofmann, S., & Stanley‐Marbell, P. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2110.05910 · Cited by 1
Neuro-inspired Computing Using Emerging Non-Volatile Memories
Shi, Y. (2023) · eScholarship (California Digital Library) · Cited by 1
Analysis of the Resistive Switching phenomenon in MOS devices for memory and logic applications
Maestro-Izquierdo, M., & Electrònica, U. A. D. B. D. D. (2017) · LA Referencia (Red Federada de Repositorios Institucionales de Publicaciones Científicas) · Cited by 1
Lateral Migration-based TFT-type Flash Memory for Hardware-based Neural Networks
Park, M. (2024) · Seoul National University Open Repository (Seoul National University) · Cited by 1
Pedro, M., & Electrònica, U. A. D. B. D. D. (2019) · LA Referencia (Red Federada de Repositorios Institucionales de Publicaciones Científicas) · Cited by 1
Bio-inspired continual learning and credit assignment for neuromorphic computing
Laborieux, A. (2021) · theses.fr (ABES) · doi:10.70675/800314bdz09a6z46fdz87f5z3a5795d98157 · Cited by 1
In-memory computing based on CMOS-RRAM hybrid architectures
Esmanhotto, E. (2022) · theses.fr (ABES) · doi:10.70675/1cf79608z3789z4025z8efcz817e8621bdd9 · Cited by 1
Reganaz, L. (2024) · theses.fr (ABES) · doi:10.70675/8a8c196ez95d7z468czabf2z768bdddceef5 · Cited by 1
Processeur sécurisé et reconfigurable incluant des technologies émergentes
Matrangolo, P.-A. (2025) · theses.fr (ABES) · doi:10.70675/3a7dcefbzeebfz43a8z8218z1fa2976d7dd8 · Cited by 1
Exploiting Processing in Non-Volatile Memory for Binary Neural Network Accelerators.Preprint
Resch, S., Khatamifard, S. K., Chowdhury, Z. I., Zabihi, M., Zhao, Z., Wang, J., Sapatnekar, S. S., & Karpuzcu, U. R. (2018) · arXiv (Cornell University)
Memory-Centric Neuromorphic Computing With Nanodevices
Querlioz, D., Grollier, J., Hirtzlin, T., Klein, J., Nowak, E., Vianello, E., Bocquet, M., Portal, J., Romera, M., & Talatchian, P. (2019) · IEEE Biomedical Circuits and Systems Conference (BioCAS) · doi:10.1109/biocas.2019.8919010
Non-filamentary non-volatile memory elements as synapses in neuromorphic systems
Fumarola, A., Narayanan, P., Shelby, R. M., Sanchez, L. L., Burr, G. W., Moon, K., Jang, J., Hwang, H., Sidler, S., & Leblebici, Y. (2019) · Non-Volatile Memory Technology Symposium · doi:10.1109/nvmts47818.2019.8986194
Embracing the Unreliability of Memory Devices for Neuromorphic ComputingPreprint
Bocquet, M., Hirtzlin, T., Klein, J., Nowak, E., Vianello, E., Portal, J., & Querlioz, D. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2007.06238
Bio-inspired learning and hardware acceleration with emerging memories
Kulkarni, S. (2019)
Resistive Switching Devices and Their Applications for Computing Beyond von Neumann Architecture
Shin, J. H. (2019) · Deep Blue (University of Michigan)
Binary Neural Networks in Spintronic Memory
Resch, S. (2021) · University of Minnesota Digital Conservancy (University of Minnesota)
MLUTNet: A Neural Network for Memory Based Reconfigurable Logic Device Architecture
Zang, X., & Nakatake, S. (2021) · Applied Sciences · doi:10.3390/app11136213
Neuromorphic Computing Using Emerging NV Memory Devices
Prince, B., & Prince, D. (2018) · Wiley eBooks · doi:10.1002/9781119298922.ch5
Zhang, D., Kang, Y., Liu, G., Zhou, Z., Han, K., Sun, C., Jiao, L., Wang, X., Chen, Y., Kong, Q., et al. (2022) · arXiv (Cornell University) · doi:10.48550/arxiv.2209.09083
(2022) · De Gruyter eBooks · doi:10.1515/9783110785944-010
A low power time-domain computing-in-memory micro for binary neural networks
He, Y. (2023) · Digital Repository Service (Northeastern University) · doi:10.17760/d20487159
Proposal and evaluation of recurrent neural network training by multi-phase quantization optimizer
Yamazaki, H., Akeno, I., Nobori, K., Asai, T., & Ando, K. (2024) · Nonlinear Theory and Its Applications IEICE · doi:10.1587/nolta.16.30
Nonvolatile Resistive Memory Technology for Deep Neural Network Hardware Applications
Choi, W., Ram, M. S., Falcone, D. F., Stecconi, T., Lombardo, D., Porta, A. L., Horst, F., Jubin, D., Bragaglia, V., & Offrein, B. J. (2026) · Wiley eBooks · doi:10.1002/9783527847419.ch22
Yayla, M. (2024) · Technische Universität Dortmund Eldorado (Technische Universität Dortmund) · doi:10.17877/de290r-24267
Architecture Supports and Optimizations for Memory-Centric Processing System
Gu, P. (2021) · eScholarship (California Digital Library)
High-Speed Image Classification for Resource-Limited Systems Using Binary Values
Simons, T. (2021) · ScholarsArchive (Brigham Young University)
Soltani Zarrin, P. (2021) · Digital Repository of the BTU Cottbus – Senftenberg (Brandenburg University of Technology)
Yang, Z., Yang, Y., Wang, B., Tao, Y., Zelun, P., Cai, L., Zhang, T., Yan, L., Li, X., & Yang, Y. (2026) · Advanced Science · doi:10.1002/advs.202521815
New analogue-type resistive switching memristive devices for artificial synapse applications
Khuu, T. (2023) · theses.fr (ABES) · doi:10.70675/b9c1ba1fzfe60z4cc2z9366z33f2c50b5a64
Kusunose, R., Schmid, A., Asai, T., Uemura, T., & Marukame, T. (2026) · Engineering Research Express · doi:10.1088/2631-8695/ae5d86
Design of mixed system (RRAM memory & digital) targeting binary neural network hardware accelerator
Jebali, F. (2023) · theses.fr (ABES) · doi:10.70675/b7632edfz3807z4b8fzb462z31a6dcf54161
VLSI Design for Artificial Intelligence and Machine Learning Applications
Das, D. (2026) · Wiley eBooks · doi:10.1002/9781394390274
Non‐Volatile Memory Devices for Neuromorphic Computing
Das, D. (2026) · Wiley eBooks · doi:10.1002/9781394390274.ch22
Metadata
- Authors
- Yu, S., Li, Z., Chen, P.-Y., Wu, H., Gao, B., Wang, D., Wu, W., & Qian, H.
- Affiliations
- Arizona State University (US)
- Tsinghua University (CN)
- Venue
- 2016 IEEE International Electron Devices Meeting (IEDM)
- Publisher
- IEEE
- Published
- 2016-12
- Pages
- 16.2.1-16.2.4
- ISSN
- 0163-1918 (ISSN-L)
- OpenAlex
- W2585407525
- Cited by
- 219
- References
- 15
- Citations by year
- 2026: 2 · 2025: 5 · 2024: 17 · 2023: 17 · 2022: 21 · 2021: 33 · 2020: 40 · 2019: 38 · 2018: 33 · 2017: 10
- FWCI
- 37.99
- Type
- conference paper
- Language
- en
- Open access
- closed
- Locations
- Technical digest - International Electron Devices Meeting/Technical digest (publishedVersion)
- Topics
- Physical Sciences › Engineering › Electrical and Electronic Engineering › Advanced Memory and Neural Computing
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
- Physical Sciences › Computer Science › Artificial Intelligence › Neural Networks and Applications
- Keywords
- binary neural networks, resistive random access memory, synaptic arrays, weight binarization, online training, image classification, MNIST handwritten digits, 130 nm CMOS
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.