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
The future of electronics based on memristive systems
Zidan, M. A., Strachan, J. P., & Lu, W. D. (2018) · Nature Electronics · doi:10.1038/s41928-017-0006-8 · Cited by 2,138
Resistive switching materials for information processing
Wang, Z., Wu, H., Burr, G. W., Hwang, C. S., Wang, K. L., Xia, Q., & Yang, J. J. (2020) · Nature Reviews Materials · doi:10.1038/s41578-019-0159-3 · Cited by 1,214
Self-citationNeuro-Inspired Computing With Emerging Nonvolatile Memorys
Yu, S. (2018) · Proceedings of the IEEE · doi:10.1109/jproc.2018.2790840 · Cited by 1,170
“If the multilevel states in the resistive synaptic devices are insufficient to meet the algorithmic precision requirement, there are two alternative solutions: First, multiple devices could be grouped to represent higher precision at the expensive of area and energy [42].”
BackgroundInfluentialSelf-citationEfficient and self-adaptive in-situ learning in multilayer memristor neural networks
Li, C., Belkin, D., Li, Y., Yan, P., Hu, M., Ge, N., Jiang, H., Montgomery, E., Lin, P., Wang, Z., et al. (2018) · Nature Communications · doi:10.1038/s41467-018-04484-2 · Cited by 931
Neuro-inspired computing chips
Zhang, W., Gao, B., Tang, J., Yao, P., Yu, S., Chang, M.-F., Yoo, H.-J., Qian, H., & Wu, H. (2020) · Nature Electronics · doi:10.1038/s41928-020-0435-7 · Cited by 892
Self-citation
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.