The DOI matches its Crossref record; 1 of the 1 references it cites were found in a registry or an index.
Design Considerations for Efficient Deep Neural Networks on Processing-in-Memory Accelerators
Open accessAbstract
This paper describes various design considerations for deep neural networks that enable them to operate efficiently and accurately on processing-in-memory accelerators. We highlight important properties of these accelerators and the resulting design considerations using experiments conducted on various state-of-the- art deep neural networks with the large-scale ImageNet dataset.
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?
Little or no loss in accuracy can be achieved when using binary weights for some earlier deep convolutional networks, such as AlexNet or VGG.
“though little or no loss in accuracy can be achieved when using binary weights for some of the earlier (very redundant) deep convolutional networks, such as AlexNet or VGG”
From 4K-memristor analog-grade passive crossbar circuit (2021) · cites this paper as [49]
4 to 8 bits of precision for both weights and activations might be necessary for the most advanced image classifiers.
“4 to 8 bits of precision for both weights and activations might be necessary for the most advanced image classifiers49”
From 4K-memristor analog-grade passive crossbar circuit (2021) · cites this paper as [49]
Citations
Cites
Efficient Processing of Deep Neural Networks: A Tutorial and Survey
Sze, V., Chen, Y.-H., Yang, T.-J., & Emer, J. S. (2017) · Proceedings of the IEEE · doi:10.1109/jproc.2017.2761740 · Cited by 4,215 · cited 1×
“peripheral circuits are much larger than the memory array; the array size of digital accelerators typically range from 16× 16 to 128 × 128 [6] compared with 128 × 128 to 4096 × 4096 for PIM accelerators [2, 4].”
BackgroundSelf-citation
Flagged first, then by citations
Research works printed but not linked: 6
- 10.3389/fnins.2016.00333 · DOI · Paper page
- 10.1109/DAC.2018.8465834 · DOI · Paper page
- 10.1145/3007787.3001177 · DOI · Paper page
- zagoruyko, 2017, Wide Residual Networks, British Machine Vision Conference
- 10.1109/JPROC.2018.2790840 · DOI · Paper page
- yang, 2018, Understanding the Limitations of Existing Energy-Efficient Design Approaches for Deep Neural Networks, SysML Conference
Cited by
Sorted by citations
A compute-in-memory chip based on resistive random-access memory
Wan, W., Kubendran, R., Schaefer, C., Eryilmaz, S. B., Zhang, W., Wu, D., Deiss, S., Raina, P., Qian, H., Gao, B., et al. (2022) · Nature · doi:10.1038/s41586-022-04992-8 · Cited by 943
4K-memristor analog-grade passive crossbar circuit
Kim, H., Mahmoodi, M. R., Nili, H., & Strukov, D. B. (2021) · Nature Communications · doi:10.1038/s41467-021-25455-0 · Cited by 265
On the Accuracy of Analog Neural Network Inference Accelerators
Xiao, T. P., Feinberg, B., Bennett, C. H., Prabhakar, V., Saxena, P., Agrawal, V., Agarwal, S., & Marinella, M. J. (2022) · IEEE Circuits and Systems Magazine · doi:10.1109/mcas.2022.3214409 · Cited by 76
Metadata
- Authors
- Yang, T.-J., & Sze, V.
- Affiliations
- Massachusetts Institute of Technology (US)
- Venue
- 2019 IEEE International Electron Devices Meeting (IEDM)
- Publisher
- IEEE
- Published
- 2019-12
- Pages
- 22.1.1-22.1.4
- ISSN
- 0163-1918 (ISSN-L)
- OpenAlex
- W3006248624
- Cited by
- 55
- References
- 1
- Citations by year
- 2026: 2 · 2025: 2 · 2024: 8 · 2023: 8 · 2022: 14 · 2021: 13 · 2020: 8
- FWCI
- 6.75
- Type
- conference paper
- Language
- en
- Open access
- green
- arxiv.org
- Licence
- Locations
- Technical digest - International Electron Devices Meeting/Technical digest (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- DSpace@MIT (Massachusetts Institute of Technology) (submittedVersion, cc-by-nc-sa)
- arXiv (Cornell University)
- Funders
- National Science Foundation (1639921, E2CDA)
- Quest for Intelligence, Massachusetts Institute of Technology
- Topics
- Physical Sciences › Computer Science › Hardware and Architecture › Parallel Computing and Optimization Techniques
- 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
- Keywords
- in-memory computing, neural network accelerators, deep neural network design, energy efficiency, ImageNet, accelerator architecture
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
