CoChat
Sign Up
Cited by 22Advanced Memory and Neural ComputingParallel Computing and Optimization TechniquesNeural Networks and Applications

The DOI matches its Crossref record; 3 of the 3 references it cites were found in a registry or an index.

Tolerating Noise Effects in Processing‐in‐Memory Systems for Neural Networks: A Hardware–Software Codesign Perspective

Open access
Yang, Xiaoxuan, Wu, Changming, Li, Mo, Chen, Yiran·2022·Advanced Intelligent Systems
DOI 10.1002/aisy.202200029
Open this paper in CoChat — free accountOpen PDF

Abstract

Neural networks have been widely used for advanced tasks from image recognition to natural language processing. Many recent works focus on improving the efficiency of executing neural networks in diverse applications. Researchers have advocated processing‐in‐memory (PIM) architecture as a promising candidate for training and testing neural networks because PIM design can reduce the communication cost between storage and computing units. However, there exist noises in the PIM system generated from the intrinsic physical properties of both memory devices and the peripheral circuits. The noises introduce challenges in stably training the systems and achieving high test performance, e.g., accuracy in classification tasks. This review discusses the current approaches to tolerating noise effects for both training and inference in PIM systems and provides an analysis from a hardware–software codesign perspective. Noise‐tolerant strategies for PIM systems based on resistive random‐access memory (ReRAM), including circuit‐level, algorithm‐level, and system‐level solutions are explained. In addition, we also present some selected noise‐tolerate cases in PIM systems for generative adversarial networks and physical neural networks.

Overview

Integrity signals

Registry

Crossref · 10.1002/aisy.202200029

Cites

3 of 3 references verified0 citation errors · 0 not checkable

Statistics

Recomputing p-values needs the paper’s full text.

Verification

Claims the paper makes

We couldn’t retrieve this paper’s full text, so its claims and self-check weren’t run. The registry and citation checks still apply.

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?

Citations

Cites

Flagged first, then by citations

Research works printed but not linked: 54

  1. J.Gómez-Luna I. E.Hajj I.Fernandez C.Giannoula G. F.Oliveira O.Mutlu in12th Int. Green and Sustain. Computing Conf. IEEE Piscataway NJ2021pp.1–7.
  2. 10.1002/aisy.201900068 · DOI
  3. 10.1109/JSSC.2016.2642198 · DOI
  4. 10.1109/JXCDC.2019.2925061 · DOI
  5. L.Song X.Qian H.Li Y.Chen in2017 IEEE Int. Symp. on High Performance Computer Architecture IEEE Computer Society Piscataway NJ2017pp.541–552. · DOI
  6. Hsu C.-W., 2013 Symposium On VLSI Technology, T166
  7. F.Chen L.Song Y.Chen in23rd Asia and South Pacific Design Automation Conf. IEEE Piscataway NJ2018 pp.178–183.
  8. X.Yang B.Yan H.Li Y.Chen inIEEE/ACM Int. Conf. On Computer Aided Design IEEE Piscataway NJ2020pp.92:1–92:9.
  9. 10.3389/fnins.2020.00423 · DOI
  10. 10.1109/TCSI.2018.2866510 · DOI
  11. 10.1038/s41467-017-02088-w · DOI · Paper page
  12. P.Chi S.Li C.Xu T.Zhang J.Zhao Y.Liu Y.Wang Y.Xie in43rd ACM/IEEE Annual Int. Symp. on Computer Architecture IEEE Computer Society Piscataway NJ2016pp.27–39. · DOI
  13. A.Shafiee A.Nag N.Muralimanohar R.Balasubramonian J. P.Strachan M.Hu R. S.Williams V.Srikumar in43rd ACM/IEEE Annual Int. Symp. on Computer Architecture IEEE Computer Society Piscataway NJ2016 pp.14–26. · DOI
  14. F.Chen L.Song H. H.Li Y.Chen inProc. of the 56th Annual Design Automation Conf.ACM New York NY2019 p.133.
  15. M.Lin H.Cheng W.Lin T.Yang I.Tseng C.Yang H.Hu H.Chang H.Li M.Chang inProc. of the Int. Conf. on Computer-Aided Design ACM New York NY2018 p.31.
  16. K.Hsu F.-M.Lee Y.Lin E.Lai J.Wu D.Lee M.-H.Lee H.Lung K.Hsieh C.Lu inSSDM Japan2015 pp.1168–1169.
  17. B.Feinberg S.Wang E.Ipek inIEEE Int. Symp. on High Performance Computer Architecture IEEE Computer Society Piscataway NJ2018pp.52–65. · DOI
  18. 10.3389/fnins.2016.00333 · DOI · Paper page
  19. Z.He J.Lin R.Ewetz J.Yuan D.Fan inProc. of the 56th Annual Design Automation Conf. ACM New York NY2019 p.57.
  20. S.Han H.Mao W. J.Dally in4th Int. Conf. on Learning Representations San Juan Puerto Rico2016.
  21. S.Migacz inGPU Technology Conf. Vol.2 San Jose CA2017 p.5.
  22. Goncharenko A., 2019, Int. J. Comput. Inform. Eng., 13, 495
  23. R.Zhao Y.Hu J.Dotzel C. D.Sa Z.Zhang inProc. of the 36th Int. Conf. on Machine Learning Vol.97 PMLR Long Beach CA2019pp.7543–7552.
  24. R.Banner Y.Nahshan D.Soudry inAdvances in Neural Information Processing Systems 32: Annual Conf. on Neural Information Processing Systems 2019 Vancouver BC Canada2019 pp.7948–7956.
  25. Y.Chen T.Luo S.Liu S.Zhang L.He J.Wang L.Li T.Chen Z.Xu N.Sun et al. in2014 47th Annual IEEE/ACM Int. Symp. on Microarchitecture IEEE Piscataway NJ2014 pp.609–622. · DOI
  26. S.Gupta A.Agrawal K.Gopalakrishnan P.Narayanan inProc. of the 32nd Int. Conf. on Machine Learning Vol.37 JMLR.org Lille France2015 pp.1737–1746.
  27. Bengio Y., 2013, CoRR
  28. Zhou S., 2016, CoRR
  29. Hubara I., 2017, J. Mach. Learn. Res., 18, 1
  30. H.Yang L.Duan Y.Chen H.Li in9th Int. Conf. on Learning Representations OpenReview.net Austria2021.
  31. M.Alizadeh A.Behboodi M.van Baalen C.Louizos T.Blankevoort M.Welling arXiv preprint arXiv:2002.075202020.
  32. H.Yang X.Yang N. Z.Gong Y.Chen arXiv preprint arXiv:2111.119862021.
  33. 10.1063/1.2810360 · DOI · Paper page
  34. I.Kataeva F.Merrikh-Bayat E.Zamanidoost D. B.Strukov In2015 Int. Joint Conf. on Neural Networks.IEEE Piscataway NJ2015pp.1–8. · DOI
  35. B.Yan J. J.Yang Q.Wu Y.Chen H.Li inIEEE/ACM Int. Conf. on Computer-Aided Design IEEE Piscataway NJ2017 pp.541–548. · DOI
  36. 10.1109/TNNLS.2013.2296777 · DOI
  37. X.Yang S.Belakaria B. K.Joardar H.Yang J. R.Doppa P. P.Pande K.Chakrabarty H. H.Li inIEEE/ACM Int. Conf. on Computer Aided Design IEEE Piscataway NJ2021pp.1–9. · DOI
  38. Y.Long X.She S.Mukhopadhyay inDesign Automation & Test in Europe Conf. & Exhibition IEEE Piscataway NJ2019 pp.1769–1774. · DOI
  39. M. V.Beigi G.Memik inProc. of the 55th Annual Design Automation Conf. ACM New York NY2018 39:1–39:6. · DOI
  40. H.Shin M.Kang L.Kim inIEEE/ACM Int. Conf. on Computer Aided Design IEEE Piscataway NJ2020pp.102:1–102:9. · DOI
  41. 10.1007/s11390-016-1608-8 · DOI
  42. 10.1109/JSSC.2020.2992886 · DOI
  43. 10.1109/JXCDC.2019.2923745 · DOI
  44. 10.1126/sciadv.abm2956 · DOI
  45. 10.1515/nanoph-2020-0291 · DOI
  46. 10.1038/s41586-018-0028-z · DOI
  47. 10.1038/ncomms13878 · DOI
  48. 10.1038/s41467-020-20314-w · DOI · Paper page
  49. 10.1088/1468-6996/15/1/014602 · DOI
  50. 10.1364/OE.23.025118 · DOI
  51. 10.3389/fnins.2020.00103 · DOI
  52. 10.1038/s41586-021-04223-6 · DOI
  53. T.-W.Weng P.Zhao S.Liu P.-Y.Chen X.Lin L.Daniel inProc. of the AAAI Conf. on Artificial Intelligence Vol.34 AAAI Press Palo Alto CA2020pp.6356–6363. · DOI
  54. B.Wu D.Feng W.Tong J.Liu C.Wang W.Zhao M.Peng in37th Int. Conf. on Computer Design IEEE Piscataway NJ2019 pp.147–155. · DOI

Cited by

Sorted by citations

Metadata

Authors
Yang, X., Wu, C., Li, M., & Chen, Y.
Affiliations
  • Duke University (US)
  • University of Washington (US)
Corresponding author
  • Yang, Xiaoxuan
  • Chen, Yiran
ORCID
Venue
Advanced Intelligent Systems
Publisher
Wiley
Published
2022-05-22
Volume
4
Issue
8
ISSN
2640-4567 (ISSN-L)
DOI
10.1002/aisy.202200029
OpenAlex
W4281289797
Cited by
22
References
3
Citations by year
2026: 4 · 2025: 5 · 2024: 3 · 2023: 8 · 2022: 2
FWCI
1.23
Type
journal article
Language
en
Open access
Licence
Locations
  • Advanced Intelligent Systems (publishedVersion, cc-by)
  • DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion)
Funders
  • National Science Foundation (1955196)
  • Army Research Office (W911NF-19-2-0107)
  • Office of Naval Research (N00014-17-1-2661)
Topics
  • Physical Sciences › Engineering › Electrical and Electronic Engineering › Advanced Memory and Neural Computing
  • Physical Sciences › Computer Science › Hardware and Architecture › Parallel Computing and Optimization Techniques
  • Physical Sciences › Computer Science › Artificial Intelligence › Neural Networks and Applications
Keywords
in-memory computing, noise immunity, neural network training, neural network inference, hardware-software co-design, resistive random access memory, generative adversarial networks, physical neural networks, classification accuracy

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