Stochastic magnetic tunnel junctions can be used to create energy-efficient neural networks with confidence estimations.
References
Wulf, Wm. A. & McKee, S. A. ACM SIGARCH Comput. Architect. News 23, 20–24 (1995).
Grollier, J. et al. Nat. Electron. 3, 360–370 (2020).
Schuman, C. D. et al. Nat. Comput. Sci. 2, 10–19 (2022).
Misra, S. et al. Adv. Mater. 35, 2204569 (2023).
Liu, S. et al. IEEE J. Exploratory Solid State Comput. Dev. Circ. 8, 194–202 (2022).
Singh, N. S. et al. In Proc. 2023 IEEE Int. Electron Devices Meeting (in the press); https://ieee-iedm.org/program
Safranski, C. et al. Nano Lett. 21, 2040–2045 (2021).
Jiang, H., Kim, B., Guan, M. Y. & Gupta, M. In 32nd Conference on Neural Information Processing Systems (ACM, 2018); https://dl.acm.org/doi/10.5555/3327345.3327458
Aadit, N. A. et al. Nat. Electron. 5, 460–468 (2022).
Harabi, K.-E. et al. Nat. Electron. 6, 53–63 (2022).
Sebastian, A. et al. Nat. Commun. 13, 6139 (2022).
Liu, S. et al. Front. Nanotechnol. 4, 1021943 (2022).
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Competing interests
The authors declare no competing interests.
Rights and permissions
About this article
Cite this article
Liu, S., Incorvia, J.A.C. Creating stochastic neural networks with the help of probabilistic bits. Nat Electron 6, 935–936 (2023). https://doi.org/10.1038/s41928-023-01088-7
Published:
Issue Date:
DOI: https://doi.org/10.1038/s41928-023-01088-7
- Springer Nature Limited