EUVIMEDEUVIMED entdecken
Crossref

High-Performance In-Memory Bayesian Inference With Multi-Bit Ferroelectric FET

Chao Li, Xuchu Huang, Zhicheng Xu, Bo Wen, Ruibin Mao, Min Zhou, Thomas Kämpfe, Kai Ni, Can Li, Xunzhao Yin, Cheng Zhuo

IEEE Transactions on Computers · 2025-09 · 74 (9) · 2923-2935

DOI: 10.1109/tc.2025.3576941 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Computers, 2025-09. Verfasst von Chao Li und 10 weiteren Autor:innen. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 45 Literaturangaben.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Conventional neural network-based machine learning algorithms often encounter difficulties in data-limited scenarios or where interpretability is critical. Conversely, Bayesian inference-based models excel with reliable uncertainty estimates and explainable predictions. Recently, many in-memory computing (IMC) architectures achieve exceptional computing capacity and efficiency for neural network tasks leveraging emerging non-volatile memory (NVM) technologies. However, their application in Bayesian inference remains limited because the operations in Bayesian inference differ substantially from those in neural networks. In this article, we introduce a compact in-memory Bayesian inference engine with high efficiency and performance utilizing a multi-bit ferroelectric field-effect transistor (FeFET). This design encodes a Bayesian model within a compact FeFET-based crossbar by mapping quantized probabilities to discrete FeFET states. Consequently, the crossbar’s outputs naturally represent the output posteriors of the Bayesian model. Our design facilitates efficient Bayesian inference, accommodating various input types and probability precisions, without additional calculation circuitry. As the first FeFET-based in-memory Bayesian inference engine, our design demonstrates a notable storage density of 26.32 Mb/mm2 and a computing efficiency of 581.40 TOPS/W in a representative Bayesian classification task, indicating a 10.7×/43.4× compactness/efficiency improvement compared to the state-of-the-art alternative. Utilizing the proposed Bayesian inference engine, we develop a feature selection system that efficiently addresses a representative NP-hard optimization problem, showcasing our design’s capability and potential to enhance various Bayesian inference-based applications. Test results suggest that our design identifies the essential features, enhancing the model’s performance while reducing its complexity, surpassing the latest implementation in operation speed and algorithm efficiency by 2.9×/2.0×, respectively.

Zitieren

APA

Li, C., Huang, X., Xu, Z., Wen, B., Mao, R., Zhou, M., Kämpfe, T., Ni, K., Li, C., Yin, X., & Zhuo, C. (2025). High-Performance In-Memory Bayesian Inference With Multi-Bit Ferroelectric FET. IEEE Transactions on Computers, 74(9), 2923-2935. https://doi.org/10.1109/tc.2025.3576941

Vancouver

Li C, Huang X, Xu Z, Wen B, Mao R, Zhou M, et al. High-Performance In-Memory Bayesian Inference With Multi-Bit Ferroelectric FET. IEEE Transactions on Computers. 2025;74(9):2923-2935. doi:10.1109/tc.2025.3576941

BibTeX
@article{Li2025,
  author = {Li, Chao and Huang, Xuchu and Xu, Zhicheng and Wen, Bo and Mao, Ruibin and Zhou, Min and Kämpfe, Thomas and Ni, Kai and Li, Can and Yin, Xunzhao and Zhuo, Cheng},
  title = {High-Performance In-Memory Bayesian Inference With Multi-Bit Ferroelectric FET},
  journal = {IEEE Transactions on Computers},
  year = {2025},
  volume = {74},
  number = {9},
  pages = {2923--2935},
  doi = {10.1109/tc.2025.3576941}
}
Kostenlos starten →