Researchers from National Yang Ming Chiao Tung University (Taiwan) published a technical paper titled “A Machine Learning Approach to Modeling Intrinsic Parameter Fluctuation of Gate-All-Around Si Nanosheet MOSFETs.”
“This study has comprehensively analyzed the potential of the ANN-based ML strategy in modeling the effect of fluctuation sources on electrical characteristics of GAA Si NS MOSFETs. A total of 4000 fluctuated devices are simulated, with intrinsic parameter fluctuation sources (WKF, RDF, ITF, and their combination), to collect a complete dataset for the training and testing of ANN models. Their independent as well as combined effects have been analyzed successfully by modeling the variations of threshold voltage, on-state current, and off-state current,” according to the paper.
Find the open access technical paper here. Published July 2022.
R. Butola, Y. Li and S. R. Kola, “A Machine Learning Approach to Modeling Intrinsic Parameter Fluctuation of Gate-All-Around Si Nanosheet MOSFETs,” in IEEE Access, vol. 10, pp. 71356-71369, 2022, doi: 10.1109/ACCESS.2022.3188690.
Related Reading
GAA Knowledge Center
Big Changes In Architectures, Transistors, Materials
Who’s doing what in next-gen chips, and when they expect to do it.
Nanosheet FETs Drive Changes In Metrology And Inspection
Detecting defects inside deep or hidden structures requires a multitool approach.
Transistors Reach Tipping Point At 3nm
Nanosheets are likeliest option throughout this decade, with CFETs and other exotic structures possible after that.
Leave a Reply