Deep learning approach to estimating work function fluctuation of gate-all-around silicon nanosheet MOSFETs with a ferroelectric HZO layer
2022 6th IEEE Electron Devices Technology & Manufacturing …, 2022•ieeexplore.ieee.org
Highly scaled MOSFETs are suffering from various fluctuations. In this paper, an artificial
neural network (ANN) device modeling technique is reported for gate-all-around silicon
nanosheet MOSFETs (GAA Si NS MOSFETs). The well-trained ANN model can rapidly and
accurately estimate the effect of work function fluctuation (WKF) on device characteristic. Our
model is generic because it can be successfully evaluated on the device with a ferroelectric
HZO layer which have material and structural dissimilarity with the GAA NS device.
neural network (ANN) device modeling technique is reported for gate-all-around silicon
nanosheet MOSFETs (GAA Si NS MOSFETs). The well-trained ANN model can rapidly and
accurately estimate the effect of work function fluctuation (WKF) on device characteristic. Our
model is generic because it can be successfully evaluated on the device with a ferroelectric
HZO layer which have material and structural dissimilarity with the GAA NS device.
Highly scaled MOSFETs are suffering from various fluctuations. In this paper, an artificial neural network (ANN) device modeling technique is reported for gate-all-around silicon nanosheet MOSFETs (GAA Si NS MOSFETs). The well-trained ANN model can rapidly and accurately estimate the effect of work function fluctuation (WKF) on device characteristic. Our model is generic because it can be successfully evaluated on the device with a ferroelectric HZO layer which have material and structural dissimilarity with the GAA NS device.
ieeexplore.ieee.org
以上显示的是最相近的搜索结果。 查看全部搜索结果