The primary objective of this study is to investigate the potential of artificial neural network (ANN) for predicting the short-channel effect parameters and current-voltage curve in gate-all-around junctionless nanowire FET (GAA-JL-NWFET). The evaluation of the effectiveness of an ANN is typically done by analyzing metrics like root mean square error (RMSE) and coefficient of determination (R-score). This study comprises various visualizations such as plots depicting the training loss per epoch against the epoch, scatter plots that compare actual values with predicted values and density plots illustrating the relationship between the density of data points and errors. The ability of the ANN model to accurately predict the important device parameters indicates its effectiveness. The parameters include drain current (I), drain induced barrier lowering (DIBL), threshold voltage (V), subthreshold swing (SS), on-current (I) and off-current (I). The root mean square error (RMSE) values corresponding to I, DIBL, V, SS, I and I were found to be 5.92 %, 0.79 %, 1.50 %, 1.31 %, 4.35 % and 9.81 % respectively. Furthermore, it is worth to mention that the R-scores associated with these characteristics exhibit a very high level of accuracy as can be seen by the values of 0.9835, 0.9156, 0.9919, 0.9644, 0.9833 and 0.9097 for I, DIBL, V, SS, I and I respectively. The approach of using ANN model matches the accuracy of physics-based technology computer aided design (TCAD) solvers and its precision makes it an excellent alternative. In summary, this work demonstrates the potential of ANN as a robust tool for accurate prediction of device performance specifically in the field of semiconductor devices.

中文翻译：

---

使用 ANN 方法预测 GAA 无结纳米线 FET 的器件参数

本研究的主要目的是研究人工神经网络 (ANN) 在预测环栅无结纳米线 FET (GAA-JL-NWFET) 的短沟道效应参数和电流-电压曲线方面的潜力。人工神经网络有效性的评估通常通过分析均方根误差 (RMSE) 和决定系数 (R 分数) 等指标来完成。这项研究包括各种可视化，例如描述每个时期相对于时期的训练损失的图、将实际值与预测值进行比较的散点图以及说明数据点密度和误差之间关系的密度图。 ANN模型准确预测重要器件参数的能力表明了其有效性。参数包括漏极电流 (I)、漏极感应势垒降低 (DIBL)、阈值电压 (V)、亚阈值摆幅 (SS)、导通电流 (I) 和关断电流 (I)。与 I、DIBL、V、SS、I 和 I 对应的均方根误差 (RMSE) 值分别为 5.92 %、0.79 %、1.50 %、1.31 %、4.35 % 和 9.81 %。此外，值得一提的是，与这些特征相关的 R 分数表现出非常高的准确度，从 I、DIBL、V、SS 的 0.9835、0.9156、0.9919、0.9644、0.9833 和 0.9097 的值可以看出，分别为 I 和 I 。使用 ANN 模型的方法与基于物理技术的计算机辅助设计 (TCAD) 求解器的精度相匹配，其精度使其成为绝佳的替代方案。总之，这项工作展示了 ANN 作为准确预测器件性能（特别是在半导体器件领域）的强大工具的潜力。