用自编码器快速建模鳍式晶体管，仅需少量数据即可高精度还原电流电压特性。
Rapid FinFET Modelling Using an Autoencoder
- 通过自编码器将完整I-V曲线压缩到低维隐空间，保留关键器件物理信息。
- 仅用少量数据训练即能准确重建I-V曲线，并提取阈值电压、亚阈值斜率等关键参数。
- 适合需要快速器件建模与电路仿真场景，尤其适用于参数依赖性强的先进制程。
本文提出一种基于自编码器（AE）的机器学习框架，用于高效建模鳍式晶体管（FinFET）。首先利用BSIM-CMG模型校准生成电流-电压（ID-VG）特性数据集，以此训练自编码器，将完整的I-V曲线压缩至低维隐空间，该空间内嵌了关键器件物理信息。创新之处在于显式引入漏源电压（VDS）作为输入特征，显著提升了模型对偏置依赖变化的捕捉能力。训练后的模型可成功重构完整I-V曲线，并直接提取阈值电压（VTH）、亚阈值斜率（SS）和峰值跨导（gm）等关键器件参数。结果表明，基于实际表征数据构建的数据驱动紧凑模型，在极少训练数据下仍可实现高精度，为快速器件表征、建模与电路级仿真提供了强大工具。
原文摘要 · Abstract (English)
This work presents a machine learning framework that leverages an autoencoder (AE) for the efficient modeling of FinFET. We first calibrated a BSIM-CMG model to generate a dataset of current-voltage (ID-VG) characteristics. This data was used to train an autoencoder that compresses full I-V curves into a low-dimensional latent space, which intrinsically encodes key device physics. A key innovation is the explicit incorporation of parameter such as drain to source voltage (VDS) as an input feature, enhancing the model ability to capture bias dependent variation. The trained model successfully reconstructs full I-V curves and directly extracts critical device metrics including threshold voltage (VTH), subthreshold slope (SS), and peak transconductance (gm). This approach demonstrates that data driven compact models, built from actual characterization data, can achieve high accuracy with minimal training data, providing a powerful tool for rapid device characterization, modelling and circuit level simulation.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。