Neural Network-Based I-V and C-V Modeling With High Accuracy and Potential Model Speed

In this brief, we demonstrate a neural network (NN)-based device modeling framework. This NN model is built to model advanced field-effect transistors (FETs). Specific transfer functions and loss functions are chosen to achieve high accuracy and smoothness in the output of this NN model. Both I-V (current-voltage) and C-V (capacitance-voltage) characteristics are studied in this work. Speed comparison between the NN-based model and Berkeley short-channel IGFET model (BSIM) has been done to show that NN has a great potential to accelerate circuit simulation speed. We also present that this NN modeling framework is not only useful for more Moore technologies e.g., gate-all-around FET (GAAFET) but also beyond Moore transistors e.g., negative capacitance FET (NCFET).

Automated summary

This paper presents a neural network-based device modeling framework that accurately models advanced FETs. Both I-V and C-V characteristics are studied, and a speed comparison with traditional models shows the potential of neural networks in accelerating circuit simulation.