Improving Semiconductor Device Modeling for Electronic Design Automation by Machine Learning Techniques

TL;DR

This paper introduces a self-augmentation method using variational autoencoders to enhance ML-based semiconductor device modeling, reducing data requirements and improving prediction accuracy in device parameter estimation.

Contribution

The paper presents a novel self-augmentation strategy with variational autoencoders that improves ML model performance using limited experimental data in semiconductor device modeling.

Findings

Achieved 70% reduction in mean absolute error for resistance prediction.

Method requires fewer experimental data points, reducing reliance on costly TCAD simulations.

Flexible approach adaptable to various semiconductor modeling tasks.

Abstract

The semiconductors industry benefits greatly from the integration of Machine Learning (ML)-based techniques in Technology Computer-Aided Design (TCAD) methods. The performance of ML models however relies heavily on the quality and quantity of training datasets. They can be particularly difficult to obtain in the semiconductor industry due to the complexity and expense of the device fabrication. In this paper, we propose a self-augmentation strategy for improving ML-based device modeling using variational autoencoder-based techniques. These techniques require a small number of experimental data points and does not rely on TCAD tools. To demonstrate the effectiveness of our approach, we apply it to a deep neural network-based prediction task for the Ohmic resistance value in Gallium Nitride devices. A 70% reduction in mean absolute error when predicting experimental results is achieved. The inherent flexibility of our approach allows easy adaptation to various tasks, thus making it highly relevant to many applications of the semiconductor industry.