PRIME: Physics-Related Intelligent Mixture of Experts for Transistor Characteristics Prediction

TL;DR

PRIME is a novel machine learning framework that combines physics-based knowledge with data-driven models to accurately predict transistor characteristics across multiple operating regions, significantly outperforming existing models.

Contribution

It introduces a dynamic mixture of experts model with physics integration and adaptive gating for improved transistor characteristic prediction.

Findings

Achieves 60-84% improvement in prediction accuracy.

Effectively captures nonlinear current responses across regions.

Demonstrates robustness on GAA transistor structures.

Abstract

In recent years, machine learning has been extensively applied to data prediction during process ramp-up, with a particular focus on transistor characteristics for circuit design and manufacture. However, capturing the nonlinear current response across multiple operating regions remains a challenge for neural networks. To address such challenge, a novel machine learning framework, PRIME (Physics-Related Intelligent Mixture of Experts), is proposed to capture and integrate complex regional characteristics. In essence, our framework incorporates physics-based knowledge with data-driven intelligence. By leveraging a dynamic weighting mechanism in its gating network, PRIME adaptively activates the suitable expert model based on distinct input data features. Extensive evaluations are conducted on various gate-all-around (GAA) structures to examine the effectiveness of PRIME and considerable improvements (60\%-84\%) in prediction accuracy are shown over state-of-the-art models.