A Unified Physics-Aware Quantum Machine Learning Framework across Power GaN HEMTs and Logic Nanowire FETs: Predicting Unseen Process Splits and Held-Out Geometry Combinations with Lower Error and Tighter Split-to-Split Variability

The researchers proposed a unified physical-sensing quantum machine learning framework aimed at handling both power gallium nitride high electron mobility transistors (GaN HEMT) and logic nanowire field-effect transistors (FET). This framework achieves lower prediction errors and tighter inter-split variations compared to existing methods by predicting unknown process split combinations and retaining geometric shape combinations.