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 potential of RL-selected, classically simulated PQCs as compact surrogates with low OOD error and improved physical consistency are demonstrated, despite imposing no explicit physical constraints, penalty terms, or device-specific equations, on the two evaluated device datasets.
Rushat Rai, Yun-Yuan Wang, Autsada Kakaen et al.
· 0 citations