A tandem neural network with surrogate-generated pretraining extracts eight TCAD parameters from I-V curves using ~500 physics simulations, achieving median R2 = 0.99 on experimental WS2 transistors and scaling to 35-parameter HEMT fits.
curse of dimensionality,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Deep Learning to Automate Parameter Extraction and Model Fitting of Two-Dimensional Transistors
A tandem neural network with surrogate-generated pretraining extracts eight TCAD parameters from I-V curves using ~500 physics simulations, achieving median R2 = 0.99 on experimental WS2 transistors and scaling to 35-parameter HEMT fits.