Probabilistic Generative Approach for Ambiguity-Aware Parameter Extraction

Artificial neural networks (ANNs) are increasingly used for parameter extraction in semiconductor device modeling. However, in practice, a parameter ambiguity issue arises, where multiple parameter combinations produce identical drain current values (<inline-formula> <tex-math notation=&quo...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:IEEE transactions on electron devices Ročník 72; číslo 10; s. 5544 - 5550
Hlavní autoři: Zeng, Bolun, Tang, Zhenhua, Zhang, Yuanke, Li, Qingsong, Zhou, Changchun, Qiu, Liling, Chen, Yuefeng, Xiang, Zikun, Xu, Jun, Luo, Chao, Guo, Guoping
Médium: Journal Article
Jazyk:angličtina
Vydáno: New York IEEE 01.10.2025
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Témata:
Ambiguity
Artificial neural network (ANN)
Artificial neural networks
conditional variational autoencoder (CVAE)
Decoding
Gaussian distribution
Integrated circuit modeling
Mathematical models
Optimization
parameter ambiguity
Parameter extraction
Parameters
Probabilistic logic
Residual neural networks
Semiconductor device modeling
Semiconductor devices
Threshold voltage
Training
ISSN:0018-9383, 1557-9646
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:Artificial neural networks (ANNs) are increasingly used for parameter extraction in semiconductor device modeling. However, in practice, a parameter ambiguity issue arises, where multiple parameter combinations produce identical drain current values (<inline-formula> <tex-math notation="LaTeX">{I}_{\text {DS}} </tex-math></inline-formula>). To address this challenge, we introduce a novel probabilistic generative framework. Specifically, we utilize a conditional variational autoencoder (CVAE) to learn the latent distribution of ambiguous parameters (e.g., threshold voltage and mobility) and generate diverse possible candidate parameter sets conditioned on <inline-formula> <tex-math notation="LaTeX">{I}_{\text {DS}} </tex-math></inline-formula> characteristics. By validating the <inline-formula> <tex-math notation="LaTeX">{I}_{\text {DS}} </tex-math></inline-formula> characteristics of the candidates, we ultimately select the optimal parameter set. Experiments across different device sizes, process technologies, and operating conditions demonstrate the effectiveness of our model.
Bibliografie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:0018-9383
1557-9646
DOI:10.1109/TED.2025.3594676