Device Modeling Based on Cost-Sensitive Densely Connected Deep Neural Networks
Engineers used TCAD tools for semiconductor devices modeling. However, it is computationally expensive and time-consuming for advanced devices with smaller dimensions. Therefore, this work proposes a machine learning-based device modeling algorithm to capture the complex nonlinear relationship betwe...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2024-01-01
|
| Series: | IEEE Journal of the Electron Devices Society |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10643157/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832583225686360064 |
|---|---|
| author | Xiaoying Tang Zhiqiang Li Lang Zeng Hongwei Zhou Xiaoxu Cheng Zhenjie Yao |
| author_facet | Xiaoying Tang Zhiqiang Li Lang Zeng Hongwei Zhou Xiaoxu Cheng Zhenjie Yao |
| author_sort | Xiaoying Tang |
| collection | DOAJ |
| description | Engineers used TCAD tools for semiconductor devices modeling. However, it is computationally expensive and time-consuming for advanced devices with smaller dimensions. Therefore, this work proposes a machine learning-based device modeling algorithm to capture the complex nonlinear relationship between parameters and electrical characteristics of gate-all-around (GAA) nanowire field-effect transistors (NWFETs) from technology computer-aided design (TCAD) simulation results. This method utilizes a densely connected deep neural networks (DenseDNN), which establishes direct connections between layers in the neural networks, provides stronger feature extraction and information transmission capabilities. By incorporating cost-sensitive learning methods, the proposed model focus more on the critical data that determines device characteristics, leading to accurate prediction of key device characteristics under various parameters. Experimental results on a test dataset of 116 NWFETs demonstrate the effectiveness of this method. The DenseDNN model with cost-sensitive learning exhibits better performance than traditional deep neural networks (DNN) with various widths and depths, with a prediction error below 1.62%. Moreover, compared to TCAD simulation results, the model can speedup <inline-formula> <tex-math notation="LaTeX">$10^{6}\times$ </tex-math></inline-formula>. |
| format | Article |
| id | doaj-art-5a2f7eb3ea094365a5331344dcf613b0 |
| institution | Kabale University |
| issn | 2168-6734 |
| language | English |
| publishDate | 2024-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Journal of the Electron Devices Society |
| spelling | doaj-art-5a2f7eb3ea094365a5331344dcf613b02025-01-29T00:00:18ZengIEEEIEEE Journal of the Electron Devices Society2168-67342024-01-011261962610.1109/JEDS.2024.344703210643157Device Modeling Based on Cost-Sensitive Densely Connected Deep Neural NetworksXiaoying Tang0https://orcid.org/0009-0002-4353-016XZhiqiang Li1https://orcid.org/0009-0003-7463-8576Lang Zeng2https://orcid.org/0000-0003-3157-1087Hongwei Zhou3https://orcid.org/0009-0000-7616-6726Xiaoxu Cheng4Zhenjie Yao5https://orcid.org/0000-0003-1027-637XKey Laboratory of Fabrication Technologies for Integrated Circuits, Chinese Academy of Sciences, Beijing, ChinaKey Laboratory of Fabrication Technologies for Integrated Circuits, Chinese Academy of Sciences, Beijing, ChinaMIIT Key Laboratory of Spintronics, School of Integrated Circuit Science and Engineering, Fert Beijing Institute, Beihang University, Beijing, ChinaMIIT Key Laboratory of Spintronics, School of Integrated Circuit Science and Engineering, Fert Beijing Institute, Beihang University, Beijing, ChinaPrimarius Technologies Company Ltd., Shanghai, ChinaKey Laboratory of Fabrication Technologies for Integrated Circuits, Chinese Academy of Sciences, Beijing, ChinaEngineers used TCAD tools for semiconductor devices modeling. However, it is computationally expensive and time-consuming for advanced devices with smaller dimensions. Therefore, this work proposes a machine learning-based device modeling algorithm to capture the complex nonlinear relationship between parameters and electrical characteristics of gate-all-around (GAA) nanowire field-effect transistors (NWFETs) from technology computer-aided design (TCAD) simulation results. This method utilizes a densely connected deep neural networks (DenseDNN), which establishes direct connections between layers in the neural networks, provides stronger feature extraction and information transmission capabilities. By incorporating cost-sensitive learning methods, the proposed model focus more on the critical data that determines device characteristics, leading to accurate prediction of key device characteristics under various parameters. Experimental results on a test dataset of 116 NWFETs demonstrate the effectiveness of this method. The DenseDNN model with cost-sensitive learning exhibits better performance than traditional deep neural networks (DNN) with various widths and depths, with a prediction error below 1.62%. Moreover, compared to TCAD simulation results, the model can speedup <inline-formula> <tex-math notation="LaTeX">$10^{6}\times$ </tex-math></inline-formula>.https://ieeexplore.ieee.org/document/10643157/Machine learningdevice modelingtechnology computer-aided design (TCAD) simulationcost-sensitive densely connected DNN |
| spellingShingle | Xiaoying Tang Zhiqiang Li Lang Zeng Hongwei Zhou Xiaoxu Cheng Zhenjie Yao Device Modeling Based on Cost-Sensitive Densely Connected Deep Neural Networks IEEE Journal of the Electron Devices Society Machine learning device modeling technology computer-aided design (TCAD) simulation cost-sensitive densely connected DNN |
| title | Device Modeling Based on Cost-Sensitive Densely Connected Deep Neural Networks |
| title_full | Device Modeling Based on Cost-Sensitive Densely Connected Deep Neural Networks |
| title_fullStr | Device Modeling Based on Cost-Sensitive Densely Connected Deep Neural Networks |
| title_full_unstemmed | Device Modeling Based on Cost-Sensitive Densely Connected Deep Neural Networks |
| title_short | Device Modeling Based on Cost-Sensitive Densely Connected Deep Neural Networks |
| title_sort | device modeling based on cost sensitive densely connected deep neural networks |
| topic | Machine learning device modeling technology computer-aided design (TCAD) simulation cost-sensitive densely connected DNN |
| url | https://ieeexplore.ieee.org/document/10643157/ |
| work_keys_str_mv | AT xiaoyingtang devicemodelingbasedoncostsensitivedenselyconnecteddeepneuralnetworks AT zhiqiangli devicemodelingbasedoncostsensitivedenselyconnecteddeepneuralnetworks AT langzeng devicemodelingbasedoncostsensitivedenselyconnecteddeepneuralnetworks AT hongweizhou devicemodelingbasedoncostsensitivedenselyconnecteddeepneuralnetworks AT xiaoxucheng devicemodelingbasedoncostsensitivedenselyconnecteddeepneuralnetworks AT zhenjieyao devicemodelingbasedoncostsensitivedenselyconnecteddeepneuralnetworks |