Enhancement and Expansion of the Neural Network-Based Compact Model Using a Binning Method
The artificial neural network (ANN)-based compact model has significant advantages over physics-based standard compact models such as BSIM-CMG because it can achieve higher accuracy over a wide range of geometric parameters. This makes it particularly suitable for design space exploration and optimi...
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/10371311/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832583203769024512 |
|---|---|
| author | Jinyoung Choi Hyunjoon Jeong Sangmin Woo Hyungmin Cho Yohan Kim Jeong-Taek Kong Soyoung Kim |
| author_facet | Jinyoung Choi Hyunjoon Jeong Sangmin Woo Hyungmin Cho Yohan Kim Jeong-Taek Kong Soyoung Kim |
| author_sort | Jinyoung Choi |
| collection | DOAJ |
| description | The artificial neural network (ANN)-based compact model has significant advantages over physics-based standard compact models such as BSIM-CMG because it can achieve higher accuracy over a wide range of geometric parameters. This makes it particularly suitable for design space exploration and optimization. However, the ANN-based compact model using only one set of model parameters (global-ANN) requires larger model sizes to achieve wider coverage and higher accuracy in order to capture the unpredictable nonlinearities of emerging devices. This results in reduced simulation speed and a trade-off between simulation accuracy, model coverage, and simulation speed makes it difficult to utilize ANN-based compact models in a variety of ways. To solve this problem, we propose the first ANN-based compact modeling flow using a binning method (binning-ANN) and we address the training requirements and data sparsity issues that may occur due to the binning method in ANNs. In addition, we develop a bin size optimization guideline for the binning-ANN. As a result, the binning-ANN not only has higher accuracy, but also much better expandability than existing methods. |
| format | Article |
| id | doaj-art-049f485f178443b79577e12895cf46a6 |
| 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-049f485f178443b79577e12895cf46a62025-01-29T00:00:07ZengIEEEIEEE Journal of the Electron Devices Society2168-67342024-01-0112657310.1109/JEDS.2023.334638010371311Enhancement and Expansion of the Neural Network-Based Compact Model Using a Binning MethodJinyoung Choi0https://orcid.org/0000-0003-0159-4800Hyunjoon Jeong1https://orcid.org/0000-0003-0350-5031Sangmin Woo2https://orcid.org/0000-0002-4374-980XHyungmin Cho3https://orcid.org/0009-0003-2094-6557Yohan Kim4https://orcid.org/0000-0002-2699-2496Jeong-Taek Kong5Soyoung Kim6https://orcid.org/0000-0001-8901-3649Department of Semiconductor and Display Engineering, College of Information and Communication Engineering, Sungkyunkwan University, Suwon, Republic of KoreaDepartment of Electrical and Computer Engineering, College of Information and Communication Engineering, Sungkyunkwan University, Suwon, Republic of KoreaDepartment of Electrical and Computer Engineering, College of Information and Communication Engineering, Sungkyunkwan University, Suwon, Republic of KoreaDepartment of Semiconductor and Display Engineering, College of Information and Communication Engineering, Sungkyunkwan University, Suwon, Republic of KoreaComputational Science and Engineering Team, Innovation Center, Samsung Electronics, Suwon, Republic of KoreaDepartment of Semiconductor Systems Engineering, College of Information and Communication Engineering, Sungkyunkwan University, Suwon, Republic of KoreaDepartment of Semiconductor Systems Engineering, College of Information and Communication Engineering, Sungkyunkwan University, Suwon, Republic of KoreaThe artificial neural network (ANN)-based compact model has significant advantages over physics-based standard compact models such as BSIM-CMG because it can achieve higher accuracy over a wide range of geometric parameters. This makes it particularly suitable for design space exploration and optimization. However, the ANN-based compact model using only one set of model parameters (global-ANN) requires larger model sizes to achieve wider coverage and higher accuracy in order to capture the unpredictable nonlinearities of emerging devices. This results in reduced simulation speed and a trade-off between simulation accuracy, model coverage, and simulation speed makes it difficult to utilize ANN-based compact models in a variety of ways. To solve this problem, we propose the first ANN-based compact modeling flow using a binning method (binning-ANN) and we address the training requirements and data sparsity issues that may occur due to the binning method in ANNs. In addition, we develop a bin size optimization guideline for the binning-ANN. As a result, the binning-ANN not only has higher accuracy, but also much better expandability than existing methods.https://ieeexplore.ieee.org/document/10371311/Artificial neural network (ANN)machine learning (ML)device modelingcompact modelbinningemerging device |
| spellingShingle | Jinyoung Choi Hyunjoon Jeong Sangmin Woo Hyungmin Cho Yohan Kim Jeong-Taek Kong Soyoung Kim Enhancement and Expansion of the Neural Network-Based Compact Model Using a Binning Method IEEE Journal of the Electron Devices Society Artificial neural network (ANN) machine learning (ML) device modeling compact model binning emerging device |
| title | Enhancement and Expansion of the Neural Network-Based Compact Model Using a Binning Method |
| title_full | Enhancement and Expansion of the Neural Network-Based Compact Model Using a Binning Method |
| title_fullStr | Enhancement and Expansion of the Neural Network-Based Compact Model Using a Binning Method |
| title_full_unstemmed | Enhancement and Expansion of the Neural Network-Based Compact Model Using a Binning Method |
| title_short | Enhancement and Expansion of the Neural Network-Based Compact Model Using a Binning Method |
| title_sort | enhancement and expansion of the neural network based compact model using a binning method |
| topic | Artificial neural network (ANN) machine learning (ML) device modeling compact model binning emerging device |
| url | https://ieeexplore.ieee.org/document/10371311/ |
| work_keys_str_mv | AT jinyoungchoi enhancementandexpansionoftheneuralnetworkbasedcompactmodelusingabinningmethod AT hyunjoonjeong enhancementandexpansionoftheneuralnetworkbasedcompactmodelusingabinningmethod AT sangminwoo enhancementandexpansionoftheneuralnetworkbasedcompactmodelusingabinningmethod AT hyungmincho enhancementandexpansionoftheneuralnetworkbasedcompactmodelusingabinningmethod AT yohankim enhancementandexpansionoftheneuralnetworkbasedcompactmodelusingabinningmethod AT jeongtaekkong enhancementandexpansionoftheneuralnetworkbasedcompactmodelusingabinningmethod AT soyoungkim enhancementandexpansionoftheneuralnetworkbasedcompactmodelusingabinningmethod |