检索结果-内蒙古大学图书馆

Compact Model Build Upon Dynamic Weighting Artificial Neural Network Approach for Complementary Field Effect Transistors

引用

IEEE Transactions on Electron Devices 2024年第1期71卷 246-253页

作者： Butola, Rajat Li, Yiming Kola, Sekhar Reddy National Yang Ming Chiao Tung University Parallel and Scientific Computing Laboratory Electrical Engineering and Computer Science International Graduate Program Hsinchu300093 Taiwan Institute of Pioneer Semiconductor Innovation The Institute of Artificial Intelligence Innovation National Yang Ming Chiao Tung University Parallel and Scientific Computing Laboratory Electrical Engineering and Computer Science International Graduate Program The Institute of Communications Engineering the Institute of Biomedical Engineering Department of Electronics and Electrical Engineering Hsinchu300093 Taiwan

In this work, a dynamic weighting-artificial neural network (DW-ANN) methodology is presented for quick and automated compact model (CM) generation. It takes advantage of both TCAD simulations for high accuracy and SPICE simulations for cost-effectiveness. This methodology is developed for gate-all-around (GAA) silicon (Si) nanosheet (NS) complementary field effect transistor (CFET), a potential candidate for future CMOS technology due to its innate properties. The critical process variation (PV) sources that severely degrade the CFET performance are estimated using DW-ANN. It reduces the computation cost and predicts the effects of PV sources with less than 1% error. Furthermore, a compact DW-ANN-based Verilog-A model has been developed that captures the dc as well as transient behavior accurately for circuit-level analysis. CFET-based circuits such as inverter, 6T-static random access memory (SRAM), and ring oscillator (RO) are characterized and implemented using DW-ANN-based CM. The overall average error of the model is reported as less than 2%. Therefore, the proposed device and circuit modeling approach provides a feasible solution for the rapid compact modeling of new emerging devices with good convergence and high accuracy. © 1963-2012 IEEE.

关键词： Neural networks

来源：评论

学校读者我要写书评

暂无评论

Transfer learning approach to modeling multichannel gate-all-around nanosheet field-effect transistors under work function fluctuations

引用

engineering Applications of Artificial Intelligence 2025年 148卷

作者： Dash, Sagarika Li, Yiming Parallel and Scientific Computing Laboratory National Yang-Ming Chiao Tung University 1001 Ta-Hsueh Rd. Hsinchu300093 Taiwan Electrical Engineering and Computer Science International Graduate Program National Yang-Ming Chiao Tung University 1001 Ta-Hsueh Rd. Hsinchu300093 Taiwan Institute of Communications Engineering National Yang-Ming Chiao Tung University 1001 Ta-Hsueh Rd. Hsinchu300093 Taiwan Institute of Biomedical Engineering National Yang-Ming Chiao Tung University 1001 Ta-Hsueh Rd. Hsinchu300093 Taiwan Institute of Pioneer Semiconductor Innovation National Yang-Ming Chiao Tung University 1001 Ta-Hsueh Rd. Hsinchu300093 Taiwan Institute of Artificial Intelligence Innovation National Yang-Ming Chiao Tung University 1001 Ta-Hsueh Rd. Hsinchu300093 Taiwan Department of Electronics and Electrical Engineering National Yang-Ming Chiao Tung University 1001 Ta-Hsueh Rd. Hsinchu300093 Taiwan Department of Microelectronics National Yang-Ming Chiao Tung University 1001 Ta-Hsueh Rd. Hsinchu300093 Taiwan

Deep learning (DL) has significantly advanced various industries, including semiconductors, by providing sophisticated methods for analyzing emerging device data. Transfer learning (TL), a prominent DL topology, leverages knowledge from a pre-trained model to improve the performance of a specific target task. This study aims to apply TL to predict the impact of work function fluctuation (WKF) on the variability of threshold voltage (σVTH) in gate-all-around silicon nanosheet field-effect transistors (GAA Si NS FETs). We used TL to transfer knowledge from models trained on 1-channel (1ch) GAA Si NS FETs to more complex 4-channel (4ch) counterparts. The prediction accuracy is evaluated by using the mean square error(MSE), root mean square error (RMSE), and the mean absolute error(MAE) metrics. Our TL approach achieved an error rate of less than 1%, demonstrating high accuracy in predicting WKF effects on σ VTH of 4ch GAA Si NS FETs using only 500 samples. This study presents a pioneering application of TL using a one-dimensional (1D) convolutional neural network (CNN) long short-term memory (LSTM) topology in semiconductor device technology. The results effectively address the challenge of predicting σ VTH variations in advanced GAA Si NS FETs because of WKF, which eliminates the need for extensive semiconductor device simulations. © 2025 Elsevier Ltd

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Formant-based analysis of vowels in Modern Standard ArabicPreliminary results

Formant-based analysis of vowels in Modern Standard ArabicPr...

引用

2012 11th International Conference on Information Science, Signal Processing and their Applications, ISSPA 2012

作者： Seddiq, Yasser Mohammad Alotaibi, Yousef Ajami Computer Engineering Department King Saud University Saudi Arabia National Program of Electronics Communications and Photonics King Abdulaziz City for Science and Technology Saudi Arabia

ISBN: (纸本)9781467303828

Although of the importance of analyzing vowel phonemes in the Modern Standard Arabic (MSA), it has not been paid a considerable attention in the published literature yet. Consequently, a formant-based analysis for the six vowels of MSA in connected speech was carried out in this work. The values of the first three formant frequencies were captured. The present results were compared to some previously published results conducted on MSA and other Arabic dialects. The comparison was performed from geometric perspective using the Euclidean distance. The results of the geometric comparison were found to be consistent with the visual inspection of the vowel triangles. © 2012 IEEE.

关键词： Linguistics

来源：评论

学校读者我要写书评

暂无评论

An implementation of a 2D FIR filter using the signed-digit number system

An implementation of a 2D FIR filter using the signed-digit ...

引用

Saudi International Electronics, communications and Photonics Conference 2011, SIECPC 2011

作者： Seddiq, Yasser Mohammad Altwaijry, Hesham National Program of Electronics Communications and Photonics King Abdulaziz City for Science and Technology Saudi Arabia Department of Computer Engineering King Saud University Saudi Arabia

ISBN: (纸本)9781457700699

An FIR filter is implemented in this work. Enhancing the arithmetic operations of the filter is considered. For the addition operation, the signed-digit number system is utilized. For the multiplication operation, Booth-3 algorithm is used to reduce the number of partial products. Then a 1D filter is used to construct a 2D filter that is deployed on real hardware in an image processing application. © 2011 IEEE.

关键词： Digital signal processing

来源：评论

学校读者我要写书评

暂无评论

Achieving compelling student comprehension of complex information structures for both on-site and on-line courses

Achieving compelling student comprehension of complex inform...

引用

2008 ASEE Annual Conference and Exposition

作者： Uhlig, Ronald Farahani, Alireza Viswanathan, Shekar Evans, Howard Sotelo, Mark National University Department of Computer Science and Information Systems School of Engineering and Technology National University Wireless Communications for the Master ot Science in Wireless Communications Program International Telecommunications Academy School of Engineering and Technology Department of Applied Engineering Lead Faculty for Engineering Management and Homeland Security and Safety Engineering Academic Computing for National University

Teaching engineering and technology subjects involves conveying understanding of abstract information structures and processes such as complex telecommunications protocols, complex mathematical concepts, and data structures. These are multidimensional and can be difficult to grasp quickly. Supported by a Hewlett-Packard (HP) Technology for Teaching grant, the School of engineering and Technology at National University has embarked on a project to enable students to grasp these complex concepts more quickly and easily, using continuous dialog among students and instructors as the structures are first introduced and then examined from multiple perspectives through real-time interaction among students, small groups, and instructors. HP Wireless Tablet PCs are used to discuss and experiment with diagrams and processes in realtime. This allows combining lectures and problem-solving sessions into a single class session. Our hypothesis is that: 1) an in-depth learning of theory is accomplished, and 2) student engagement is enhanced. Presentation of theory by the instructor is integrated with application while the theory is still in the student's short-term memory. Students no longer have to wait for a separate session such as a recitation session to apply the concepts. This approach often takes less time. In addition to accelerating the learning process, expert instructors find this approach more rewarding as students grasp new concepts more quickly. Analysis of data captured from both students and instructors are presented to support our hypotheses, and our results are compared with similar research carried out by other universities. In addition, the level of interaction enabled by the use of HP Tablets in on-line classes is discussed. The best teaching tools available in existing on-line teaching platforms are compared with the additional tools available in on-site courses when every student has a wireless Tablet PC and specific recommendations are made to on-line teachi

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

Assessing the intercultural competence of sophomore mechanical engineering students: Baseline data and analysis

Assessing the intercultural competence of sophomore mechanic...

引用

2010 ASEE Annual Conference and Exposition

作者： Thompson, Juila Jesiek, Brent Atkinson, Dianne Dept. of Engineering Education Purdue University United States Dept. of Engineering Education and Electrical and Computer Engineering Purdue University United States School of Mechanical Engineering Purdue University Technical Communications Program United States

This paper presents baseline analysis of Intercultural Development Inventory (IDI) results for approximately five hundred sophomore mechanical engineering students at Purdue University. The IDI is a statistically reliable and cross-culturally valid measure of an individual's actual and perceived intercultural development. This instrument is being used by Purdue's School of Mechanical engineering, particularly to assess students who are involved in global educational programs such as Global engineering Alliance for Research and Education (GEARE). In this paper we examine IDI results for Purdue sophomore mechanical engineering students, including comparisons based on gender, amount of time spent living abroad, and whether or not they later participated in GEARE. We intend that our results will provide valuable baseline data for sophomore mechanical engineering students, thereby paving the way for cross-institutional comparisons, and enhancing the ability of university staff to design courses and experiences for students that match their current levels of intercultural sensitivity. We conclude with suggestions for further research and analysis, such as collecting and analyzing post-experience IDI data for students who have participated in global educational experiences. © American Society for engineering Education, 2010.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

Needs of collaborative digital library for secondary school students in Thailand

Needs of collaborative digital library for secondary school ...

引用

14th International Conference on Asia-Pacific Digital Libraries, ICADL 2012

作者： Kanyacome, Suparp Loipha, Smarn Numprasertchai, Somchai Information Studies Khon Kaen University Thailand Program of Information Science and Communications Faculty of Humanities and Social Sciences Khon Kaen University Thailand Department of Computer Engineering Faculty of Engineering Kasetsart University Thailand

ISBN: (纸本)9783642347511

The objective of this research was to examine needs of collaborative digital library for secondary school students. 132 teachers and 397students from 132 secondary schools were selected by multi-stage random sampling method as samples. Data were collected during December 2011 - February 2012 by questionnaires and recording forms. Data were statically analyzed by using the percentage, mean, standard deviation and independent t-test. The outcome revealed that needs of collaborative digital library were virtual spaces consisted of 4 main aspects: 1) public area, 2) personal area, 3) collaborative area and 4) social activities area. The result illustrated that teachers were statistical significantly needed more in every aspect than the students at the level of 0.01. This study was a part to fulfill Ph.D dissertation and the result will be used to develop a prototype system in the future. © 2012 Springer-Verlag.

关键词： Digital libraries

来源：评论

学校读者我要写书评

暂无评论

A Comprehensive Technique Based on Machine Learning for Device and Circuit Modeling of Gate-All-Around Nanosheet Transistors

IEEE Open Journal of Nanotechnology

引用

IEEE Open Journal of Nanotechnology 2023年 4卷 181-194页

作者： Butola, Rajat Li, Yiming Kola, Sekhar Reddy National Yang Ming Chiao Tung University Parallel and Scientific Computing Laboratory Electrical Engineering and Computer Science International Graduate Program Hsinchu300093 Taiwan National Yang Ming Chiao Tung University Institute of Communications Engineering the Institute of Biomedical Engineering the Department of Electronics and Electrical Engineering the Institute of Pioneer Semiconductor Innovation and the Institute of Artificial Intelligence Innovation Hsinchu300093 Taiwan

Machine learning (ML) is poised to play an important part in advancing the predicting capability in semiconductor device compact modeling domain. One major advantage of ML-based compact modeling is its ability to capture complex relationships and patterns in large datasets. Therefore, in this paper a novel design scheme based on dynamically adaptive neural network (DANN) is proposed to develop fast and accurate compact model (CM). This framework constitutes a powerful yet computationally efficient methodology and exhibits emergent dynamic behaviors. This paper demonstrates that the compact model based on ML can be designed to replicate the performance of conventional compact model for nanodevices. For this work, gate-all-around (GAA) nanosheet (NS) device characteristics are comprehensively analyzed for process variability sources using the proposed model. The device geometry parameters such as channel length, nanosheet width and nanosheet thickness are fed as input features to the DANN model. The adaptive neural network learns dynamically by updating weights of the model in accordance with the input features and achieves accurate neural weight convergence. The proposed model predicted the electrical characteristics of NS devices with less than 1% error rate. The model is also implemented and validated for the simulations of digital circuit designs such as inverter, and logic gates. ©;2023 The Authors.

关键词： Circuit simulation

来源：评论

学校读者我要写书评

暂无评论

A Physical-Based Artificial Neural Networks Compact Modeling Framework for Emerging FETs

引用

IEEE Transactions on Electron Devices 2024年第1期71卷 223-230页

作者： Yang, Ya-Shu Li, Yiming Kola, Sekhar Reddy Reddy National Yang Ming Chiao Tung University Parallel and Scientific Computing Laboratory The Institute of Communications Engineering Hsinchu300093 Taiwan National Yang Ming Chiao Tung University Parallel and Scientific Computing Laboratory Institute of Communications Engineering Institute of Biomedical Engineering Department of Electronics and Electrical Engineering Hsinchu300093 Taiwan National Yang Ming Chiao Tung University Parallel and Scientific Computing Laboratory Electrical Engineering and Computer Science International Graduate Program Hsinchu300093 Taiwan

We report a compact modeling framework based on the Grove-Frohman (GF) model and artificial neural networks (ANNs) for emerging gate-all-around (GAA) MOSFETs. The framework consists of two ANNs;the first ANN constructed with the drain current model not only can capture the main trend of device I - V characteristics but also can predict its variation even when the amount of training data for the ANN is insufficient or outside the range of applied biases. The second one is then designed to improve the model accuracy by further minimizing the errors between the target and the model outputs. We implement the proposed framework to accurately model emerging GAA nanosheet (NS) MOSFETs and complementary FETs (CFETs) without suffering from divergent issues in circuit simulation. In addition, nonphysical behaviors, such as nonzero current at zero bias, do not occur in the modeling framework. Compared to recently reported machine-learning (ML) models, our approach can achieve a similar level of model accuracy with merely 20% amount of the training data. © 1963-2012 IEEE.

关键词： Neural networks

来源：评论

学校读者我要写书评

暂无评论

Hardware Resource Reliability Analysis based on Deep Learning for Virtual Machine Deployment Optimization 9

Hardware Resource Reliability Analysis based on Deep Learnin...

引用

9th IEEE Global Conference on Consumer Electronics, GCCE 2020

作者： Huang, Chih-Hao Huang, Bo-Hong Wu, Tin-Yu National Ilan University. Master Program of E-Learning for Multimedia and Network Communications Yilan Taiwan National Ilan University Department of Computer Science and Information Engineering Yilan Taiwan

This paper proposes a new method based on the Apriori algorithm and deep learning technology to improve the flexibility of hardware deployment and to analyze hardware usage reliability for VM. This method can signific... 详细信息

ISBN: (纸本)9781728198026

关键词： Reliability analysis

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：