检索结果-内蒙古大学图书馆

arXiv 2025年

作者： Liu, Yiting Zhou, Hai Wang, Jia Yang, Fan Zeng, Xuan Shang, Li School of Computer Science Fudan University Shanghai China Department of ECE Northwestern University Evanston United States Department of ECE IIIinois Institute of Technology Chicago United States State Key Lab of ASIC & System Microelectronics Department Fudan University Shanghai China

Placement is a critical task with high computation complexity in VLSI physical design. Modern analytical placers formulate the placement objective as a nonlinear optimization task, which suffers a long iteration time. To accelerate and enhance the placement process, recent studies have turned to deep learning-based approaches, particularly leveraging graph convolution networks (GCNs). However, learning-based placers require time- and data-consuming model training due to the complexity of circuit placement that involves large-scale cells and design-specific graph statistics. This paper proposes GiFt, a parameter-free technique for accelerating placement, rooted in graph signal processing. GiFt excels at capturing multi-resolution smooth signals of circuit graphs to generate optimized placement solutions without the need for time-consuming model training, and meanwhile significantly reduces the number of iterations required by analytical placers. Experimental results show that GiFt significantly improving placement efficiency, while achieving competitive or superior performance compared to state-of-the-art placers. In particular, compared to DREAMPlace, the recently proposed GPU-accelerated analytical placer, GF-Placer improves total runtime over 45%. Copyright © 2025, The Authors. All rights reserved.

关键词： Nonlinear programming

来源：评论

学校读者我要写书评

暂无评论

Enhancement of refresh time in quasi-nonvolatile memory by the density of states engineering

引用

Journal of Semiconductors 2021年第2期42卷 100-107页

作者： Zhaowu Tang Chunsen Liu Senfeng Zeng Xiaohe Huang Liwei Liu Jiayi Li Yugang Jiang David Wei Zhang Peng Zhou State Key Laboratory of ASIC and System School of MicroelectronicsFudan UniversityShanghai 200433China School of Computer Science Fudan UniversityShanghai 200433China

The recently reported quasi-nonvolatile memory based on semi-floating gate architecture has attracted extensive attention thanks to its potential to bridge the large gap between volatile and nonvolatile ***,the further extension of the refresh time in quasi-nonvolatile memory is limited by the charge leakage through the p-n ***,based on the density of states engineered van der Waals heterostructures,the leakage of electrons from the floating gate to the channel is greatly *** a result,the refresh time is effectively extended to more than 100 s,which is the longest among all previously reported quasi-nonvolatile *** work provides a new idea to enhance the refresh time of quasi-nonvolatile memory by the density of states engineering and demonstrates great application potential for high-speed and low-power memory technology.

关键词： quasi-nonvolatile memory refresh time density of states engineering

来源：评论

学校读者我要写书评

暂无评论

DeepCell: Multiview Representation Learning for Post-Mapping Netlists

arXiv

引用

arXiv 2025年

作者： Shi, Zhengyuan Ma, Chengyu Zheng, Ziyang Zhou, Lingfeng Pan, Hongyang Jiang, Wentao Yang, Fan Yang, Xiaoyan Chu, Zhufei Xu, Qiang Department of Computer Science and Engineering The Chinese University of Hong Kong Sha Tin Hong Kong Faculty of Electrical Engineering and Computer Science Ningbo University Ningbo China School of Computer Science Hangzhou Dianzi University Hangzhou China School of Microelectronics State Key Laboratory of Integrated Chips and System Fudan University Shanghai China National Center of Technology Innovation for EDA Nanjing China

Representation learning for post-mapping (PM) netlists is a critical challenge in Electronic Design Automation (EDA), driven by the diverse and complex nature of modern circuit designs. Existing approaches focus on intermediate representations like And-Inverter Graphs (AIGs), limiting their applicability to post-synthesis stages. We introduce DeepCell, a multiview representation learning framework that integrates structural and functional insights from both PM netlists and AIGs to learn rich, generalizable embeddings. At its core, DeepCell employs the novel Mask Circuit Modeling (MCM) mechanism, which refines PM netlist representations in a self-supervised manner using pretrained AIG encoders. DeepCell sets a new benchmark in PM netlist representation, outperforming existing methods in predictive accuracy and reconstruction fidelity. To validate its efficacy, we apply DeepCell to functional Engineering Change Orders (ECO), achieving significant reductions in patch generation costs and runtime while improving patch quality. Copyright © 2025, The Authors. All rights reserved.

关键词： Mapping

来源：评论

学校读者我要写书评

暂无评论

Multilayer CVD graphene electrodes using a transfer-free process for the next generation of optically transparent and MRI-compatible neural interfaces

引用

Microsystems & Nanoengineering 2022年第5期8卷 183-196页

作者： Nasim Bakhshaee Babaroud Merlin Palmar Andrada Iulia Velea Chiara Coletti Sebastian Weingärtner Frans Vos Wouter A.Serdijn Sten Vollebregt Vasiliki Giagka Department of Microelectronics Faculty of Electrical EngineeringMathematics and Computer ScienceDelft University of TechnologyMekelweg 4Delft 2628 CDThe Netherlands Technologies for Bioelectronics Group Department of System Integration and Interconnection TechnologiesFraunhofer Institute for Reliability and Micro-integration IZMGustav-Meyer-Allee 25Berlin 13355Germany Department of Imaging Physics Faculty of Applied ScienceDelft University of TechnologyLorentzweg 1Delft 2628 CJThe Netherlands Erasmus University Medical Center(Erasmus MC) dr.Molewaterplein 40Rotterdam 3015 GDThe Netherlands

Multimodal platforms combining electrical neural recording and stimulation,optogenetics,optical imaging,and magnetic resonance(MRI)imaging are emerging as a promising platform to enhance the depth of characterization in neuroscientific *** conductive,optically transparent,and MRI-compatible electrodes can optimally combine all *** as a suitable electrode candidate material can be grown via chemical vapor deposition(CVD)processes and sandwiched between transparent biocompatible ***,due to the high graphene growth temperature(≥900℃)and the presence of polymers,fabrication is commonly based on a manual transfer process of pre-grown graphene sheets,which causes reliability *** this paper,we present CVD-based multilayer graphene electrodes fabricated using a wafer-scale transfer-free process for use in optically transparent and MRI-compatible neural *** fabricated electrodes feature very low impedances which are comparable to those of noble metal electrodes of the same size and *** also exhibit the highest charge storage capacity(CSC)reported to date among all previously fabricated CVD graphene *** graphene electrodes did not reveal any photo-induced artifact during 10-Hz light pulse ***,we show here,for the first time,that CVD graphene electrodes do not cause any image artifact in a 3T MRI *** results demonstrate that multilayer graphene electrodes are excellent candidates for the next generation of neural interfaces and can substitute the standard conventional metal *** fabricated graphene electrodes enable multimodal neural recording,electrical and optogenetic stimulation,while allowing for optical imaging,as well as,artifact-free MRI studies.

关键词： transparent transfer process

来源：评论

学校读者我要写书评

暂无评论

Wiki2GH: A Recommendation Service to Link Software Engineering Knowledge to Practical Development 17th

Wiki2GH: A Recommendation Service to Link Software Engineeri...

引用

CCF 17th International Conference on Service Science, CCF ICSS 2024

作者： Zhou, Yuqi Sun, Yanchun Wu, Jiawei Zhang, Jiaqi Huang, Gang Key Laboratory of High Confidence Software Technologies Ministry of Education Beijing China School of Computer Science Peking University Beijing China School of Software and Microelectronics Peking University Beijing China National Key Laboratory of Data Space Technology and System Beijing China

ISBN: (纸本)9789819757596

High-quality software applications are built on the knowledge and best practices of software engineering. However, there is a huge gap between the theoretical knowledge of software engineering and its practical implementation for software developers, especially beginners of software development. This paper proposes an innovative recommendation service named Wiki2GH to link Wikipedia software engineering knowledge to GitHub frameworks and libraries, aiming to help software developers systematically learn knowledge and apply it into practice. To implement the Wiki2GH recommendation service, this paper first uses the public data of Wikipedia to build a hierarchy software development knowledge catalog as the entrance of the service. Next, we propose a deep learning method to identify frameworks and libraries and construct a knowledge graph of open source software repositories based on dependency graph. Then, we propose a combined application recommendation service of frameworks and libraries in the development practice. The methods proposed in this paper are all evaluated, including the repository type classification method, the recommendation method, and the knowledge graph construction method. Experimental results show the effectiveness of the recommendation service proposed in this paper. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Knowledge graph

来源：评论

学校读者我要写书评

暂无评论

FedAA: A Reinforcement Learning Perspective on Adaptive Aggregation for Fair and Robust Federated Learning 39

FedAA: A Reinforcement Learning Perspective on Adaptive Aggr...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： He, Jialuo Chen, Wei Zhang, Xiaojin National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Cluster and Grid Computing Lab School of Computer Science and Technology Huazhong University of Science and Technology Wuhan 430074 China School of Microelectronics and Communication Engineering Chongqing University Chongqing 400044 China School of Software Engineering Huazhong University of Science and Technology Wuhan 430074 China

ISBN: (纸本)157735897X

Federated Learning (FL) has emerged as a promising approach for privacy-preserving model training across decentralized devices. However, it faces challenges such as statistical heterogeneity and susceptibility to adversarial attacks, which can impact model robustness and fairness. Personalized FL attempts to provide some relief by customizing models for individual clients. However, it falls short in addressing server-side aggregation vulnerabilities. We introduce a novel method called FedAA, which optimizes client contributions via Adaptive Aggregation to enhance model robustness against malicious clients and ensure fairness across participants in non-identically distributed settings. To achieve this goal, we propose an approach involving a Deep Deterministic Policy Gradient-based algorithm for continuous control of aggregation weights, an innovative client selection method based on model parameter distances, and a reward mechanism guided by validation set performance. Empirically, extensive experiments demonstrate that, in terms of robustness, FedAA outperforms the state-of-the-art methods, while maintaining comparable levels of fairness, offering a promising solution to build resilient and fair federated systems. Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Deep Q-learning Sampling Based on Advantages 5

Deep Q-learning Sampling Based on Advantages

引用

5th International Conference on Intelligent Robotics and Control Engineering, IRCE 2022

作者： Xie, Ming Ren, Xinrui Yu, Jianbo Shu, Feng Shanghai Engineering Research Center of Ultra-Precision Motion Control and Measurement Academy for Engineering and Technology Fudan University Shanghai China School of Optical-Electrical and Computer Engineering University of Shanghai for Science and Technology Shanghai China School of Microelectronics Fudan University State Key Laboratory of ASIC and System Shanghai200433 China

ISBN: (数字)9781665469951

ISBN: (纸本)9781665469951

Deep Q-learning (DQN) has shown recent success on a wide range of complicated sequential decision-making issues, especially in the classic control area. However, in most DQN training, the sampling policies, particularly the ϵ-greedy policy and its derivation rules, produce noise erroneously due to the unsteadiness and unreliability of Q values utilized for searching for optimum actions. We begin with a fundamental hypothesis: complete advantages-based exploitation may be employed to help in successful exploration, and the gap between advantages on outstanding and poor actions tends to extend during the early phases of training before stabilizing. We then present a novel DQN architecture with a superior sampling policy that is totally and directly based on advantage values. This new DQN is named A-sampling DQN, and it requires minor code changes based on the original DQN codes. In most cases, A-sampling DQN and its derivatives outperformed the traditional DQN method. © 2022 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

A Multichannel 14-Bit, 3-Msps/channel, Event-Driven Hybrid ADC with SAR/SS/TDC Architecture for Dark Matter Detection

A Multichannel 14-Bit, 3-Msps/channel, Event-Driven Hybrid A...

引用

IEEE Symposium on Nuclear Science (NSS/MIC)

作者： C. Yu J. Cheng B. Yang Y. Qian W. Gao School of Computer Science Institute of Microelectronics Northwestern Polytechnical University Xi’an China Chinese Academy of Science Institute of Modern Physics Lanzhou China Ministry of Education Engineering Research Center of Embedded System Integrated Xi’an China

In the next-generation dark matter detection misssion, energy-efficient front-end electronics plays an importan role to construct space-bone radiation detector systems. A multichannel analog-to-digital converter (ADC) is required to digitize the analog signals from readout channels which is employed to read out the charges from a PMT detector with the plastic scintillator. The requirements of the ADC are listed below: the resolution of 14 bits; the sampling rate of larger than 3 Msps per channel, and the channel number of 16 (or more). In this paper, a novel hybrid ADC, which combines the techniques of successive approximate register (SAR) ADC, single-slope (SS) ramp ADC and time-to-digital converter (TDC) based on delay-locked loop (DLL), is proposed to meet the above performance constrains. A 5-bit SAR ADC, a 4-bit SS ADC and a 5-bit TDC are finally selected to construct a 14-bit converter under the tradeoff of resolution, speed and power dissipation. The advantage of this architecture lies in that it is easy to extended to multiple channels by the increase small power and area overhead in each channel. Both event-driven mode and continuous-conversion mode are realized for timing controlling and data readout. A four-channel prototype chip has been designed and fabricated in 0.18 μm CMOS process with 1.8/3.3 V power supply. A sampling rate of ~ 3.3 MS/s is achieved at the clock frequency of 100 MHz. Under the power consumption of 4 mW/channel, the differential nonlinearity (DNL) and the integral nonlinearity (INL) are simulated as -1/+0.7 LSB and -3 LSB/+2.8 LSB, respectively. The effective-number-of-bits (ENOB) is 12.7 bits and the signal-to-noise ratio (SNR) is 85.9 dB. The figure-of-merit (FOM) of 192.9 f J /conv.-step has been achieved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Numerical Analysis of Self-Heating Effect in HEMT Transistors

Numerical Analysis of Self-Heating Effect in HEMT Transistor...

引用

International Conference on Electrical, Communication, and computer Engineering (ICECCE)

作者： Faouzi Nasri Haikel Mzoughi Husien Salama Khalifa Ahmed Salama Center for Research in Microelectronics and Nanotechnology Sousse Tunisia Laboratory of Thermal Process Research and Technology of Energy Tunis Tunisia Computer System Institute Boston USA Libyan Center for Enginnering Research and Information Technology Bani Walid Libya

The analysis of power dissipation and operating temperature is of great importance for electrothermal design in power electronics. In this communication, an electrothermal simulation analysis of AlGaN/GaN double metal gate (DMG) high electron mobility transistor (HEMT) using finite element method (FEM) was done. The thermal and electrical behavior of the device was evaluated by simulating the output and transfer characteristics with and without Joule effect and power dissipation. In addition, we have carefully studied the effect of VDS drain polarization on the increase in the HEMT operating temperature. The results indicate that self-heating significantly degrades the electrical performance of the device, as evidenced by the increase in the operating temperature of the transistor.

关键词：

来源：评论

学校读者我要写书评

暂无评论

FedAA: A Reinforcement Learning Perspective on Adaptive Aggregation for Fair and Robust Federated Learning

arXiv

引用

arXiv 2024年

作者： He, Jialuo Chen, Wei Zhang, Xiaojin National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Cluster and Grid Computing Lab School of Computer Science and Technology Huazhong University of Science and Technology Wuhan430074 China School of Microelectronics and Communication Engineering Chongqing University Chongqing400044 China School of Software Engineering Huazhong University of Science and Technology Wuhan430074 China

Federated Learning (FL) has emerged as a promising approach for privacy-preserving model training across decentralized devices. However, it faces challenges such as statistical heterogeneity and susceptibility to adversarial attacks, which can impact model robustness and fairness. Personalized FL attempts to provide some relief by customizing models for individual clients. However, it falls short in addressing server-side aggregation vulnerabilities. We introduce a novel method called FedAA, which optimizes client contributions via Adaptive Aggregation to enhance model robustness against malicious clients and ensure fairness across participants in non-identically distributed settings. To achieve this goal, we propose an approach involving a Deep Deterministic Policy Gradient-based algorithm for continuous control of aggregation weights, an innovative client selection method based on model parameter distances, and a reward mechanism guided by validation set performance. Empirically, extensive experiments demonstrate that, in terms of robustness, FedAA outperforms the state-of-the-art methods, while maintaining comparable levels of fairness, offering a promising solution to build resilient and fair federated systems. Our code is available at https://***/Gp1g/FedAA. Copyright © 2024, The Authors. All rights reserved.

关键词： Federated learning

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：