检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Hu, Xuemin Chen, Pan Wen, Yijun Tang, Bo Chen, Long School of Artificial Intelligence Hubei University Wuhan430062 China Key Laboratory of Intelligent Sensing System and Security Hubei University Ministry of Education Hubei Wuhan430062 China Department of Electrical and Computer Engineering Worcester Polytechnic Institute WorcesterMA01609 United States State Key Laboratory of Multimodal Artificial Intelligence Systems State Key Laboratory of Management and Control for Complex Systems Chinese Academy of Sciences Beijing100190 China WAYTOUS Inc. Beijing100083 China Shenzhen518107 China Institute of Artificial Intelligence and Robotics Xi'an Jiaotong University Xi’an710049 China

Reinforcement learning (RL) has been widely used in decision-making and control tasks, but the risk is very high for the agent in the training process due to the requirements of interaction with the environment, which seriously limits its industrial applications such as autonomous driving systems. Safe RL methods are developed to handle this issue by constraining the expected safety violation costs as a training objective, but the occurring probability of an unsafe state is still high, which is unacceptable in autonomous driving tasks. Moreover, these methods are difficult to achieve a balance between the cost and return expectations, which leads to learning performance degradation for the algorithms. In this paper, we propose a novel algorithm based on the long and short-term constraints (LSTC) for safe RL. The short-term constraint aims to enhance the shortterm state safety that the vehicle explores, while the long-term constraint enhances the overall safety of the vehicle throughout the decision-making process, both of which are jointly used to enhance the vehicle safety in the training process. In addition, we develop a safe RL method with dual-constraint optimization based on the Lagrange multiplier to optimize the training process for end-to-end autonomous driving. Comprehensive experiments were conducted on the MetaDrive simulator. Experimental results demonstrate that the proposed method achieves higher safety in continuous state and action tasks, and exhibits higher exploration performance in long-distance decision-making tasks compared with state-of-the-art methods. Copyright © 2024, The Authors. All rights reserved.

关键词： Lagrange multipliers

来源：评论

学校读者我要写书评

暂无评论

Hardware-aware Compilation for Chip-to-Chip Coupler-Connected Modular Quantum systems

arXiv

引用

arXiv 2025年

作者： Du, Zefan Kan, Shuwen Stein, Samuel A. Liang, Zhiding Li, Ang Mao, Ying Department of Computer and Information Sciences Fordham University NY United States High Performance Computing Group Pacific Northwest National Laboratory WA United States Department of Electrical Computer and Systems Engineering Rensselaer Polytechnic Institute NY United States

As quantum processors scale, monolithic architectures face growing challenges due to limited qubit density, heterogeneous error profiles, and restricted connectivity. Modular quantum systems, enabled by chip-to-chip coupler-connected modular architectures, provide a scalable alternative. However, existing quantum compilers fail to accommodate this new architecture. We introduce CCMap, a circuit-compiler co-design framework that enhances existing quantum compilers with system-level coordination across modular chips. It leverages calibration data and introduces a coupler-aligned and noise-aware cost metric to evaluate circuit compilation. CCMap integrates with existing compilers by partitioning circuits into subcircuits compiled on individual chips, followed by a global mapping step to minimize the total cost. We evaluated CCMap on IBM-Q noisy emulators using real hardware calibrations across various coupler-connected topologies. Results show that CCMap improves circuit fidelity by up to 21.9%, representing a 30% increase, and reduces compilation cost by up to 58.6% over state-of-the-art baselines. These findings highlight CCMap’s potential to enable scalable, high-fidelity execution in coupler-connected modular quantum systems. Copyright © 2025, The Authors. All rights reserved.

关键词： Program compilers

来源：评论

学校读者我要写书评

暂无评论

Dynamic neural network with memristive CIM and CAM for 2D and 3D vision

arXiv

引用

arXiv 2024年

作者： Zhang, Yue Zhang, Woyu Wang, Shaocong Lin, Ning Yu, Yifei He, Yangu Wang, Bo Jiang, Hao Lin, Peng Xu, Xiaoxin Qi, Xiaojuan Wang, Zhongrui Zhang, Xumeng Shang, Dashan Liu, Qi Cheng, Kwang-Ting Liu, Ming Department of Electrical and Electronic Engineering The University of Hong Kong Hong Kong Key Laboratory of Microelectronic Devices & Integrated Technology Institute of Microelectronics Chinese Academy of Sciences Beijing100049 China ACCESS – AI Chip Center for Emerging Smart Systems InnoHK Centers Hong Kong Science Park Hong Kong Institute of the Mind The University of Hong Kong Hong Kong Key Lab of Fabrication Technologies for Integrated Circuits Chinese Academy of Sciences Beijing100049 China State Key Laboratory of Integrated Chips and Systems Frontier Institute of Chip and System Fudan University Shanghai200433 China University of Chinese Academy of Sciences Beijing100049 China College of Computer Science and Technology Zhejiang University Zhejiang310027 China Department of Electronic and Computer Engineering The Hong Kong University of Science and Technology Hong Kong

The brain is dynamic, associative and efficient. It reconfigures by associating the inputs with past experiences, with fused memory and processing. In contrast, AI models are static, unable to associate inputs with past experiences, and run on digital computers with physically separated memory and processing. We propose a hardware-software co-design, a semantic memory-based dynamic neural network (DNN) using memristor. The network associates incoming data with the past experience stored as semantic vectors. The network and the semantic memory are physically implemented on noise-robust ternary memristor-based Computing-In-Memory (CIM) and Content-Addressable Memory (CAM) circuits, respectively. We validate our co-designs, using a 40nm memristor macro, on ResNet and PointNet++ for classifying images and 3D points from the MNIST and ModelNet datasets, which not only achieves accuracy on par with software but also a 48.1% and 15.9% reduction in computational budget. Moreover, it delivers a 77.6% and 93.3% reduction in energy consumption. © 2024, CC BY.

关键词： Memristors

来源：评论

学校读者我要写书评

暂无评论

Real-Space Imaging of the Tailored Plasmons in Twisted Bilayer Graphene

arXiv

引用

arXiv 2023年

作者： Hu, Fengrui Das, Suprem R. Luan, Yilong Chung, T.-F. Chen, Yong P. Fei, Zhe Department of Physics and Astronomy Iowa State University AmesIA50011 United States Ames Laboratory U.S. Department of Energy Iowa State University AmesIA50011 United States Department of Mechanical Engineering Iowa State University AmesIA50011 United States Department of Industrial and Manufacturing Systems Engineering Kansas State University ManhattanKS66506 United States Department of Electrical and Computer Engineering Kansas State University ManhattanKS66506 United States Birck Nanotechnology Center Purdue University West LafayetteIN47907 United States Department of Physics and Astronomy Purdue University West LafayetteIN47907 United States School of Electrical and Computer Engineering Purdue University West LafayetteIN47907 United States Purdue Quantum Center Purdue University West LafayetteIN47907 United States

We report a systematic plasmonic study of twisted bilayer graphene (TBLG) – two graphene layers stacked with a twist angle. Through real-space nanoimaging of TBLG single crystals with a wide distribution of twist angles, we find that TBLG supports confined infrared plasmons that are sensitively dependent on the twist angle. At small twist angles, TBLG has a plasmon wavelength comparable to that of single-layer graphene (SLG). At larger twist angles, the plasmon wavelength of TBLG increases significantly with apparently lower damping. Further analysis and modeling indicate that the observed twist-angle-dependence of TBLG plasmons in the Dirac linear regime is mainly due to the Fermi-velocity renormalization, a direct consequence of interlayer electronic coupling. Our work unveils the tailored plasmonic characteristics of TBLG and deepens our understanding of the intriguing nano-optical physics in novel van der Waals (vdW) coupled two-dimensional (2D) materials. © 2023, CC BY.

关键词： Plasmonics

来源：评论

学校读者我要写书评

暂无评论

AlScN High Electron Mobility Transistors: Integrating High Piezoelectric, High K Dielectric, and Ferroelectric Functionality

AlScN High Electron Mobility Transistors: Integrating High P...

引用

BiCMOS and Compound Semiconductor Integrated Circuits and Technology Symposium (BCICTS)

作者： Joseph Casamento Kazuki Nomoto Thai-Son Nguyen Hyunjea Lee Chandrasekhar Savant Lei Li Austin Hickman Takuya Maeda Yu-Tsun Shao Jimy Encomendero Ved Gund Timothy Vasen Shamima Afroz Daniel Hannan David A. Muller Huili Grace Xing Debdeep Jena Department of Materials Science and Engineering Cornell University Ithaca NY USA School of Electrical and Computer Engineering Cornell University Ithaca NY USA Kavli Institute at Cornell for Nanoscale Science Cornell University Ithaca NY USA School of Applied and Engineering Physics Cornell University Ithaca New York USA Northrop Grumman Mission Systems Advanced Technology Laboratory Linthicum Maryland USA Department of Physics Cornell University Ithaca New York USA

This paper presents an overview of the promising physical properties of the aluminum scandium nitride (AlScN) ternary alloy system and its integration in radiofrequency heterostructure high electron mobility transistors (RF HEMTs). Specifically, heterostructures with AlScN demonstrate enhanced piezoelectric response and enhanced relative dielectric permittivity, as well as ferroelectric behavior. These promising physical phenomena are manifested in HEMTs that show larger on current densities compared to aluminum gallium nitride (AlGaN) HEMTs and display ferroelectric behavior. An overlook on future improvements in thin film deposition and device fabrication is discussed to fully maximize the potential devices and integrated circuits incorporating AlScN.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Single-source Domain Expansion Network for Cross-Scene Hyperspectral Image Classification

arXiv

引用

arXiv 2022年

作者： Zhang, Yuxiang Li, Wei Sun, Weidong Tao, Ran Du, Qian The School of Information and Electronics Beijing Institute of Technology Beijing Key Laboratory of Fractional Signals and Systems Beijing100081 China Tsinghua University Beijing100084 China The Department of Electrical and Computer Engineering Mississippi State University Mississippi State MS39762 United States

Currently, cross-scene hyperspectral image (HSI) classification has drawn increasing attention. It is necessary to train a model only on source domain (SD) and directly transfering the model to target domain (TD), when TD needs to be processed in real time and cannot be reused for training. Based on the idea of domain generalization, a Single-source Domain Expansion Network (SDEnet) is developed to ensure the reliability and effectiveness of domain extension. The method uses generative adversarial learning to train in SD and test in TD. A generator including semantic encoder and morph encoder is designed to generate the extended domain (ED) based on encoder-randomization-decoder architecture, where spatial and spectral randomization are specifically used to generate variable spatial and spectral information, and the morphological knowledge is implicitly applied as domain invariant information during domain expansion. Furthermore, the supervised contrastive learning is employed in the discriminator to learn class-wise domain invariant representation, which drives intra-class samples of SD and ED. Meanwhile, adversarial training is designed to optimize the generator to drive intra-class samples of SD and ED to be separated. Extensive experiments on two public HSI datasets and one additional multispectral image (MSI) dataset demonstrate the superiority of the proposed method when compared with state-of-the-art techniques. Copyright © 2022, The Authors. All rights reserved.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Distributed identification of power system network branch events

Distributed identification of power system network branch ev...

引用

2020 IEEE Power and Energy Society General Meeting, PESGM 2020

作者： Madurasinghe, Dulip Arunagirinathan, Paranietharan Venayagamoorthy, Ganesh K. Clemson University Real-Time Power and Intelligent Systems Laboratory Holcombe Department of Electrical and Computer Engineering ClemsonSC29634 United States School of Engineering University of Kwazulu-Natal Durban4041 South Africa

ISBN: (纸本)9781728155081

Online identification of power system network branches is critical in modern electric power system operation. Availability of phasor measurement units (PMUs) can be used to identify branch events. Due to complexity of the power system, a distributed cellular computational network (CCN) is proposed. Comparison of centralized and distributed neural network based power system network branch events identification is studied. IEEE 12-bus benchmark power system is simulated on real-time digital simulator platform for this study. CCN based distributed neural network approach is computationally efficient compared to centralized approach. © 2020 IEEE.

关键词： Phasor measurement units

来源：评论

学校读者我要写书评

暂无评论

Enhancing Deep Reinforcement Learning: A Tutorial on Generative Diffusion Models in Network Optimization

arXiv

引用

arXiv 2023年

作者： Du, Hongyang Zhang, Ruichen Liu, Yinqiu Wang, Jiacheng Lin, Yijing Li, Zonghang Niyato, Dusit Kang, Jiawen Xiong, Zehui Cui, Shuguang Ai, Bo Zhou, Haibo Kim, Dong In The School of Computer Science and Engineering The Energy Research Institute @ NTU Interdisciplinary Graduate Program Nanyang Technological University Singapore The School of Computer Science and Engineering Nanyang Technological University Singapore The State Key Laboratory of Networking and Switching Technology Beijing University of Posts and Telecommunications China The School of Information and Communication Engineering University of Electronic Sciences and Technology of China Chengdu China The School of Automation Guangdong University of Technology China The Pillar of Information Systems Technology and Design Singapore University of Technology and Design Singapore Shenzhen China The State Key Laboratory of Rail Traffic Control and Safety Beijing Jiaotong University Beijing100044 China School of Electronic Science and Engineering Nanjing University Jiangsu Nanjing210093 China The Department of Electrical and Computer Engineering Sungkyunkwan University Suwon16419 Korea Republic of

Generative Diffusion Models (GDMs) have emerged as a transformative force in the realm of Generative Artificial Intelligence (GenAI), demonstrating their versatility and efficacy across various applications. The ability to model complex data distributions and generate high-quality samples has made GDMs particularly effective in tasks such as image generation and reinforcement learning. Furthermore, their iterative nature, which involves a series of noise addition and denoising steps, is a powerful and unique approach to learning and generating data. This paper serves as a comprehensive tutorial on applying GDMs in network optimization tasks. We delve into the strengths of GDMs, emphasizing their wide applicability across various domains, such as vision, text, and audio generation. We detail how GDMs can be effectively harnessed to solve complex optimization problems inherent in networks. The paper first provides a basic background of GDMs and their applications in network optimization. This is followed by a series of case studies, showcasing the integration of GDMs with Deep Reinforcement Learning (DRL), incentive mechanism design, Semantic Communications (SemCom), Internet of Vehicles (IoV) networks, etc. These case studies underscore the practicality and efficacy of GDMs in real-world scenarios, offering insights into network design. We conclude with a discussion on potential future directions for GDM research and applications, providing major insights into how they can continue to shape the future of network optimization. © 2023, CC BY.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Large Language Models for Traffic and Transportation Research: Methodologies, State of the Art, and Future Opportunities

arXiv

引用

arXiv 2025年

作者： Yan, Yimo Liao, Yejia Xu, Guanhao Yao, Ruili Fan, Huiying Sun, Jingran Wang, Xia Sprinkle, Jonathan An, Ziyan Ma, Meiyi Cheng, Xi Liu, Tong Ke, Zemian Zou, Bo Barth, Matthew Kuo, Yong-Hong Department of Data and Systems Engineering The University of Hong Kong Hong Kong Department of Civil Materials and Environmental Engineering University of Illinois ChicagoIL United States Department of Electrical Engineering University of California RiversideCA United States Buildings and Transportation Science Division Oak Ridge National Laboratory TN United States University of California RiversideCA United States School of Civil and Environmental Engineering Georgia Institute of Technology GA United States University of Texas AustinTX United States Department of Computer Science Vanderbilt University TN United States Cornell University NY United States Department of Civil and Environmental Engineering University of Illinois Urbana-Champaign IL United States Google Inc. CA United States

The rapid rise of Large Language Models (LLMs) is transforming traffic and transportation research, with significant advancements emerging between the years 2023 and 2025 – a period marked by the inception and swift growth of adopting and adapting LLMs for various traffic and transportation applications. However, despite these significant advancements, a systematic review and synthesis of the existing studies remain lacking. To address this gap, this paper provides a comprehensive review of the methodologies and applications of LLMs in traffic and transportation, highlighting their ability to process unstructured textual data to advance transportation research. We explore key applications, including autonomous driving, travel behavior prediction, and general transportation-related queries, alongside methodologies such as zero- or few-shot learning, prompt engineering, and fine-tuning. Our analysis identifies critical research gaps. From the methodological perspective, many research gaps can be addressed by integrating LLMs with existing tools and refining LLM architectures. From the application perspective, we identify numerous opportunities for LLMs to tackle a variety of traffic and transportation challenges, building upon existing research. By synthesizing these findings, this review not only clarifies the current state of LLM adoption and adaptation in traffic and transportation but also proposes future research directions, paving the way for smarter and more sustainable transportation systems. © 2025, CC BY-NC-SA.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Pseudo Oversampling Based on Feature Transformation and Fuzzy Membership Functions for Imbalanced and Overlapping Data

SSRN

引用

SSRN 2023年

作者： Pan, Tingting Pedrycz, Witold Yang, Jie School of Mathematical Sciences Tiangong University Tianjin Tianjin300387 China Department of Electrical and Computer Engineering University of Alberta AB-Alberta EdmontonT6G 2R3 Canada Systems Research Institute Polish Academy of Sciences Mazowiekie Warsaw00-901 Poland Faculty of Engineering and Natural Sciences Department of Computer Engineering Istinye University Sariyer Istanbul34460 Turkey School of Mathematical Sciences Dalian University of Technology Liaoning Dalian116024 China Key Laboratory for Computational Mathematics and Data Intelligence of Liaoning Province Liaoning Dalian116024 China

The class imbalance in data can lead to significant challenges for classifier learning and has attracted increased attention in the fields of data mining and machine learning. Additionally, the occurrence of class overlap, which is also commonly observed in real-world data, further exacerbates the learning difficulty. In this paper, we propose a novel pseudo oversampling method (POM) for imbalanced and overlapping data. It is motivated by the point that overlapping samples from different classes share the same distribution space, and therefore information underlying in majority (negative) overlapping samples can be extracted and used to generate additional positive samples. To identify negative overlapping samples, a membership function encountered fuzzy logic is defined by taking advantage of both local and global information to quantitatively measure the degree, to which each negative sample is an overlapping sample. Then the identified negative overlapping samples are transformed by a transformation matrix that carries the distribution information of all negative samples and shifted to the positive sample region with the center of positive samples. POM is compared with 15 commonly used methods on 14 open-access datasets and experimental results show its superior performance in terms of metrics of Gm, F1 and AUC. © 2023, The Authors. All rights reserved.

关键词： Membership functions

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：