检索结果-内蒙古大学图书馆

18th Pacific Rim International Conference on Artificial Intelligence, PRICAI 2021

作者： Ni, Guangsen Zhang, Hongguang Zhao, Jing Xu, Liyang Yang, Wenjing Lan, Long Institute for Quantum Information and State Key Laboratory of High Performance Computing College of Computer National University of Defense Technology Changsha410073 China Systems Engineering Institute AMS Beijing China

ISBN: (纸本)9783030893699

How to learn concepts from few-shot samples remains an open challenge in the deep learning era. The previous meta-learning methods require a large number of annotated samples in the training phase, which still contributes to high manual-labeling costs. In this paper, we propose a unsupervised few-shot learning framework and pointed out that negative queue constructed via randomly sampling contains many false-negative samples (noise), which has negative impacts on the model’s generalized performance especially when only few samples are available. Specially, we propose an Attention-based Noise Filtering (ANF) strategy to make momentum contrastive loss more applicable to few-shot learning scenario. In addition, we also propose a dynamic momentum update method, which can greatly improve the classification accuracy. Our evaluations demonstrate state-of-the-art unsupervised few-shot learning performance, which is comparable to supervised baseline models. © 2021, Springer Nature Switzerland AG.

关键词： computer vision

来源：评论

学校读者我要写书评

暂无评论

Symbolic Verification of Fuzzy Logic Models

Symbolic Verification of Fuzzy Logic Models

引用

IEEE International Conference on Automated Software engineering (ASE)

作者： Siang Zhao Zhongyang Li Zhenbang Chen Ji Wang College of Computer National University of Defense Technology China Key Laboratory of Software Engineering for Complex Systems National University of Defense Technology China State Key Laboratory of High Performance Computing National University of Defense Technology China

Fuzzy logic is widely applied in various applications. However, verifying the correctness of fuzzy logic models can be difficult. This extended abstract presents our ongoing work on verifying fuzzy logic models. We treat a fuzzy logic model as a program and propose a verification method based on symbolic execution for fuzzy logic models. We have developed and implemented the environment models for the common functions and the inference rules in fuzzy logic models. Our preliminary evaluation shows the potential of our verification method.

关键词：

来源：评论

学校读者我要写书评

暂无评论

DL-Chain: Scalable and Stable Blockchain Sharding with high Concurrency via Dual-Layer Consensus

arXiv

引用

arXiv 2024年

作者： Lin, You Li, Mingzhe Wei, Qingsong Liu, Yong Goh, Siow Mong Rick Zhang, Jin The Shenzhen Key Laboratory of Safety and Security for Next Generation of Industrial Internet Department of Computer Science and Engineering Southern University of Science and Technology Shenzhen518055 China The Department of Computer Science and Engineering Southern University of Science and Technology Shenzhen China The Department of Computer Science and Engineering Hong Kong University of Science and Technology Hong Kong The Institute of High Performance Computing A*STAR Singapore Singapore The Shenzhen Key Laboratory of Safety and Security for Next Generation of Industrial Internet Department of Computer Science and Engineering Southern University of Science and Technology Shenzhen518055 China

Sharding enhances blockchain scalability by partitioning nodes into multiple groups for concurrent transaction processing. Configuring a large number of small shards helps improve the transaction concurrency of a sharding system. However, it increases the fraction of malicious nodes within each shard, easily leading to shard corruption and jeopardizing system security. Some existing works have attempted to improve concurrency by reducing the shard size while maintaining security. However, they often require frequent and time-consuming recovery of corrupted shards, leading to severe system stagnation. Also, they usually require network-wide consensus to guarantee security, which limits scalability. To address these issues, we propose DL-Chain, a blockchain sharding system that can securely provide high concurrency with stable and scalable performance. Our core idea is a Dual-Layer architecture and consensus, which consists of numerous smaller proposer shards (PSs) for transaction processing and multiple larger finalizer committees (FCs) for transaction finalization. To avoid system stagnation and thus guarantee stable performance, we ensure PSs’ liveness even if they are corrupted through the cooperation of PSs and FCs, thus eliminating the recovery process of corrupted PSs. To better trade-off security and scalability, we fine-tune the FCs to enable multiple FCs to coexist securely. As a result, DL-Chain allows a larger fraction of malicious nodes in each PS ( Copyright © 2024, The Authors. All rights reserved.

关键词： Blockchain

来源：评论

学校读者我要写书评

暂无评论

Fundus Image Quality Assessment and Enhancement: a Systematic Review

arXiv

引用

arXiv 2025年

作者： Li, Heng Li, Haojin Ou, Mingyang Yu, Xiangyang Zhang, Xiaoqing Niu, Ke Fu, Huazhu Liu, Jiang Research Institute of Trustworthy Autonomous Systems SUSTech Shenzhen China Department of Computer Science and Engineering SUSTech Shenzhen China Center for High Performance Computing and Shenzhen Key Laboratory of Intelligent Bioinformatics Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Shenzhen China Computer School Beijing Information Science and Technology University Beijing China Singapore

As an affordable and convenient eye scan, fundus photography holds the potential for preventing vision impairment, especially in resource-limited regions. However, fundus image degradation is common under intricate imaging environments, impacting following diagnosis and treatment. Consequently, image quality assessment (IQA) and enhancement (IQE) are essential for ensuring the clinical value and reliability of fundus images. While existing reviews offer some overview of this field, a comprehensive analysis of the interplay between IQA and IQE, along with their clinical deployment challenges, is lacking. This paper addresses this gap by providing a thorough review of fundus IQA and IQE algorithms, research advancements, and practical applications. We outline the fundamentals of the fundus photography imaging system and the associated interferences, and then systematically summarize the paradigms in fundus IQA and IQE. Furthermore, we discuss the practical challenges and solutions in deploying IQA and IQE, as well as offer insights into potential future research directions. Copyright © 2025, The Authors. All rights reserved.

关键词： Photography

来源：评论

学校读者我要写书评

暂无评论

SpaceCube GHOST: A Resilient Processor for Low-Power, high-Reliability Space computing

SpaceCube GHOST: A Resilient Processor for Low-Power, High-R...

引用

IEEE Conference on Aerospace

作者： Noah Perryman Nicholas Franconi Gary Crum Christopher Wilson Alan D. George Department of Electrical and Computer Engineering NSF Center for Space High-Performance and Resilient Computing (SHREC) University of Pittsburgh Pittsburgh PA Science Data Processing Branch Code 587 Software Engineering Division NASA Goddard Space Flight Center Greenbelt MD

There is a direct need for high-visibility NASA missions that provide significant scientific impact or have a high mission class using completely radiation-hardened (rad-hard) electronics solutions, to enable artificial intelligence (AI) applications in harsh environments despite severe size, weight, and power (SWaP) constraints. For these missions, where current state-of-the-art solutions are too power-demanding or are incapable of surviving the intended radiation environment, an alternative rad-hard processing architecture that can leverage the control-flow capabilities of scalar processors while also incorporating the hardware-acceleration capabilities of an FPGA is of significant value. Therefore, in this research, we propose a miniaturized (3.5 in. × 3.5 in. form factor) processor card featuring the GR740 quad-core rad-hard processor and the CertusPro-NX-RT radiation-tolerant FPGA, called the SpaceCube GR740 Host for Onboard Science and Telemetry (GHOST) architecture. The card will be designed to conform to the NASA Goddard Space Flight Center (GSFC) CubeSat Card Specification (CS2), which provides a common template to build new 1U CubeSat-sized cards compatible with a variety of other avionics designs. The GR740 features a fault-tolerant quad- processor LEON4FT SPARC V8 integer unit with a 7-stage pipeline and 4×4 KiB instruction and data caches. To extend the capabilities of the GR740, the CertusPro-NX-RT, a low-power radiation-tolerant FPGA, was combined to create a hybrid system architecture, providing the benefits of a programmable logic fabric. The GHOST architecture supports high-reliability, general-purpose processing and system monitoring via the GR740 while simultaneously increasing the AI-based application performance via a combination of the GR740 and CertusPro-NX-RT.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Dynamic recrystallization-induced temperature insensitivity of yield stress in single-crystal Al1.2CrFeCoNi micropillars

引用

Science China(Technological Sciences) 2021年第1期64卷 11-22页

作者： HUANG RuiRui ZHANG Qian ZHANG Xuan LI JianGuo CAO TangQing YAO JiaHao XUE YunFei GAO HuaJian LI XiaoYan Center for Advanced Mechanics and Materials Applied Mechanics LaboratoryDepartment of Engineering MechanicsTsinghua UniversityBeijing 100084China School of Materials Science and Engineering Beijing Institute of TechnologyBeijing 100081China Shenyang National Laboratory for Materials Science Institute of Metal ResearchChinese Academy of SciencesShenyang 110016China School of Mechanical and Aerospace Engineering College of EngineeringNanyang Technological UniversitySingapore 639798Singapore Institute of High Performance Computing A*STARSingapore 138632Singapore

high-entropy alloys, a new class of metallic materials, exhibit excellent mechanical properties at high temperatures. In spite of the worldwide interest, the underlying mechanisms for temperature dependence of mechanical properties of these alloys remain poorly understood. Here, we systemically investigate the mechanical behaviors and properties of Al_(1.2)CrFeCoNi(comprising a body-centered cubic phase) and Al_(0.3)CrFeCoNi(comprising a face-centered cubic phase) single-crystal micropillars with three orientations([100], [110], and [111]) at temperatures varying from 300 to 675 K by using in situ compression of micropillars inside a scanning electron microscope. The results show that the yield stresses of Al_(1.2)CrFeCoNi micropillars are insensitive to temperature changes, and their flow stresses and work hardening rates increase slightly with increasing temperature from 300 to550 K, which differs from the typical temperature dependence of yield/flow stresses in metals and alloys. In contrast,Al_(0.3)CrFeCoNi micropillars exhibit typical thermal softening. Furthermore, it is found that the Al_(1.2)CrFeCoNi micropillars exhibit a transition from homogenous deformation to localized deformation at a critical temperature, while the Al_(0.3)CrFeCoNi micropillars always maintain a well-distributed and fine slip deformation. Detailed transmission electron microscopy analyses reveal that dynamic recrystallization(involving dislocation tangles, and formation of dislocation cell structures and sub-grains)plays a key role in the observed temperature insensitivity of the yield stress and increasing flow stress(and work hardening rate)with increasing temperature in the Al_(1.2)CrFeCoNi micropillars, and that thermally activated dislocation slip leads to thermal softening of the Al_(0.3)CrFeCoNi micropillars. The differences in deformation modes and temperature dependence of the mechanical properties between Al_(1.2)CrFeCoNi and Al_(0.3)CrFeCoNi essentially originate from the d

关键词： high entropy alloy temperature insensitivity dynamic recrystallization micropillar deformation twin

来源：评论

学校读者我要写书评

暂无评论

System size dependent topological zero modes in coupled topolectrical chains

引用

Physical Review B 2022年第7期106卷 075158-075158页

作者： S. M. Rafi-Ul-Islam Zhuo Bin Siu Haydar Sahin Ching Hua Lee Mansoor B. A. Jalil Department of Electrical and Computer Engineering National University of Singapore Singapore 117583 Institute of High Performance Computing Agency for Science Technology and Research Singapore 138632 Department of Physics National University of Singapore Singapore 117551

In this paper, we demonstrate the emergence and disappearance of topological zero modes (TZMs) in a coupled topolectrical (TE) circuit lattice. Specifically, we consider non-Hermitian TE chains in which TZMs do not occur in the individual uncoupled chains, but emerge when these chains are coupled by interchain capacitors. The coupled system hosts TZMs which show size-dependent behaviors and vanish beyond a certain critical size. In addition, the emergence or disappearance of the TZMs in the open boundary condition spectra for a given size of the coupled system can be controlled by modulating the signs of its inverse decay length. Analytically, trivial and nontrivial phases of the coupled system can be distinguished by the differing ranks of their corresponding Laplacian matrix. The TE circuit framework enables the physical detection of the TZMs via electrical impedance measurements. Our work establishes the conditions for inducing TZMs and modulating their behavior in coupled TE chains.

关键词： Skin effect Topological insulators 1-dimensional systems Non-Hermitean systems Bloch wave theory Green's function methods Tight-binding model

来源：评论

学校读者我要写书评

暂无评论

CoChain: high Concurrency Blockchain Sharding via Consensus on Consensus

CoChain: High Concurrency Blockchain Sharding via Consensus ...

引用

IEEE Annual Joint Conference: INFOCOM, IEEE computer and Communications Societies

作者： Mingzhe Li You Lin Jin Zhang Wei Wang Computer Science and Engineering Department Guangdong Provincial Key Laboratory of Brain-Inspired Intelligent Computation Research Institute of Trustworthy Autonomous Systems Southern University of Science and Technology Computer Science and Engineering Department Hong Kong University of Science and Technology Technology and Research Institute of High Performance Computing and Agency for Science Singapore

Sharding is an effective technique to improve the scalability of blockchain. It splits nodes into multiple groups so that they can process transactions in parallel. To achieve higher parallelism and concurrency at large scales, it is desirable to maintain a large number of small shards. However, simply configuring small shards easily results in a higher fraction of malicious nodes inside shards, causing shard corruption and compromising system security. Existing sharding techniques hence demand large shards, at the expense of limited concurrency. To address this limitation, we propose CoChain: a blockchain sharding system that can securely configure small shards for enhanced concurrency. CoChain allows some shards to be corrupted. For security, each shard is monitored by multiple other shards. The latter reach a cross-shard Consensus on the Consensus results of their monitored shard. Once a corrupted shard is found, its subsequent consensus will be taken over by another shard, hence recovering the system. Via Consensus on Consensus, CoChain allows the existence of shards with more fraction of malicious nodes (<2/3) while securing the system, thus reducing the shard size safely. We implement CoChain based on Harmony and conduct extensive experiments. Compared with Harmony, CoChain achieves 35x throughput gain with 6,000+ nodes.

关键词：

来源：评论

学校读者我要写书评

暂无评论

TOWARDS ROBUST NEURAL NETWORKS VIA CLOSE-LOOP CONTROL 9

TOWARDS ROBUST NEURAL NETWORKS VIA CLOSE-LOOP CONTROL

引用

9th International Conference on Learning Representations, ICLR 2021

作者： Chen, Zhuotong Li, Qianxiao Zhang, Zheng Department of Electrical & Computer Engineering University of California Santa BarbaraCA93106 United States Department of Mathematics National University of Singapore Singapore Institute of High Performance Computing A*STAR Singapore

Despite their success in massive engineering applications, deep neural networks are vulnerable to various perturbations due to their black-box nature. Recent study has shown that a deep neural network can misclassify the data even if the input data is perturbed by an imperceptible amount. In this paper, we address the robustness issue of neural networks by a novel close-loop control method from the perspective of dynamic systems. Instead of modifying the parameters in a fixed neural network architecture, a close-loop control process is added to generate control signals adaptively for the perturbed or corrupted data. We connect the robustness of neural networks with optimal control using the geometrical information of underlying data to design the control objective. The detailed analysis shows how the embedding manifolds of state trajectory affect error estimation of the proposed method. Our approach can simultaneously maintain the performance on clean data and improve the robustness against many types of data perturbations. It can also further improve the performance of robustly trained neural networks against different perturbations. To the best of our knowledge, this is the first work that improves the robustness of neural networks with close-loop control. © 2021 ICLR 2021 - 9th International Conference on Learning Representations. All rights reserved.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Transformative effects of ChatGPT on modern education: Emerging Era of AI Chatbots

引用

Internet of Things and Cyber-Physical Systems 2024年第1期4卷 19-23页

作者： Gill, Sukhpal Singh Xu, Minxian Patros, Panos Wu, Huaming Kaur, Rupinder Kaur, Kamalpreet Fuller, Stephanie Singh, Manmeet Arora, Priyansh Parlikad, Ajith Kumar Stankovski, Vlado Abraham, Ajith Ghosh, Soumya K. Lutfiyya, Hanan Kanhere, Salil S. Bahsoon, Rami Rana, Omer Dustdar, Schahram Sakellariou, Rizos Uhlig, Steve Buyya, Rajkumar School of Electronic Engineering and Computer Science Queen Mary University of London London United Kingdom Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Shenzhen China Raygun Performance Monitoring Wellington New Zealand Center for Applied Mathematics Tianjin University Tianjin China Department of Science Kings Education London United Kingdom Cymax Group Technologies BC Canada QM Academy Queen Mary University of London London United Kingdom Jackson School of Geosciences University of Texas at Austin AustinTX United States Centre for Climate Change Research Indian Institute of Tropical Meteorology Pune India Microsoft Hyderabad India Institute for Manufacturing Department of Engineering University of Cambridge Cambridge United Kingdom Faculty of Computer and Information Science University of Ljubljana Ljubljana Slovenia Machine Intelligence Research Labs AuburnWA United States Faculty of Computing and Data Science FLAME University Maharashtra Pune India Department of Computer Science and Engineering Indian Institute of Technology Kharagpur India Department of Computer Science University of Western Ontario London Canada Sydney Australia School of Computer Science University of Birmingham United Kingdom School of Computer Science and Informatics Cardiff University Cardiff United Kingdom Distributed Systems Group Vienna University of Technology Vienna Austria Department of Computer Science University of Manchester Oxford Road Manchester United Kingdom Laboratory School of Computing and Information Systems The University of Melbourne Australia

ChatGPT, an AI-based chatbot, offers coherent and useful replies based on analysis of large volumes of data. In this article, leading academics, scientists, distinguish researchers and engineers discuss the transformative effects of ChatGPT on modern education. This research discusses ChatGPT capabilities and its use in the education sector, identifies potential concerns and challenges. Our preliminary evaluation shows that ChatGPT perform differently in different subject areas including finance, coding, maths, and general public queries. While ChatGPT has the ability to help educators by creating instructional content, offering suggestions and acting as an online educator to learners by answering questions, transforming education through smartphones and IoT gadgets, and promoting group work, there are clear drawbacks in its use, such as the possibility of producing inaccurate or false data and circumventing duplicate content (plagiarism) detectors where originality is essential. The often reported "hallucinations" within GenerativeAI in general, and also relevant for ChatGPT, can render its use of limited benefit where accuracy is essential. What ChatGPT lacks is a stochastic measure to help provide sincere and sensitive communication with its users. Academic regulations and evaluation practices used in educational institutions need to be updated, should ChatGPT be used as a tool in education. To address the transformative effects of ChatGPT on the learning environment, educating teachers and students alike about its capabilities and limitations will be crucial. © 2023 The Authors

关键词： Machine 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：