检索结果-内蒙古大学图书馆

Investigating Bi-level optimization for learning and vision from a unified perspective: A survey and beyond

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Liu, Risheng Gao, Jiaxin Zhang, Jin Meng, Deyu Lin, Zhouchen DUT-RU International School of Information Science & Engineering Dalian University of Technology Key Laboratory for Ubiquitous Network Service Software of Liaoning Province Dalian116024 China Department of Mathematics Southern University of Science and Technology National Center for Applied Mathematics Shenzhen China School of Mathematics and Statistics Ministry of Education Key Lab of Intelligent Networks and Network Security Xi’an Jiaotong University Xi’an Shaanxi China School of Electronics Engineering and Computer Science Peking University Beijing100871 China Cooperative Medianet Innovation Center Shanghai Jiao Tong University Shanghai200240 China

Bi-Level Optimization (BLO) is originated from the area of economic game theory and then introduced into the optimization community. BLO is able to handle problems with a hierarchical structure, involving two levels of optimization tasks, where one task is nested inside the other. In machine learning and computer vision fields, despite the different motivations and mechanisms, a lot of complex problems, such as hyper-parameter optimization, multi-task and meta learning, neural architecture search, adversarial learning and deep reinforcement learning, actually all contain a series of closely related subproblms. In this paper, we first uniformly express these complex learning and vision problems from the perspective of BLO. Then we construct a best-response-based single-level reformulation and establish a unified algorithmic framework to understand and formulate mainstream gradient-based BLO methodologies, covering aspects ranging from fundamental automatic differentiation schemes to various accelerations, simplifications, extensions and their convergence and complexity properties. Last but not least, we discuss the potentials of our unified BLO framework for designing new algorithms and point out some promising directions for future research. © 2021, CC BY.

关键词： Deep learning

Vision Inspection of Bottle Caps in Drink Factories Using Convolutional Neural Networks 15

学校读者我要写书评

暂无评论

Vision Inspection of Bottle Caps in Drink Factories Using Co...

15th IEEE International Conference on Intelligent computer Communication and Processing, ICCP 2019

作者： Bahaghighat, Mahdi Abedini, Fereshteh S'Hoyan, Misak Molnar, Arthur-Jozsef Raja University Department of Electrical Engineering Qazvin Iran Amirkabir University of Technology Department of Electrical Engineering Tehran Iran National Polytechnic University of Armenia Department of Information Security Yerevan Iran Babeş-Bolyai University Faculty of Mathematics and Computer Science Cluj-Napoca Romania

ISBN: (纸本)9781728149141

Nowadays, the growth and development of artificial intelligence is more evident than any other time. Consequently, the development of machine vision systems in the industry has been studied extensively. The provision of a high-level quality control system based on vision inspection in production lines is an important issue. It not only can increase the efficiency, but also derives the necessary tools to gather information about technical errors and faults in the target system. In this paper, we focus on the vision inspection of bottle caps in drink factories using convolutional neural networks. There are different cap encapsulation statuses which are classified as Normal Cap, Unfixed Cap, and No Cap. According to these classes, we can make a decision between either acceptance or rejection of a given bottle. Achieved results show that our optimized fine-tuning method based on the VGG-19 as an End-to-End deep learning approach can lead to more than 99% accuracy. © 2019 IEEE.

关键词： Bottles

Fourier-reflexive partitions induced by poset metric

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Xu, Yang Kan, Haibin Han, Guangyue Shanghai Key Laboratory of Intelligent Information Processing School of Computer Science Fudan University Shanghai200433 China Department of Mathematics Faculty of Science The University of Hong Kong Pokfulam Road Hong Kong Hong Kong Fudan-Zhongan Joint Laboratory of Blockchain and Information Security Shanghai Engineering Research Center of Blockchain Fudan University Shanghai200433 China

Let H be the cartesian product of a family of finite abelian groups indexed by a finite set Ω. A given poset (i.e., partially ordered set) P = (Ω ≤ P) gives rise to a poset metric on H, which further leads to a partition Q(H,P) of H. We prove that if Q(H,P) is Fourier-reflexive, then its dual partition Λ coincides with the partition of H induced by P, the dual poset of P, and moreover, P is necessarily hierarchical. This result establishes a conjecture proposed by Gluesing-Luerssen in [4]. We also show that with some other assumptions, Λ is finer than the partition of H induced by P. In addition, we give some necessary and sufficient conditions for P to be hierarchical, and for the case that P is hierarchical, we give an explicit criterion for determining whether two codewords in H belong to the same block of Λ. We prove these results by relating the involved partitions with certain family of polynomials, a generalized version of which is also proposed and studied to generalize the aforementioned results. © 2021, CC BY.

关键词： Group theory

Amateur Drones Detection: A machine learning approach utilizing the acoustic signals in the presence of strong interference

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Uddin, Zahoor Altaf, Muhammad Bilal, Muhammad Nkenyereye, Lewis Bashir, Ali Kashif COMSATS University Islamabad Wah Campus Pakistan Div. of Computer and Electronics Systems Engineering Hankuk University of Foreign Studies Yongin-si17035 Korea Republic of Department of Computer and Information Security Sejong University Seoul Korea Republic of Department of Computing and Mathematics Manchester Metropolitan University United Kingdom

MSC Codes 68T45, 68T10, 62H30,Owing to small size, sensing capabilities and autonomous nature, the Unmanned Air Vehicles (UAVs) have enormous applications in various areas e.g., remote sensing, navigation, archaeology, journalism, environmental science, and agriculture. However, the un-monitored deployment of UAVs called the amateur drones (AmDr) can lead to serious security threats and risk to human life and infrastructure. Therefore, timely detection of the AmDr is essential for the protection and security of sensitive organizations, human life and other vital infrastructure. AmDrs can be detected using different techniques based on sound, video, thermal, and radio frequencies. However, the performance of these techniques is limited in Copyright © 2020, The Authors. All rights reserved.

关键词： Aircraft detection

DynaComm: Accelerating distributed CNN training between edges and clouds through dynamic communication scheduling

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Cai, Shangming Wang, Dongsheng Wang, Haixia Lyu, Yongqiang Xu, Guangquan Zheng, Xi Vasilakos, Athanasios V. Department of Computer Science and Technology Tsinghua University Beijing100084 China Beijing National Research Center for Information Science and Technology Tsinghua University Beijing100084 China Cyberspace Security Research Center Peng Cheng Laboratory Shenzhen518066 China Big Data School Qingdao Huanghai University Qingdao266427 China College of Intelligence and Computing Tianjin University Tianjin300350 China Department of Computing Macquarie University SydneyNSW2109 Australia College of Mathematics and Computer Science Fuzhou University Fuzhou350116 China School of Electrical and Data Engineering University of Technology Sydney Australia Department of Computer Science Electrical and Space Engineering Lulea University of Technology Lulea97187 Sweden

To reduce uploading bandwidth and address privacy concerns, deep learning at the network edge has been an emerging topic. Typically, edge devices collaboratively train a shared model using real-time generated data through the Parameter Server framework. Although all the edge devices can share the computing workloads, the distributed training processes over edge networks are still time-consuming due to the parameters and gradients transmission procedures between parameter servers and edge devices. Focusing on accelerating distributed Convolutional Neural Networks (CNNs) training at the network edge, we present DynaComm, a novel scheduler that dynamically decomposes each transmission procedure into several segments to achieve optimal layer-wise communications and computations overlapping during run-time. Through experiments, we verify that DynaComm manages to achieve optimal layer-wise scheduling for all cases compared to competing strategies while the model accuracy remains untouched. Copyright © 2021, The Authors. All rights reserved.

关键词： Edge computing

The Battery Capacity of Energy-storing Quantum Systems

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Yang, Xue Yang, Yan-Han Alimuddin, Mir Salvia, Raffaele Fei, Shao-Ming Zhao, Li-Ming Nimmrichter, Stefan Luo, Ming-Xing The School of Information Science and Technology Southwest Jiaotong University Chengdu610031 China School of Computer and Network Security Chengdu University of Technology Chengdu610059 China Department of Physics of Complex Systems S. N. Bose National Center for Basic Sciences Kolkata700106 India Scuola Normale Superiore PisaI-56127 Italy School of Mathematical Sciences Capital Normal University Beijing100048 China Max-Planck-Institute for Mathematics in the Sciences Leipzig04103 Germany Naturwissenschaftlich-Technische Fakultät Universität Siegen Siegen57068 Germany CAS Center for Excellence in Quantum Information and Quantum Physics Hefei230026 China Shenzhen Institute for Quantum Science and Engineering Southern University of Science and Technology Shenzhen518055 China

The quantum battery capacity is introduced in this letter as a figure of merit that expresses the potential of a quantum system to store and supply energy. It is defined as the difference between the highest and the lowest energy that can be reached by means of the unitary evolution of the system. This function is closely connected to the ergotropy, but it does not depend on the temporary level of energy of the system. The capacity of a quantum battery can be directly linked with the entropy of the battery state, as well as with measures of coherence and entanglement. © 2023, CC BY.

关键词： Quantum optics

Accelerating NATO Transformation with SnTEE: Experiments with Network security Function Virtualization in Coalition Networks

学校读者我要写书评

暂无评论

Accelerating NATO Transformation with SnTEE: Experiments wit...

International Conference on Military Communications and Information Systems (ICMCIS)

作者： Roberto Rigolin F. Lopes Johannes F. Loevenich Konrad Wrona Paulo H. L. Rettore Jerry Falkcrona Joseph Mathews Nils Nordbotten Bogdan Vasilache Thorsten Lampe Olwen L. Worthington Juha Röning Secure Communications & Information (SIX) Thales Deutschland Ditzingen Germany Department of Mathematics/Computer Science University of Osnabrück Osnabrück Germany NATO Cyber Security Centre The Hague Netherlands Military University of Technology Warsaw Poland Communication Systems (KOM) Fraunhofer FKIE Bonn Germany Cyber Defence and C2 Technology Swedish Defence Research Agency Linköping Sweden Information Technology Division U.S. Naval Research Laboratory Washington DC USA Thales Norway Oslo Norway WonderBit B.V. Almere The Netherlands Defence Science and Technology Laboratory (Dstl) UK Ministry of Defence London United Kingdom Information Technology and Electrical Engineering University of Oulu Oulu Finland

This paper introduces a virtual laboratory for experiments with cybersecurity functions in coalition networks. The motivation comes from the NATO Allied Command Transformation (ACT) initiative on Science and Technology Experimentation Environment (SnTEE), which supports the transfer of scientific and technical activities carried out by the NATO Science and Technology Organization (STO) research task groups towards NATO operations. The goal of the experiments reported in this paper is to emulate a network topology inspired by Protected Core Networking (PCN), which defines two interfaces. One interface between two protected core segments, from different nations, and another interface between a protected core segment and a colored cloud within a particular nation. The experiments are intended to support the investigation performed by the STO IST-196 RTG on Cyber security in Virtualized Networks. In particular, the starting hypothesis of IST-196 is that security function virtualization can support/speedup PCN topology changes when links are added/removed. We define our experimental setup as Infrastructure as Code (IaC) and introduce experiments that emulate topology changes. We also sketch a solution for the deployment of two chains of virtualized cybersecurity functions at lower protocol layers (physical and IP) and at higher protocol layers (transport and application). This paper also lists future experiments for the NATO SnTEE lab, namely risk-aware routing, cross-layer enforcement of policies, information exchange functions, and federate monitoring and detection of cyber incidents/attacks.

关键词：

学校读者我要写书评

暂无评论

反向连边在大型分层网络中的影响（英文）

engineering 2024年第5期 240-249页

作者：曹浩森胡斌斌莫小雨陈都鑫高建喜袁烨陈关荣 Tamás Vicsek 管晓宏张海涛 MOE Engineering Research Center of Autonomous Intelligent Unmanned Systems State Key Laboratory of Intelligent Manufacturing Equipment and Technology School of Artificial Intelligence and Automation Huazhong University of Science and Technology School of Mechanical and Aerospace Engineering Nanyang Technological University Jiangsu Key Laboratory of Networked Collective Intelligence School of Mathematics Southeast University Department of Computer Science Rensselaer Polytechnic Institute Department of Electronic Engineering City University of Hong Kong Department of Biological Physics E?tv?s University MOE Key Laboratory for Intelligent Networks and Network Security School of Automation Science and Engineering Xi'an Jiaotong University

Hierarchical networks are frequently encountered in animal groups, gene networks, and artificial engineering systems such as multiple robots, unmanned vehicle systems, smart grids, wind farm networks,and so forth. The structure of a large directed hierarchical network is often strongly influenced by reverse edges from lower-to higher-level nodes, such as lagging birds' howl in a flock or the opinions of lowerlevel individuals feeding back to higher-level ones in a social group. This study reveals that, for most large-scale real hierarchical networks, the majority of the reverse edges do not affect the synchronization process of the entire network; the synchronization process is influenced only by a small part of these reverse edges along specific paths. More surprisingly, a single effective reverse edge can slow down the synchronization of a huge hierarchical network by over 60%. The effect of such edges depends not on the network size but only on the average in-degree of the involved subnetwork. The overwhelming majority of active reverse edges turn out to have some kind of ‘‘bunchingo effect on the information flows of hierarchical networks, which slows down synchronization processes. This finding refines the current understanding of the role of reverse edges in many natural, social, and engineering hierarchical networks,which might be beneficial for precisely tuning the synchronization rhythms of these networks. Our study also proposes an effective way to attack a hierarchical network by adding a malicious reverse edge to it and provides some guidance for protecting a network by screening out the specific small proportion of vulnerable nodes.

关键词：

An Enhanced Feature Selection Approach based on Mutual Information for Breast Cancer Diagnosis 6

学校读者我要写书评

暂无评论

An Enhanced Feature Selection Approach based on Mutual Infor...

6th International Conference on Image and Signal Processing and their Applications, ISPA 2019

作者： Zemmal, Nawel Azizi, Nabiha Ziani, Amel Benzebouchi, Nacer Eddine Aldwairi, Monther Badji Mokhtar University Labged Laboratory Annaba23000 Algeria Department of Mathematics and Computer Science Mohamed Cherif Messaadia University Souk-Ahras41000 Algeria Lri Laboratory: Information Research Laboratory Computer Science Department Annaba23000 Algeria Jordan University of Science and Technology Department of Network Engineering and Security Irbid22110 Jordan

ISBN: (纸本)9781728131566

Breast cancer is the most feared disease in the female population. Early detection plays an important role to improve prognosis. Mammography is the best examination for the detection of breast cancer. However, in some cases, reading mammograms is difficult for radiologists. For this reason, several researches have been conducted to develop computer Aided Diagnosis tools (CAD) for this disease which aims to interpret mammography images. This paper investigates a new CAD system based on Transductive scheme and Mutual Information for breast abnormalities diagnosis. In the proposed method, a feature vector contains a combination of two features extraction method: Grey Level Co-occurrence Matrix and local Binary Pattern. In the next step, a novel scheme combining Mutual Information and Correlation-based feature selection was applied for selecting the most relevant features. Finally, the classification was achieved using a Transductive Support Vector Machine classifier. The effectiveness of the proposed CAD is examined on the DDSM dataset using classification accuracy, recall and precision. Experimental results demonstrate that the proposed CAD system is clinically significant and can be used to classify the abnormalities of the breast. © 2019 IEEE.

关键词： computer aided diagnosis