检索结果-内蒙古大学图书馆

11th International Conference on Image and Graphics, ICIG 2021

作者： Zhang, Haitao Shi, Yucheng Dong, Benyu Han, Yahong Li, Yuanzhang Kuang, Xiaohui College of Intelligence and Computing and Tianjin Key Lab of Machine Learning Tianjin University Tianjin China Beijing Institute of Technology Beijing China National Key Laboratory of Science and Technology on Information System Security Beijing China

ISBN: (纸本)9783030873578

Due to the existence of adversarial attacks, various applications that employ deep neural networks (DNNs) have been under threat. Adversarial training enhances robustness of DNN-based systems by augmenting training data with adversarial samples. Projected gradient descent adversarial training (PGD AT), one of the promising defense methods, can resist strong attacks. We propose "free" adversarial training with layerwise heuristic learning (LHFAT) to remedy these problems. To reduce heavy computation cost, we couple model parameter updating with projected gradient descent (PGD) adversarial example updating while retraining the same mini-batch of data, where we "free" and unburden extra updates. Learning rate reflects weight updating speed. Weight gradient indicates weight updating efficiency. If weights are frequently updated towards opposite directions in one training epoch, then there are redundant updates. For higher level of weight updating efficiency, we design a new learning scheme, layerwise heuristic learning, which accelerates training convergence by restraining redundant weight updating and boosting efficient weight updating of layers according to weight gradient information. We demonstrate that LHFAT yields better defense performance on CIFAR-10 with approximately 8% GPU training time of PGD AT and LHFAT is also validated on ImageNet. We have released the code for our proposed method LHFAT at https://***/anonymous530/LHFAT. © 2021, Springer Nature Switzerland AG.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Applications of Multi-Agent Deep Reinforcement Learning with Communication in Network Management: A Survey

arXiv

引用

arXiv 2024年

作者： Pi, Yue Zhang, Wang Zhang, Yong Huang, Hairong Rao, Baoquan Ding, Yulong Yang, Shuanghua 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 Shenzhen China Peng Cheng Laboratory Shenzhen China Huawei Technologies Co. Ltd. China Department of Computer Science University of Reading United Kingdom

With the advancement of artificial intelligence technology, the automation of network management, also known as Autonomous Driving Networks (ADN), is gaining widespread attention. The network management has shifted from traditional homogeneity and centralization to heterogeneity and decentralization. Multi-agent deep reinforcement learning (MADRL) allows agents to make decisions based on local observations independently. This approach is in line with the needs of automation and has garnered significant attention from academia and industry. In a distributed environment, information interaction between agents can effectively address the non-stationarity problem of multiple agents and promote cooperation. Therefore, in this survey, we first examined the application of MADRL in network management, including specific application fields such as traffic engineering, wireless network access, power control, and network security. Then, we conducted a detailed analysis of communication behavior between agents, including communication schemes, communication content construction, communication object selection, message processing, and communication constraints. Finally, we discussed the open issues and future research directions of agent communication in MADRL for future network management and ADN applications. Copyright © 2024, The Authors. 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

Fuzzy Safety and Liveness Properties in Linear-time

Fuzzy Safety and Liveness Properties in Linear-time

引用

IEEE International Conference on Software Quality, Reliability and security (QRS)

作者： Fan Shi Zhiqiu Huang Haiyu Pan Yuting Chang Heng Xu College of Computer Science and Technology/College of Software Nanjing University of Aeronautics and Astronautics Nanjing Jiangsu China Key Laboratory for Safety-critical Software Development and Verification Ministry of Industry and Information Technology Nanjing Jiangsu China School of Computer and Information Security/School of Software Guilin University of Electronic Technology Guilin Guangxi China Nokis Solutions and Networks System Technology (Beijing) Co. Ltd. Hangzhou Zhejiang China

ISBN: (数字)9798350365634

ISBN: (纸本)9798350365641

Safety and liveness are fundamental to many system verification paradigms. In contrast to existing approaches for extending safety and liveness properties of fuzzy systems, we first utilize ultrametric to measure the similarity of valuations, traces and properties in a fuzzy Kripke structure (FKS). A distance threshold $\alpha$ is introduced, which is used to define two quantitative extensions of safety and liveness properties, called $\alpha$-safety and $\alpha$-liveness properties. In addition, we provide characterizations of $\alpha$-safety and $\alpha$-liveness properties in terms of Büchi automata. These results will provide the foundation for the verification of fuzzy systems.

关键词： Uncertainty system verification Software algorithms Automata Software quality Safety Software reliability

来源：评论

学校读者我要写书评

暂无评论

Neural Network-Based Safety Optimization Control for Constrained Discrete-Time systems

Neural Network-Based Safety Optimization Control for Constra...

引用

Annual Conference of Industrial Electronics Society

作者： Xueli Wang Shangwei Zhao Ming Yang Xiaoming Wu Xin Wang Shuo Xu Xu Hu Key Laboratory of Computing Power Network and Information Security Shandong Computer Science Center Qilu University of Technology Jinan China Department of Automation Shanghai Jiao Tong University Shanghai China Public Security Bureau of Jinan Jinan China

This paper proposes a constraint-aware safety control approach via adaptive dynamic programming (ADP) to address the control optimization issues for discrete-time systems subjected to state constraints. First, the constrained control framework is established via the primal-dual approach with the modified Lagrangian based on the relaxed barrier function. Herein, the Lagrangian multiplier is designed to achieve the trade-off between optimization performance and state constraints. In addition, the sub optimality of the dual method is built by proving that the dual gap can be arbitrarily small. And the value iteration algorithm is utilized to implement the constraint-aware ADP controller. Furthermore, the weight estimation error is proved to be bounded when the learning rate satisfies a given sufficient condition. Finally, numerical simulation proves the effectiveness and superiority of the proposed method.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Unsupervised Fact-Checking via Recursively Verifying Presuppositions

IEEE Transactions on Audio, Speech and Language Processing

引用

IEEE Transactions on Audio, Speech and Language Processing 2025年 33卷 2189-2199页

作者： Xiucheng Lyu Runcong Zhao Jiazheng Li Bin Liang Min Yang Lin Gui Ruifeng Xu School of Computer Science and Technology Harbin Institute of Technology (Shenzhen) Shenzhen China Guangdong Provincial Key Laboratory of Novel Security Intelligence Technologies Shenzhen China Department of Informatics King’s College London London U.K. Department of Computer Science and Engineering Chinese University of Hong Kong Hong Kong SAR China Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences Shenzhen China Peng Cheng Laboratory Shenzhen China

Presuppositions are implicit assumptions that interlocutors take for granted. Verifying presuppositions is crucial for reasoning-based fact-checking that aims to reason about True or False, but existing pipelines have overlooked it. We first raise this critical issue with the community and propose a system that addresses the generation, verification, and reasoning of presuppositions through a recursive question-answering process. Importantly, our system automatically determines which knowledge entails which presuppositions, making it an unsupervised system for evidence retrieval, fact-checking, and justification production. We conduct a comprehensive experiment on the FEVER, Vitamin C, and FEVEROUS-S datasets. Our system outperforms competitive baselines, including LLM, and achieves state-of-the-art unsupervised performance. We highlight this critical issue to encourage further research on reasoning-based fact-checking.

关键词： Cognition Training Speech processing Pipelines Electronic mail Production Semantics Tree traversal security Reliability

来源：评论

学校读者我要写书评

暂无评论

A Deep Learning-Based Algorithm for Energy and Performance Optimization of Computational Offloading in Mobile Edge Computing

引用

Wireless Communications and Mobile Computing 2023年第1期2023卷

作者： Khan, Israr Raza, Salman Rehman, Waheed Ur Khan, Razaullah Nahida, Kiran Tao, Xiaofeng National Engineering Laboratory for Mobile Network Technologies Beijing University of Posts and Telecommunications Beijing100876 China Department of Computer Science National Textile University Faisalabad Pakistan Department of Computer Science University of Peshawar Peshawar Pakistan Department of Computer Science University of Engineering and Technology Mardan Pakistan Beijing Laboratory of Advanced Information Network Beijing Key Laboratory of Network System Architecture and Convergence Beijing University of Posts and Telecommunications China

Mobile edge computing (MEC) has produced incredible outcomes in the context of computationally intensive mobile applications by offloading computation to a neighboring server to limit the energy usage of user equipment (UE). However, choosing a pool of application components to offload in addition to the volume of data transfer along with the latency in communication is an intricate issue. In this article, we introduce a novel energy-efficient offloading scheme based on deep neural networks. The proposed scheme trains an intelligent decision-making model that picks a robust pool of application components. The selection is based on factors such as the remaining UE battery power, network conditions, the volume of data transfer, required energy by the application components, postponements in communication, and computational load. We have designed the cost function taking all the mentioned factors, get the cost for all conceivable combinations of component offloading decisions, pick the robust decisions over an extensive dataset, and train a deep neural network as a substitute for the exhaustive computations associated. Model outcomes illustrate that our proposed scheme is proficient in the context of accuracy, root mean square error (RMSE), mean absolute error (MAE), and energy usage of UE. © 2023 Israr Khan et al.

关键词： Data transfer

来源：评论

学校读者我要写书评

暂无评论

An Operational Assessment Framework for Near Real-time Cropland Dynamics:Toward Sustainable Cropland Use in Mid-Spine Belt of Beautiful China

Journal of Remote Sensing

引用

Journal of Remote Sensing 2023年第1期3卷 247-263页

作者： Zhenrong Du Le Yu Xin Chen Xiyu Li Dailiang Peng Shijun Zheng Pengyu Hao Jianyu Yang Huadong Guo Peng Gong Department of Earth System Science Ministry of Education Key Laboratory for Earth System ModelingInstitute for Global Change StudiesTsinghua UniversityBeijing 100084China Ministry of Education Ecological Field Station for East Asian Migratory Birds Beijing 100084China Tsinghua University(Department of Earth System Science)-Xi’an Institute of Surveying and Mapping Joint Research Center for Next-Generation Smart Mapping Beijing 100084China Key Laboratory of Digital Earth Science Aerospace Information Research InstituteChinese Academy of SciencesBeijing 100094China International Research Center of Big Data for Sustainable Development Goals Beijing 100094China University of Chinese Academy of Sciences Beijing 100049China Food and Agriculture Organization of the United Nations Viale delle Terme di Caracalla00153 RomeItaly College of Land Science and Technology China Agricultural UniversityBeijing 100193China Department of Geography Department of Earth Sciences and Institute for Climate and Carbon NeutralityUniversity of Hong KongHong Kong 999077China

Cropland monitoring is a crucial component for a broad user community from Land Use and Land Cover Change study to food security policy *** with the rich natural ecological environment and variable agricultural production conditions of Mid-Spine Belt of Beautiful China(MSBBC),this study developed a novel operational assessment framework that combined the near real-time land cover mapping platform(i.e.,FROM-GLC Plus),the FAO Agricultural Stress Index system,and the land degradation monitoring method suggested by United Nations Convention to Combat Desertification for the timely monitoring of cropland extent change,cropland conditions,and cropland *** integrated monitoring system,this framework can provide convenient access to high-spatiotemporalresolution cropland maps(30 m,dekadal)and instant(near real time)cropland *** to the monitoring results,we found that the abnormally high temperatures of summer 2022 adversely affected crop health in the southwest of ***,our results suggested that China’s ecological restoration projects made remarkable achievement in *** productivity of more than 70% of cropland in MSBBC has improved,and only~6% cropland(~3.69×10^(4) km^(2))has degraded since 2000,mainly distributed in cropland with steep slope,insufficient precipitation,and intensive ***-specific measures,such as conservation tillage,improved tillage systems,and cropland ecological projects,should be adopted for sustainable cropland use and further increase in land carrying capacity of MSBBC to achieve balanced east-west development in China.

关键词： Sustainable southwest policy

来源：评论

学校读者我要写书评

暂无评论

Multi-view Contrastive Learning for Medical Question Summarization

Multi-view Contrastive Learning for Medical Question Summari...

引用

International Conference on computer Supported Cooperative Work in Design

作者： Sibo Wei Xueping Peng Hongjiao Guan Lina Geng Ping Jian Hao Wu Wenpeng Lu Ministry of Education Shandong Computer Science Center (National Supercomputer Center in Jinan) Key Laboratory of Computing Power Network and Information Security Qilu University of Technology (Shandong Academy of Sciences) Jinan China Shandong Provincial Key Laboratory of Computer Networks Shandong Fundamental Research Center for Computer Science Jinan China Australian Artificial Intelligence Institute University of Technology Sydney Australia Department of Blood Purification Qilu Hospital of Shandong University Jinan China School of Computer Science and Technology Beijing Institute of Technology Beijing China

ISBN: (数字)9798350349184

ISBN: (纸本)9798350349191

Most Seq2Seq neural model-based medical question summarization (MQS) systems have a severe mismatch between training and inference, i.e., exposure bias. However, this problem remains unexplored in the MQS task. To bridge this research gap and alleviate the problem of exposure bias, we propose a novel re-ranking training framework for MQS called Multi-view Contrastive Learning (MvCL). MvCL simultaneously considers the similarity scores between medical questions and candidate summaries as well as the average similarity scores between candidate summaries and other candidates within the same group, and utilizes contrastive learning to optimize the model’s ranking ability. Additionally, we propose a new multilevel inference approach to adapt to this training strategy. The approach first filters out candidate summaries that are dissimilar to the original medical question, and then selects the summary with the highest average similarity to other candidate summaries from the remaining candidates as the final output. We conducted extensive experiments, and the results demonstrate that our proposed MvCL framework achieves state-of-the-art results on the majority of evaluation metrics across four datasets. 1

关键词： Training Measurement Bridges Adaptation models Limiting Filters Federated learning

来源：评论

学校读者我要写书评

暂无评论

Forensics Forest: Multi-scale Hierarchical Cascade Forest for Detecting GAN-generated Faces

Forensics Forest: Multi-scale Hierarchical Cascade Forest fo...

引用

IEEE International Conference on Multimedia and Expo (ICME)

作者： Jiucui Lu Yuezun Li Jiaran Zhou Bin Li Siwei Lyu Department of Computer Science and Technology Ocean University of China Qingdao China Guangdong Key Laboratory of Intelligent Information Processing Shenzhen Key Laboratory of Media Security Shenzhen University Shenzhen China University at Buffalo State University of New York USA

We describe a simple and effective method called ForensicsForest to detect GAN-generate faces. Instead of using the commonly used CNN models, we describe a novel multi-scale hierarchical cascade forest, which takes semantic and frequency features as input, and hierarchically cascades different levels of features for authenticity prediction. We then propose a multi-scale ensemble, which comprehensively considers different levels of information to improve the performance further. Our method is validated on state-of-the-art GAN-generated face datasets in comparison with several CNN models, which demonstrates the surprising effectiveness of our method in detecting GAN-generated faces.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Video key concept extraction using Convolution Neural Network

Video key concept extraction using Convolution Neural Networ...

引用

AI in Cybersecurity (ICAIC), International Conference on

作者： Tanvir H Sardar Ruhul Amin Hazarika Bishwajeet Pandey Guru Prasad M S Sk Mahmudul Hassan Radhakrishna Dodmane Hardik Gohel Dept. of Computer Science & Engg School of Technology (GST) GITAM University Bengaluru India Department of Information Technology Manipal Institute of Technology Bengaluru India Department of Intelligent System and Cyber Security Astana IT University Kazakhstan Dept. of Computer Science & Engg. Graphic Era (Deemed to be University) Dehradun India School of Computer Science and Engineering VIT-AP India Department of Computer Science & Engg. NMAM Institute of Technology Nitte India Department of CSE University of Houston Victoria USA

Objectives: This work aims to develop an automated video summarising methodology and timestamping that uses natural language processing (NLP) tools to extract significant video ***: The methodology comprises extracting the audio from the video, splitting it into chunks by the size of the pauses, and transcribing the audio using Google's speech recognition. The transcribed text is tokenised to create a summary, sentence and word frequencies are calculated, and the most relevant sentences are selected. The summary quality is assessed using ROUGE criteria, and the most important keywords are extracted from the transcript using ***: Our proposed method successfully extracts key points from video lectures and creates text summaries. Timestamping these key points provides valuable context and facilitates navigation within the lecture. Our method combines video-to-text conversion and text summarisation with timestamping key concepts, offering a novel approach to video lecture analysis. Existing video analysis methods focus on keyword extraction or summarisation, while our method offers a more comprehensive approach. Our timestamped key points provide a unique feature compared to other methods. Our method enhances existing video reports by (i) providing concise summaries of key concepts and (ii) enabling quick access to specific information through timestamps. (iii) Facilitating information retrieval through a searchable index. Further research directions: (i) Improve the accuracy of the multi-stage processing pipeline. (ii) Develop techniques to handle diverse accents and pronunciations. (iii) Explore applications of the proposed method to other video genres and ***/Improvements: This approach is practical in giving accurate video summaries, saving viewers time and effort when comprehending the main concepts presented in a video.

关键词：

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：