检索结果-内蒙古大学图书馆

11th International Conference on Learning Representations, ICLR 2023

作者： Hu, Jiachen Zhong, Han Jin, Chi Wang, Liwei School of Computer Science Peking University China Center for Data Science Peking University China Department of Electrical and Computer Engineering Princeton University United States National Key Laboratory of General Artificial Intelligence School of Intelligence Science and Technology Peking University Center for Data Science Peking University Beijing Institute of Big Data Research China

Sim-to-real transfer, which trains RL agents in the simulated environments and then deploys them in the real world, has been widely used to overcome the limitations of gathering samples in the real world. Despite the empirical success of the sim-to-real transfer, its theoretical foundation is much less understood. In this paper, we study the sim-to-real transfer in continuous domain with partial observations, where the simulated environments and real-world environments are modeled by linear quadratic Gaussian (LQG) systems. We show that a popular robust adversarial training algorithm is capable of learning a policy from the simulated environment that is competitive to the optimal policy in the real-world environment. To achieve our results, we design a new algorithm for infinite-horizon average-cost LQGs and establish a regret bound that depends on the intrinsic complexity of the model class. Our algorithm crucially relies on a novel history clipping scheme, which might be of independent interest. © 2023 11th International Conference on Learning Representations, ICLR 2023. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Don’t Ignore the Drive of Curiosity: Rethinking Subtleties Between Universality of Commonsense Knowledge and Excellence of Large Language Models

引用

SN computer science 2024年第6期5卷 1-14页

作者： Wang, Chao Chen, Tao Liu, Jingping School of Future Technology Shanghai University Shanghai China Institute of Artificial Intelligence Shanghai University Shanghai China Shanghai Key Laboratory of Data Science School of Computer Science Fudan University Shanghai China School of Information Science and Engineering East China University of Science and Technology Shanghai China

Commonsense reasoning is one of the abilities necessary for artificial intelligence to be as intelligent as humans. However, how to make AI understand commonsense has been a problem that has plagued artificial intelligence for more than 60 years. Existing efforts focus more on the means of knowledge acquisition and strive to enrich the capacity of commonsense knowledge (CSK) bases and dimensions of CSK through advanced methods. Unfortunately, this exuberance has obscured a general consideration of CSK, such as how to follow human habits to obtain the most representative knowledge we need to understand the world. In this paper, this representative knowledge is referred to as core CSK. The influence of core CSK is extensive, and it constitutes almost the fundamental element of human life and the most fundamental cognition of the world. Harnessing human curiosity to find solutions to the above problems is an effective and straightforward route. Specifically, we focus on a special corpus to mine core CSK, namely, why-questions. For example, we can harvest “the sky is blue” from “why is the sky blue?”. To this end, we propose a novel method to extract CSK from why-questions, which mainly consist of two modules. The first is a question classification module used to determine whether a question contains CSK. In this module, we propose a classifier based on a one-sided bootstrapping method and design several informative features for the classifier. The second is a crowdsourcing module used to improve the quality of the extracted commonsense. We conduct extensive experiments, and the experimental results show that our method effectively mines CSK from question corpora. Furthermore, statistical analysis demonstrates the feasibility of this curiosity-driven approach, implying that we provide a basic idea for collecting core CSK. Remarkably, today’s outstanding large language models do not have such simple knowledge summarization capabilities, demonstrating the barrier between

关键词： Classification Core Commonsense knowledge Crowdsourcing Curiosity Psychologically

来源：评论

学校读者我要写书评

暂无评论

A Multi-QoS-Constrained Routing Algorithm for Double-Layer Satellite Networks Based on Enhanced NSGA-II Algorithm

A Multi-QoS-Constrained Routing Algorithm for Double-Layer S...

引用

2024 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2024

作者： Yu, Song Hao, Ning Long, Jun Liu, Limin School of Computer Science and Engineering Central South University Changsha410075 China School of Computer Science at Central South University Changsha410075 China The Big Data Institute Central South University Changsha410083 China

ISBN: (纸本)9781665410205

Addressing the issue of inadequate Quality of Service (QoS) in inter-satellite communication under high load conditions due to limited network resources and uneven user distribution in a double-layer satellite constellation, this paper proposes a routing algorithm that satisfies multiple QoS constraints based on an enhanced NSGA-II algorithm. By utilizing the NSGA-II genetic algorithm, a chromosome path encoding scheme is constructed, treating the multi-QoS constraints of paths as a minimization multi-objective optimization within the NSGA-II algorithm. Moreover, elite solution preservation strategies are fine-tuned to procure a broader and more efficacious optimal Pareto front solution ensemble. This ensures the derivation of optimal pathways that meet multiple Quality of Service (QoS) constraints effectively. Simulation results demonstrate that the proposed algorithm effectively achieves load balancing in satellite network communication. Furthermore, significant improvements are observed in meeting various QoS requirements such as end-to-end latency, latency jitter, packet loss rate, and remaining bandwidth. © 2024 IEEE.

关键词： Satellite communication systems

来源：评论

学校读者我要写书评

暂无评论

Role-based Access and Advanced Encryption Techniques Ensure Cloud data Security in data Deduplication Schemes 7

Role-based Access and Advanced Encryption Techniques Ensure ...

引用

7th International Conference on I-SMAC (IoT in Social, Mobile, Analytics and Cloud), I-SMAC 2023

作者： Swathika, P. Sekar, J. Raja Mepco Schlenk Engineering College Department of Artificial Intelligence and Data Science Tamilnadu Sivakasi India Mepco Schlenk Engineering College Department of Computer Science and Engineering Tamilnadu Sivakasi India

ISBN: (纸本)9798350341485

The proliferation of cloud-based storage solutions has accentuated the need for robust security mechanisms. This research delved into enhancing cloud storage security by intertwining advanced client-side encryption with Role-Based Access Control (RBAC). Empirical evaluations revealed the encryption's consistent ability to produce unique ciphertexts for data, ensuring heightened confidentiality and resilience against unauthorized decryption. Concurrently, RBAC streamlined access controls, dynamically grouping users into predefined roles with associated permissions. Furthermore, our deduplication tests underscored the system's prowess in optimizing storage, significantly reducing redundancy while preserving data integrity. The RBAC system's performance metrics, even under varying loads, confirmed its scalability and efficiency. While the proposed blend of encryption and RBAC demonstrated substantial advancements in ensuring data security and storage efficiency, the results also hint at potential avenues for future refinement and research in the ever-evolving cybersecurity landscape. © 2023 IEEE.

关键词： Cryptography

来源：评论

学校读者我要写书评

暂无评论

An improved branching algorithm for the proper interval edge deletion problem

引用

Frontiers of computer science 2022年第2期16卷 178-180页

作者： Wenjun LI Xiaojing TANG Yongjie YANG School of Computer and Communication Engineering Hunan Provincial Key Laboratory of Intelligent Processing of Big Data on TransportationChangsha University of Science and TechnologyChangsha 410015China School of Computer Science and Engineering Central South UniversityChangsha 410083China

1 Introduction For a graph class G,the G-EDGE DELETION problem is to determine whether a given graph can be transformed into a graph in G by deleting at most k *** G-EDGE DELETION problem for a large body of graph cla... 详细信息

关键词： branching problem transformed

来源：评论

学校读者我要写书评

暂无评论

A Pre-selected Local Weighted Method for Improving the Performance of LMKNN Classifier 6

A Pre-selected Local Weighted Method for Improving the Perfo...

引用

6th IEEE International Conference on Power, Intelligent Computing and Systems, ICPICS 2024

作者： Zhang, Yuzhi Guan, Ziyan Xiong, Chen School of Aeronautic Science and Engineering Beihang University Beijing China School of Big Data & Software Engineering Chongqing University Chongqing China School of Computer Science Xi'an Jiaotong University City College Xi'an China

ISBN: (纸本)9798350374315

The K-nearest neighbor (KNN) algorithm and its variant Local Mean K-nearest neighbor (LMKNN) have been widely used in the field of data mining due to their simplicity and intuition. However, these methods have limitations when dealing with unbalanced datasets and edge samples, such as sensitivity to the choice of nearest neighbor size and degradation of classification performance for outlier points. To address these issues, this paper proposes a pre-selected locally weighted mean K-nearest neighbor (PLWMKNN) algorithm, which aims to improve the performance of LMKNN through an advanced pre-selection mechanism and a weighted average method. PLWMKNN firstly pre-selects favorable classes as the nearest neighbors based on the distance weights, and then computes the weighted center vectors of each class to classify them by the minimum distance principle. Through experimental validation on four real datasets, PLWMKNN shows significant performance improvement over traditional KNN and LMKNN for unbalanced datasets. Our results demonstrate the effectiveness of the PLWMKNN algorithm in improving classification accuracy and robustness, especially when dealing with extremely unbalanced datasets. © 2024 IEEE.

关键词： Nearest neighbor search

来源：评论

学校读者我要写书评

暂无评论

Balancing Usability and Security Innovative Approaches to Privacy in Digital Environments

Balancing Usability and Security Innovative Approaches to Pr...

引用

2024 International Conference on Communication, computer sciences and engineering, IC3SE 2024

作者： Baswaraju, Swathi Yadav, M. Geeta Nijhawan, Ginni Rana, Ajay Rani, T. K. Pushpa Al-Rubaye, Taqi Mohammed Khattab New Horizon College Of Engineering Department Of Computer Science - Data Science Bangalore India Institute Of Aeronautical Engineering Department Of Computer Science And Engineering Telangana Hyderabad India Lovely Professional University Phagwara India Amity School Of Engineering And Technology Amity University Greater Noida India Mlr Institute Of Technology Department Of Computer Science And Engineering Telangana Hyderabad India College Of Medical Technologies The Islamic University Department Of Medical Laboratory Technology Najaf Iraq

ISBN: (纸本)9798350366846

data analysis, private protection, detecting unusual things, identifying people, and transferring data are part of the study's unique security design. The major system method is AUA. Your authentication level depends on your activity, device, and location. Context-aware Privacy uses AUA to tailor user privacy options. Encrypting AES data transfers with Secure data Transfer (SDT) is offered. Machine learning anomaly detection (ADML) analyzes user behavior and implements security measures to uncover vulnerabilities rapidly. DPDA employs controlled noise to make it statistically tougher to identify a person while processing data to safeguard privacy. Ablation study indicates adaptive security design strategies function better together. The recommended design may be safer and easier to employ with visual models and performance testing. With this knowledge, managers may be able to create business-friendly security solutions. Finally, the framework's extensive and adaptable security models boost digital safety. It offers new privacy protection in the internet age. © 2024 IEEE.

关键词： data Analytics

来源：评论

学校读者我要写书评

暂无评论

Priority Based Cyber Incident Handling: Work in Progress 11

Priority Based Cyber Incident Handling: Work in Progress

引用

11th International Conference on Electrical engineering, computer science and Informatics, EECSI 2024

作者： Mulyati Stiawan, Deris Widhiarso, Wijang Budiarto, Rahmat Multi Data Palembang University & Faculty of Engineering Universitas Sriwijaya Department of Information System Palembang Indonesia Sriwijaya University Faculty of Computer Science Palembang Indonesia Multi Data Palembang University Department of Informatics Palembang Indonesia College of Computer Science & IT Albaha University Saudi Arabia

ISBN: (纸本)9798350355314

Effective and efficient cyber incident handling is crucial for maintaining the security of information systems and organizational data. This research aims to develop a priority-based cyber incident handling method by adopting the NIST 2.0 framework and utilizing machine learning classification algorithms. This method enables organizations to quickly and accurately identify and respond to incidents based on threat levels and impact, focusing resources on the most critical incidents. The research employs the Support Vector Machine (SVM) classification algorithm to determine incident priorities. The study is still developing for handling cyber incidents, followed by testing and evaluating the system prototype within organizations. Initial results indicate that the priority-based approach using the SVM classification algorithm achieves a True Positive (TP) Rate of 0.999 and a False Positive (FP) Rate of 0.008, with a correlation of 98.88%, resulting in excellent performance in identifying positive cases and a low error rate. © 2024 IEEE.

关键词： Cyber attacks

来源：评论

学校读者我要写书评

暂无评论

Unified binary and multiclass margin-based classification

The Journal of Machine Learning Research

引用

The Journal of Machine Learning Research 2024年第1期25卷 6810-6860页

作者： Yutong Wang Clayton Scott Department of Electrical Engineering and Computer Science and Michigan Institute of Data Science Department of Electrical Engineering and Computer Science and Department of Statistics University of Michigan Ann Arbor MI

The notion of margin loss has been central to the development and analysis of algorithms for binary classification. To date, however, there remains no consensus as to the analogue of the margin loss for multiclass classification. In this work, we show that a broad range of multiclass loss functions, including many popular ones, can be expressed in the relative margin form, a generalization of the margin form of binary losses. The relative margin form is broadly useful for understanding and analyzing multiclass losses as shown by our prior work (Wang and Scott, 2020, 2021). To further demonstrate the utility of this way of expressing multiclass losses, we use it to extend the seminal result of Bartlett et al. (2006) on classification-calibration of binary margin losses to multiclass. We then analyze the class of Fenchel-Young losses, and expand the set of these losses that are known to be classification-calibrated.

关键词： classification loss functions consistency margins label encodings

来源：评论

学校读者我要写书评

暂无评论

A disk I/O optimized system for concurrent graph processing jobs

引用

Frontiers of computer science 2024年第3期18卷 13-29页

作者： Xianghao XU Fang WANG Hong JIANG Yongli CHENG Dan FENG Peng FANG School of Computer Science and Engineering Nanjing University of Science and TechnologyNanjing 210094China Wuhan National Laboratory for Optoelectronics Huazhong University of Science and TechnologyWuhan 430074China Department of Computer Science&Engineering University of Texas at ArlingtonArlingtonTX 76019USA College of Computer and Data Science Fuzhou UniversityFuzhou 350108China Zhejiang Lab Hangzhou 311121China

In order to analyze and process the large graphs with high cost efficiency,researchers have developed a number of out-of-core graph processing systems in recent years based on just one commodity *** the other hand,with the rapidly growing need of analyzing graphs in the real-world,graph processing systems have to efficiently handle massive concurrent graph processing(CGP)***,due to the inherent design for single graph processing job,existing out-of-core graph processing systems usually incur unnecessary data accesses and severe competition of I/O bandwidth when handling the CGP *** this paper,we propose GraphCP,a disk I/O optimized out-of-core graph processing system that efficiently supports the processing of CGP *** proposes a benefit-aware sharing execution model to share the I/O access and processing of graph data among the CGP jobs and adaptively schedule the graph data loading based on the states of vertices,which efficiently overcomes above challenges faced by existing out-of-core graph processing ***,GraphCP adopts a dependency-based future-vertex updating model so as to reduce disk I/Os in the future *** addition,GraphCP organizes the graph data with a Source-Sorted Sub-Block graph representation for better processing capacity and I/O access *** evaluation results show that GraphCP is 20.5×and 8.9×faster than two out-of-core graph processing systems GridGraph and GraphZ,and 3.5×and 1.7×faster than two state-of-art concurrent graph processing systems Seraph and GraphSO.

关键词： graph processing disk I/O concurrent jobs

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：