检索结果-内蒙古大学图书馆

arXiv 2021年

作者： Bai, Yu Gao, Yang Huang, Heyan School of Computer Science and Technology Beijing Institute of Technology Beijing China. Southeast Academy of Information Technology Fujian China. Beijing Engineering Research Center of High Volume Language Information Processing and Cloud Computing Applications Beijing China

Parallel cross-lingual summarization data is scarce, requiring models to better use the limited available cross-lingual resources. Existing methods to do so often adopt sequenceto- sequence networks with multi-task frameworks. Such approaches apply multiple decoders, each of which is utilized for a specific task. However, these independent decoders share no parameters, hence fail to capture the relationships between the discrete phrases of summaries in different languages, breaking the connections in order to transfer the knowledge of the high-resource languages to lowresource languages. To bridge these connections, we propose a novel Multi-Task framework for Cross-Lingual Abstractive Summarization (MCLAS) in a low-resource setting. Employing one unified decoder to generate the sequential concatenation of monolingual and cross-lingual summaries, MCLAS makes the monolingual summarization task a prerequisite of the cross-lingual summarization (CLS) task. In this way, the shared decoder learns interactions involving alignments and summary patterns across languages, which encourages attaining knowledge transfer. Experiments on two CLS datasets demonstrate that our model significantly outperforms three baseline models in both low-resource and full-dataset scenarios. Moreover, in-depth analysis on the generated summaries and attention heads verifies that interactions are learned well using MCLAS, which benefits the CLS task under limited parallel resources. Copyright © 2021, The Authors. All rights reserved.

关键词： Knowledge management

来源：评论

学校读者我要写书评

暂无评论

PID Control for Aeroengine Based on Sparrow Search Algorithm

PID Control for Aeroengine Based on Sparrow Search Algorithm

引用

Chinese Automation Congress (CAC)

作者： Liang Xu Hao Wang Ying Liu Wei Xue Ningning Li Tianjin Key Laboratory for Control Theory & Applications in Complicated Systems and School of Electrical Engineering and Automation Tianjin University of Technology Tianjin China National Key Laboratory for Complex Systems Simulation Beijing China Beijing Aerospace Propulsion Institute Beijing China

ISBN: (纸本)9781665426480

To address the problem of aeroengine PID parameter optimization and tuning, this work employs the excellent performance of the sparrow search algorithm (SSA) with high convergence accuracy and fast convergence speed to propose a self-tuning PID control method (SSA-PID) for aeroengine parameters. Considering that the oil supply output by the actuator may have a substantial overshoot, the proposed technique adds a penalty mechanism for the overshoot at the output, designs and improves the fitness function weighted by performance indicators, and effectively avoids the possible excessive overshoot and sharp oil supply phenomenon of the engine oil supply. The SSA-PID simulates and verifies the mathematical models of the turbofan engine’ s steady-state operating points on the ground and at high altitudes. The results show that the SSA-PID control method has better parameter tuning and optimization effects, a faster speed step response, and generates a fuel supply that does not have a targe overshoot, thereby proving its effectiveness and feasibility.

关键词： PI control Oils Search problems Mathematical models Steady-state PD control Fuels

来源：评论

学校读者我要写书评

暂无评论

Dynamical relaxation behavior of extended XY chain with gapless phase following a quantum quench

arXiv

引用

arXiv 2023年

作者： Cao, Kaiyuan Hu, Yayun Tong, Peiqing Yang, Guangwen Zhejiang Lab Hangzhou311100 China Department of Physics Institute of Theoretical Physics Nanjing Normal University Nanjing210023 China Jiangsu Key Laboratory for Numerical Simulation of Large Scale Complex Systems Nanjing Normal University Nanjing210023 China Department of Computer Science and Technology Tsinghua University Haidian District Beijing100084 China

We investigate the dynamical relaxation behavior of the two-point correlation in extended XY models with a gapless phase after quenches from various initial states. Specifically, we study the XY chain with gapless phase induced by the additional interactions: Dzyaloshinskii-Moriya interaction and XZY-YZX type of three-site interaction. When quenching from the gapped phase, we observe that the additional interactions have no effect on the relaxation behavior. The relaxation behavior is δCmn(t) ∼ t−3/2 and ∼ t−1/2 for the quench to the commensurate phase and the incommensurate phase, respectively. However, when quenching from the gapless phase, we demonstrate that the scaling behavior of δCmn(t) is changed to ∼ t−1 for the quench to the commensurate phase, and the decay of δCmn(t) follows ∼ t−1 or ∼ t−1/2 for the quench to the incommensurate phase depending on the parameters of pre-quench Hamiltonian. We also establish the dynamical phase diagrams based on the dynamical relaxation behavior of δCmn(t) in the extended XY models. Copyright © 2023, The Authors. All rights reserved.

关键词： Quenching

来源：评论

学校读者我要写书评

暂无评论

Information exchange in public-culture service domain bason on CIEM 20

Information exchange in public-culture service domain bason ...

引用

2020 ACM Turing Celebration Conference - China, ACM TURC 2020

作者： Wang, Yashen Shi, Ge Zhang, Xi China Academy of Electronics and Information Technology of CETC Beijing China Beijing Eng. Res. Ctr. of High Vol. Language Information Processing and Cloud Computing Applications School of Computer Beijing Institute of Technology Beijing China School of Cyberspace Security Beijing University of Posts and Telecommunications Beijing China

ISBN: (纸本)9781450375344

This paper proposes a novel framework for information exchange in public-culture service domain, which leverages: (i) a widely available translation language (i.e., eXtensible Markup Language (XML)), and (ii) a consistent implementation methodology framework provided for within the China Information Exchange Model (CIEM). The evaluation about public-culture effectiveness measurement mission, demonstrates the efficiency of the proposed framework. © 2020 ACM.

关键词： XML

来源：评论

学校读者我要写书评

暂无评论

Efficient Online and Privacy-preserving Medical Pre-diagnosis Based on Growing Learning Vector Quantization

Efficient Online and Privacy-preserving Medical Pre-diagnosi...

引用

International Conference on Advanced Cloud and Big Data (CBD)

作者： Xiao Zheng Qiuyue Zhang Xuan Tang Xiujun Wang Chunlai Du School of Computer Science and Technology Anhui University of Technology Maanshan-Anhui China Institute of Artificial Intelligence Hefei Comprehensive National Science Center Hefei-Anhui China Anhui Engineering Research Center for Intelligent Applications and Security of Industrial Internet Maanshan-Anhui China School of Information Science and Technology North China University of Technology Beijing China

ISBN: (纸本)9798350309720

With more and more people turning to online medical pre-diagnosis systems, it becomes increasingly important to protect patient privacy and enhance the accuracy and efficiency of diagnosis. That is because the ever rapidly growing medical records not only contain a large amount of private information but are often highly unequally distributed (e.g., the number of cases and the rate of increase of covid-19 can be much higher than that of common diseases). However, existing methods are not capable of simultaneously boosting the intensity of privacy protection, and the accuracy and efficiency of diagnosis. In this paper, we propose an online medical pre-diagnosis scheme based on incremental learning vector quantization (called WL-OMPD) to achieve the two objectives at the same time. Specifically, within WL-OMPD, we design an efficient algorithm, Wasserstein-Learning Vector Quantization (W-LVQ), to smartly compress the original medical records into hypothetic samples. Then, we transmit these compressed data to the cloud instead of the original records to offer a more accurate pre-diagnosis. Extensive evaluations of real medical datasets show that the WL-OMPD scheme can improve the imbalance ratio of the data to a certain extent and then the intensity of privacy protection. These results also demonstrate that WL-OMPD substantially boost the accuracy of the classification model and increase diagnostic efficiency at a lower compression rate.

关键词： Privacy Data privacy Vector quantization Turning Explosions Data models Classification algorithms

来源：评论

学校读者我要写书评

暂无评论

Persistent hyperdigraph homology and persistent hyperdigraph Laplacians

arXiv

引用

arXiv 2023年

作者： Chen, Dong Liu, Jian Wu, Jie Wei, Guo-Wei Department of Mathematics Michigan State University MI48824 United States Mathematical Science Research Center Chongqing University of Technology Chongqing400054 China Yanqi Lake Beijing Institute of Mathematical Sciences and Applications Beijing101408 China Department of Electrical and Computer Engineering Michigan State University MI48824 United States Department of Biochemistry and Molecular Biology Michigan State University MI48824 United States

Hypergraphs are useful mathematical models for describing complex relationships among members of a structured graph, while hyperdigraphs serve as a generalization that can encode asymmetric relationships in the data. However, obtaining topological information directly from hyperdigraphs remains a challenge. To address this issue, we introduce hyperdigraph homology in this work. We also propose topological hyperdigraph Laplacians, which can extract both harmonic spectra and non-harmonic spectra from directed and internally organized data. Moreover, we introduce persistent hyperdigraph homology and persistent hyperdigraph Laplacians through filtration, enabling the capture of topological persistence and homotopic shape evolution of directed and structured data across multiple scales. The proposed methods offer new multiscale algebraic topology tools for topological data analysis. © 2023, CC BY.

关键词： Algebra

来源：评论

学校读者我要写书评

暂无评论

Stochastic anderson mixing for nonconvex stochastic optimization 21

Stochastic anderson mixing for nonconvex stochastic optimiza...

引用

Proceedings of the 35th International Conference on Neural Information Processing Systems

作者： Fuchao Wei Chenglong Bao Yang Liu Department of Computer Science and Technology Tsinghua University Yau Mathematical Sciences Center Tsinghua University and Yanqi Lake Beijing Institute of Mathematical Sciences and Applications Department of Computer Science and Technology Tsinghua University and Institute for AI Industry Research Tsinghua University

ISBN: (纸本)9781713845393

Anderson mixing (AM) is an acceleration method for fixed-point iterations. Despite its success and wide usage in scientific computing, the convergence theory of AM remains unclear, and its applications to machine learning problems are not well explored. In this paper, by introducing damped projection and adaptive regularization to the classical AM, we propose a Stochastic Anderson Mixing (SAM) scheme to solve nonconvex stochastic optimization problems. Under mild assumptions, we establish the convergence theory of SAM, including the almost sure convergence to stationary points and the worst-case iteration complexity. Moreover, the complexity bound can be improved when randomly choosing an iterate as the output. To further accelerate the convergence, we incorporate a variance reduction technique into the proposed SAM. We also propose a preconditioned mixing strategy for SAM which can empirically achieve faster convergence or better generalization ability. Finally, we apply the SAM method to train various neural networks including the vanilla CNN, ResNets, WideResNet, ResNeXt, DenseNet and LSTM. Experimental results on image classification and language model demonstrate the advantages of our method.

关键词：

来源：评论

学校读者我要写书评

暂无评论

ERetinex: Event Camera Meets Retinex Theory for Low-Light Image Enhancement

arXiv

引用

arXiv 2025年

作者： Guo, Xuejian Tian, Zhiqiang Wang, Yuehang Li, Siqi Jiang, Yu Du, Shaoyi Gao, Yue the School of Software Engineering Xi’an Jiaotong University Xi’an710049 China the College of Computer Science and Technology Jilin University Changchun130012 China the National Key Laboratory of Human-Machine Hybrid Augmented Intelligence National Engineering Research Center for Visual Information and Applications Institute of Artificial Intelligence and Robotics Xi’an Jiaotong University Xi’an710049 China BNRist THUIBCS KLISS BLBCI School of Software Tsinghua University Beijing100084 China

Low-light image enhancement aims to restore the under-exposure image captured in dark scenarios. Under such scenarios, traditional frame-based cameras may fail to capture the structure and color information due to the exposure time limitation. Event cameras are bio-inspired vision sensors that respond to pixel-wise brightness changes asynchronously. Event cameras’ high dynamic range is pivotal for visual perception in extreme low-light scenarios, surpassing traditional cameras and enabling applications in challenging dark environments. In this paper, inspired by the success of the retinex theory for traditional frame-based low-light image restoration, we introduce the first methods that combine the retinex theory with event cameras and propose a novel retinex-based low-light image restoration framework named ERetinex. Among our contributions, the first is developing a new approach that leverages the high temporal resolution data from event cameras with traditional image information to estimate scene illumination accurately. This method outperforms traditional image-only techniques, especially in low-light environments, by providing more precise lighting information. Additionally, we propose an effective fusion strategy that combines the high dynamic range data from event cameras with the color information of traditional images to enhance image quality. Through this fusion, we can generate clearer and more detail-rich images, maintaining the integrity of visual information even under extreme lighting conditions. The experimental results indicate that our proposed method outperforms state-of-the-art (SOTA) methods, achieving a gain of 1.0613 dB in PSNR while reducing FLOPS by 84.28%. The code is available at https://***/lodew920/ERetinex. © 2025, CC BY.

关键词： Cameras

来源：评论

学校读者我要写书评

暂无评论

Efficient Random Subspace Decision Forests with A Simple Probability Dimensionality Setting Scheme

SSRN

引用

SSRN 2022年

作者： Wang, Quan Wang, Fei Li, Zhongheng Jiang, Peilin Ren, Fuji Nie, Feiping Institute of Artificial Intelligence and Robotics Xi’an Jiaotong University Shaanxi Xi’an710049 China Beijing Key Laboratory of Intelligent Space Robotic Systems Technology and Applications Beijing Institute of Spacecraft System Engineering Beijing100094 China School of Software Engineering Xi’an Jiaotong University Shaanxi Xi’an710049 China School of Computer Science and Engineering University of Electronic Science and Technology of China Sichuan Chengdu611731 China Northwestern Polytechnical University Shaanxi Xi’an710072 China

The random subspace concept is widely used in decision forests. However, there is not a reasonable approach to specify the appropriate number of randomly selected features. Previous random subspace decision forests simply specify the random subspace dimensionality d s to a preset function value such as [log 2 d ] or [√ d ] where d is the number of the total feature dimensions. Actually, this preset value may be a relatively poor choice for high dimensional data sets. In this paper, a novel framework named Efficient Random Subspace decision forest (ERS) is proposed which pays attention to how to set the random subspace dimensionality for each decision tree of decision forests. Specifically, a simple discrete uniform distribution is employed to set with probability the number of randomly selected features for each tree in random subspace decision forests. The proposed Half Range Discrete Uniform distribution-based Varied Dimensionality setting (HRDUVD) method removes the hesitation of how to preset an appropriate d s for different data sets but also results in good enough classification performance along with relatively short running time. Plenty of experiments on public benchmark data sets have demonstrated the effectiveness and the efficiency of the proposed ERS. © 2022, The Authors. All rights reserved.

关键词： Decision trees

来源：评论

学校读者我要写书评

暂无评论

A comprehensive survey of fast graph clustering

引用

Vicinagearth 2024年第1期1卷 1-22页

作者： Xue, Jingjing Xing, Liyin Wang, Yuting Fan, Xinyi Kong, Lingyi Zhang, Qi Nie, Feiping Li, Xuelong School of Artificial Intelligence OPtics and ElectroNics (iOPEN) Northwestern Polytechnical University Xi’an People’s Republic of China Key Laboratory of Intelligent Interaction and Applications (Northwestern Polytechnical University) Ministry of Industry and Information Technology Xi’an People’s Republic of China School of Cybersecurity Northwestern Polytechnical University Xi’an People’s Republic of China School of Computer Science Northwestern Polytechnical University Xi’an People’s Republic of China Institute of Artificial Intelligence (TeleAI) China Telecom Corp Ltd Beijing People’s Republic of China

Graph clustering methods are popular due to their ability to discover clusters with arbitrary shapes. However, with the emergence of large-scale datasets, the efficiency of graph clustering algorithms has become a significant concern. As a result, many researchers have been drawn to the field of fast graph clustering algorithms, leading to rapid and intricate advancements in related research. Nevertheless, there is currently no comprehensive survey available for fast graph clustering algorithms. To address this gap, we review these fast graph clustering models in both single and multi-view fields, categorizing them based on different properties and analyzing their advantages and disadvantages. In the single-view field, the main categories we explore include large graph methods and bipartite graph methods. The former includes graph cut and graph density methods, while the latter includes graph cut, co-clustering, and label transmission methods. For the multi-view field, the main categories also include large graph methods and bipartite graph methods. The former is specifically designed to avoid the eigenvalue decomposition of graph cut models, and the latter focuses on accelerating algorithms by integrating anchor points. Towards the conclusion of this paper, we discuss the challenges and provide several further research directions for fast graph clustering.

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：