检索结果-内蒙古大学图书馆

arXiv 2020年

作者： Najt, Lorenzo DeFord, Daryl Solomon, Justin Department of Mathematics University of Wisconsin United States Department of Mathematics and Statistics Washington State University United States Computer Science and Artificial Intelligence Laboratory Massachusetts Institute of Technology United States

The space of connected graph partitions underlies statistical models used as evidence in court cases and reform efforts that analyze political districting plans. In response to the demands of redistricting applications, researchers have developed sampling methods that traverse this space, building on techniques developed for statistical physics. In this paper, we study connections between redistricting and statistical physics, and in particular with self-avoiding walks. We exploit knowledge of phase transitions and asymptotic behavior in self avoiding walks to analyze two questions of crucial importance for Markov Chain Monte Carlo analysis of districting plans. First, we examine mixing times of a popular Glauber dynamics based Markov chain and show how the self-avoiding walk phase transitions interact with mixing time. We examine factors new to the redistricting context that complicate the picture, notably the population balance requirements, connectivity requirements, and the irregular graphs used. Second, we analyze the robustness of the qualitative properties of typical districting plans with respect to score functions and a certain lattice-like graph, called the state-dual graph, that is used as a discretization of geographic regions in most districting analysis. This helps us better understand the complex relationship between typical properties of districting plans and the score functions designed by political districting analysts. We conclude with directions for research at the interface of statistical physics, Markov chains, and political *** Codes 62P25, 82-05 Copyright © 2020, The Authors. All rights reserved.

关键词： Graph theory

来源：评论

学校读者我要写书评

暂无评论

Multi-view learning for vision-and-language navigation

arXiv

引用

arXiv 2020年

作者： Xia, Qiaolin Li, Xiujun Li, Chunyuan Bisk, Yonatan Sui, Zhifang Gao, Jianfeng Smith, Noah A. Choi, Yejin Paul G. Allen School of Computer Science & Engineering University of Washington MOE Key Laboratory of Computational Linguistics Peking University Microsoft Research AI Allen Institute for Artificial Intelligence

Learning to navigate in a visual environment following natural language instructions is a challenging task because natural language instructions are highly variable, ambiguous, and underspecified. In this paper, we present a novel training paradigm, LEARN FROM EVERYONE (LEO), which leverages multiple instructions (as different views) for the same trajectory to resolve language ambiguity and improve generalization. By sharing parameters across instructions, our approach learns more effectively from limited training data and generalizes better in unseen environments. On the recent Room-to-Room (R2R) benchmark dataset, LEO achieves 16% improvement (absolute) over a greedy agent1 (25.3% → 41.4%) in Success Rate weighted by Path Length (SPL). Further, LEO is complementary to most existing models for vision-and-language navigation, allowing for easy integration with the existing techniques, leading to LEO+. It improves generalization on unseen environments when a single instruction is used in testing, and pushes the R2R benchmark to 62% when multiple instruction are used. Copyright © 2020, The Authors. All rights reserved.

关键词： Visual languages

来源：评论

学校读者我要写书评

暂无评论

Investigation of lump, soliton, periodic, kink, and rogue waves to the time-fractional phi-four and (2+1) dimensional CBS equations in mathematical physics

引用

Partial Differential Equations in Applied Mathematics 2021年 4卷

作者： Alam, Lohani Md. Badrul Xingfang, Jiang Mamun, Abdulla - Al Ananna, Samsun Nahar School of Computer Science and Artificial Intelligence Changzhou University Changzhou 213016 China School of Mathematics and Physics Changzhou University Changzhou 213016 China State Key Laboratory of Satellite Ocean Environment Dynamics The Second Institute of Oceanography Hangzhou 310012 China Department of Mathematics College of Science Hohai University Nanjing 210098 China

In this article, we investigate the lump, soliton, periodic, kink, and rogue waves to the time-fractional phi-four and (2+1) dimensional Calogero-Bogoyavlanskil schilf (CBS) equations. The (G′/G,1/G)-expansion technique is applied to obtain the solutions of the phi-four and Calogero-Bogoyavlanskil schilf (CBS) equations with the contribution of conformable derivative. The stated method declines a huge volume of calculation. The (G′/G,1/G)-expansion technique is also known as the two-variable method. Consequently, lump, mixed lump, soliton, bell-shaped soliton, periodic, kink, periodic-kink, singular kink, rogue wave solutions are displayed in hyperbolic and trigonometric function solutions. Varieties of other traveling wave solutions are also formulated with the mentioned method. Moreover, for the physical explanation of the obtained solutions, the three-dimensional (3D) surface plots, contour plots combined with 3D surface plots, and two-dimensional (2D) plots are presented using the computer software MATLAB. Additionally, it is possible to deduce that the obtained solutions and their physical properties will aid in the understanding of water wave circulation in nonlinear dynamics. © 2021 The Authors

关键词： Calogero-Bogoyavlanskil Schilf equation Lump wave Periodic wave Phi-four equation Soliton wave The (G′/G,1/G)-expansion method Traveling wave solution

来源：评论

学校读者我要写书评

暂无评论

COO-DuDo: computation overhead optimization methods for dual-domain sparse-view CT reconstruction

引用

Expert Systems with Applications 2025年 286卷

作者： Deng, Zihan Wang, Zhisheng Shan, Yuanlin He, Guohang Du, Tiantian Wang, Shunli Center of Ultra-Precision Optoelectronic Instrument Engineering Harbin Institute of Technology Harbin150080 China Ministry of Industry and Information Technology Harbin150080 China Artificial Intelligence Media Computing Laboratory School of Computer Science and Technology Harbin Engineering University Harbin150080 China Guangxi Key Laboratory of Multimedia Communications and Network Technology School of Computer Electronic and Information Guangxi University Nanning530000 China Faculty of Education University of Hong Kong Hong Kong

Recently, deep learning methods have shown exciting effects in Sparse-view CT reconstruction. The Dual-Domain (DuDo) deep learning method is one of the representative methods, and it can process the information in both the sinogram and image domains. However, the existing DuDo methods do not pay enough attention to the allocation of training costs and strategies for the two domains, which will result in wasted computing overhead or insufficient training in one of the two domains. In this paper, we propose a Computation-Overhead Optimization (COO) DuDo training strategy for sparse-view CT reconstruction, i.e., COO-DuDo. The training ratio of different domains is controlled by calculating their computation overhead, loss, and gradient variation of the loss. To make our COO-DuDo strategy enable sparse-view CT reconstruction better, we adopt a DuDo-Network (COO-DDNet) structure based on two coding-decoding-type subnetworks. The evaluation, animal and clinical experiments have verified the effectiveness of our training strategies and methods. Our research provides a broader perspective for dual-domain image restoration tasks from the perspective of computational overhead. © 2025 Elsevier Ltd

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

A Domain Adaptation Framework by Aligning the Inverse Gram Matrices for Cross-Subject Motor Imagery Classification

引用

IEEE Transactions on Consumer Electronics 2025年

作者： Fan, Cunhang Yang, Fan Zhang, Jingjing Sun, Jingpeng Che, Hao Hu, Su Wen, Zhengqi Lv, Zhao Anhui University Anhui Province Key Laboratory of Multimodal Cognitive Computation School of Computer Science and Technology Hefei230601 China Anhui University School of Artificial Intelligence Hefei230601 China Migu Culture Technology Co. Ltd Beijing100190 China Tsinghua University Department of Automation Tsinghua University Beijing National Research Center for Information Science and Technology Beijing100190 China

Motor imagery (MI)-based brain-computer interfaces (BCIs) using electroencephalography (EEG) have been widely adopted due to their portability and safety. However, the non-stationary nature of EEG signals introduces significant variability between individuals, making it difficult to directly use data from other subjects (source domain) to decode the intentions of a new subject (target domain). To tackle this issue, this paper proposes a domain adaptation framework by aligning the inverse Gram matrices for cross-subject motor imagery classification (DAIG), which consists of a feature extraction module and the aligns the inverse Gram matrices module. Specifically, in the feature extraction module, EEGBiMamba is proposed to capture the temporal dependencies in one-dimensional EEG time-series representations with a bidirectional (forward and backward) modeling. For the extracted EEG features from both domains, the model aligns their inverse Gram matrices from the perspectives of angle and scale, effectively minimizing the differences in feature distributions. Furthermore, the multilayer perceptron (MLP) layer is replaced with a Kolmogorov-Arnold Network (KAN) to generate an M-dimensional vector for classification, improving the model’s expressiveness and adaptability. The proposed method is evaluated on two public datasets, BCI IV IIa and BCI IV IIb, along with the AMI_MD dataset collected in our laboratory. The results show that the proposed method achieved average cross-subject decoding accuracies of 68.58%, 86.72%, and 81.65% across different datasets, representing remarkable performance improvements of 17.06%, 13.6%, and 15.76% over baseline methods, respectively. © 1975-2011 IEEE.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

CyberEarth: A virtual simulation platform for robotics and cyber-physical systems

CyberEarth: A virtual simulation platform for robotics and c...

引用

2019 IEEE International Conference on Robotics and Biomimetics, ROBIO 2019

作者： Zhang, Xiaoyang Wang, Hongpeng Liu, Jingtai Li, Haifeng Nankai University Tianjin Key Laboratory of Intelligent Robotics College of Artificial Intelligence Tianjin300350 China Civil Aviation University of China Department of Computer Science and Technology Tianjin300300 China

ISBN: (纸本)9781728163215

The increasing sophisticated robot and intelligent system applications require universal visualization platforms which can guarantee the security and efficiency of task process execution in the situation of user-programming and using different kinds of automated equipment. In this paper, we present a universal visualization framework to build up program-driven simulation software of complex robots and intelligent systems by integrating several open-source technical modules, including Ubuntu Linux operation-system, QT Creator IDE environment, ROS robot operation system, OSG(OpenSceneGraph) 3D scene, osgEarth GIS(Geographic Information System)-based 3D scene, and also Python based user-programing robotic script language. Many complex visualization simulation systems of complex tasks in wide area and dynamic scenarios are realized by using this framework. Based on this framework, we built a virtual simulation platform CyberEarth for robotics and Cyber-Physical systems. The typical robotic simulation task, which is a visual coverage task for Multi-Agent/UAV, is also introduced to demonstration the universality of this platform. © 2019 IEEE.

关键词： Intelligent systems

来源：评论

学校读者我要写书评

暂无评论

Multi-label Classification with High-rank and High-order Label Correlations

arXiv

引用

arXiv 2022年

作者： Si, Chongjie Jia, Yuheng Wang, Ran Zhang, Min-Ling Feng, Yanghe Qu, Chongxiao The Chien-Shiung Wu College Southeast University Nanjing210096 China The MoE Key Lab of Artificial Intelligence AI Institute Shanghai Jiao Tong University Shanghai200240 China The School of Computer Science and Engineering Southeast University Nanjing210096 China Ministry of Education China School of Computing & Information Sciences Caritas Institute of Higher Education Hong Kong The Key Laboratory of Computer Network and Information Integration Southeast University Ministry of Education China The School of Mathematical Science Shenzhen University Shenzhen518060 China Shenzhen Key Laboratory of Advanced Machine Learning and Applications Shenzhen University Shenzhen518060 China The College of Systems Engineering National University of Defense Technology China The 52nd Research Institute of China Electronics Technology Group China

Exploiting label correlations is important to multi-label classification. Previous methods capture the high-order label correlations mainly by transforming the label matrix to a latent label space with low-rank matrix factorization. However, the label matrix is generally a full-rank or approximate full-rank matrix, making the low-rank factorization inappropriate. Besides, in the latent space, the label correlations will become implicit. To this end, we propose a simple yet effective method to depict the high-order label correlations explicitly, and at the same time maintain the high-rank of the label matrix. Moreover, we estimate the label correlations and infer model parameters simultaneously via the local geometric structure of the input to achieve mutual enhancement. Comparative studies over twelve benchmark data sets validate the effectiveness of the proposed algorithm in multi-label classification. The exploited high-order label correlations are consistent with common sense empirically. Our code is publicly available at https://***/Chongjie-Si/HOMI. Copyright © 2022, The Authors. All rights reserved.

关键词： Matrix algebra

来源：评论

学校读者我要写书评

暂无评论

Quantum annealing speedup of embedded problems via suppression of Griffiths singularities

引用

Physical Review B 2020年第22期102卷 220407(R)-220407(R)页

作者： Sergey Knysh Eugeniu Plamadeala Davide Venturelli USRA Research Institute for Advanced Computer Science (RIACS) 615 National Ave Mountain View California 94043 USA Quantum Artificial Intelligence Laboratory (QuAIL) NASA Ames Research Center Mail Stop 269-3 Moffett Field California 94035 USA

Optimal parameter settings for application problems embedded into hardware graphs is key to practical quantum annealers (QAs). Embedding chains typically crop up as harmful Griffiths phases but can be used as a resource as we show here: to balance out singularities in the logical problem, changing its universality class. A smart choice of embedding parameters reduces annealing times for random Ising chain from O(exp[cN]) to O(N2). Dramatic reduction in time-to-solution for QAs is confirmed by numerics, for which we developed a custom integrator to overcome convergence issues.

关键词： Adiabatic quantum optimization Quantum phase transitions 1-dimensional spin chains Disordered systems Critical exponents Ising model Numerical approximation & analysis Renormalization group

来源：评论

学校读者我要写书评

暂无评论

Erratum to: CA-DTS: A Distributed and Collaborative Task Scheduling Algorithm for Edge Computing Enabled Intelligent Road Network

引用

Journal of computer science and Technology 2023年第6期38卷 1451-1451页

作者： Hu, Shi-Hong Luo, Qu-Yuan Li, Guang-Hui Shi, Weisong Ye, Bao-Liu Key Laboratory of Water Big Data Technology of Ministry of Water Resources Hohai University Nanjing China School of Computer and Information Hohai University Nanjing China School of Information Science and Technology Southwest Jiaotong University Chengdu China School of Artificial Intelligence and Computer Science Jiangnan University Wuxi China Department of Computer and Information Sciences University of Delaware Newark USA National Key Laboratory for Novel Software Technology Nanjing University Nanjing China

来源：评论

学校读者我要写书评

暂无评论

Clustering with dynamic bipartite graph learning

引用

Neurocomputing 2025年

作者： Yun Liang Wang Gao Qimin Liang Cankun Zhong Feiping Nie South China Agricultural University College of Mathematics and Informatics Guangzhou 510642 Guangdong China Northwestern Polytechnical University School of Artificial Intelligence Optics and Electronics (iOPEN) and the Key Laboratory of Intelligent Interaction and Applications (Ministry of Industry and Information Technology) Xi’an 710072 Shaanxi China Northwestern Polytechnical University School of Computer Science Xi’an 710072 Shaanxi China

Anchor-based bipartite graph clustering algorithms greatly enhance data analysis by accelerating computations without sacrificing performance. However, these methods face two limitations: reliance on fixed bipartite graphs and lack of interaction between the bipartite graph and anchor labels, which reduces adaptability to dynamic data and clustering performance. To overcome these, a novel method, called Clustering with Dynamic Bipartite Graph Learning (DBGL) is proposed. The DBGL objective function is composed of two parts: construct the bipartite graph and learn the anchor labels. The bipartite graph and anchor labels are updated iteratively, resulting in a dynamic bipartite graph that evolves throughout the clustering process. Our dynamic technique is more flexible and performs better on large, complicated datasets than fixed bipartite graph methods. Additionally, we introduce label transmission into DBGL, enabling autonomous interaction between bipartite graph and anchor labels, which mutually guide each other toward optimal clustering results. We design an alternating optimization algorithm where the bipartite graph is updated using an Iteratively Re-Weighted (IRW) algorithm, while the anchor labels are optimized through an improved Coordinate Descent (CD) algorithm. Comprehensive experiments on benchmark datasets demonstrate that DBGL outperforms leading methods in clustering accuracy, efficiency, and robustness, with theoretical analysis confirming its convergence and stability.

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：