检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Zhang, Juan Luo, Junyue Key Laboratory of Intelligent Computing and Information Processing of Ministry of Education Hunan Key Laboratory for Computation and Simulation in Science and Engineering School of Mathematics and Computational Science Xiangtan University Hunan Xiangtan411105 China

In this paper, we apply the practical GADI-HS iteration as a smoother in algebraic multigrid (AMG) method for solving second-order non-selfadjoint elliptic problem. Additionally, we prove the convergence of the derived algorithm and introduce a data-driven parameter learing method called Gaussian process regression (GPR) to predict optimal parameters. Numerical experimental results show that using GPR to predict parameters can save a significant amount of time cost and approach the optimal parameters accurately. © 2024, CC BY.

关键词： Algebra

来源：评论

学校读者我要写书评

暂无评论

Research on Multi-Agent Question Answering Based on Large Language Models 25

Research on Multi-Agent Question Answering Based on Large La...

引用

Proceedings of the 2025 3rd International Conference on Communication Networks and Machine Learning

作者： Xinpeng Lei Fucheng Wan Key Laboratory of Linguistic and Cultural Computing Ministry of Education Northwest Minzu University Lanzhou Gansu China Key Laboratory of Minzu Languages and Cultures Intelligent Information Processing Northwest Minzu University Lanzhou Gansu China

ISBN: (纸本)9798400713231

The continuous development of large language models has led to tremendous performance improvement and has made them increasingly more important. More and more researchers are starting to explore the use of these large language models in developing artificial intelligence agents. The goal of this research is to develop a question-answering system based on a multi-agent setup with the open-source large language model Qwen2.5. In this multi-agent setup, the two agents include a student and a teacher where the student solves issues with guidance from the teacher. We evaluate accuracy difference between a single-agent and a multi-agent setup with the Chinese evaluation data, C-Eval. This is a departure from other approaches like fine-tuning large models or utilizing methods like chain of thought (CoT) and n-shot learning that are tailor-made to improve model performance. Rather, it is a more general approach aimed at further testing the abilities of large language models and thereby improve their logical reasoning capabilities. The experimental results demonstrate a significant improvement in accuracy in multi-agent systems compared to single-agent setup. In particular, improvement in accuracy over various subjects is around 2.5%. In addition, it has been found that improvement is directly proportional to model parameter size; for example, a model with a parameter size of 14 billion has a 22.18% improvement in accuracy for hard cases and reflects a significant improvement in performance.

关键词： Multi-agent

来源：评论

学校读者我要写书评

暂无评论

A NEURAL MULTIGRID SOLVER FOR HELMHOLTZ EQUATIONS WITH HIGH WAVENUMBER AND HETEROGENEOUS MEDIA

arXiv

引用

arXiv 2024年

作者： Cui, Chen Jiang, Kai Shu, Shi Hunan Key Laboratory for Computation and Simulation in Science and Engineering Key Laboratory of Intelligent Computing and Information Processing of Ministry of Education School of Mathematics and Computational Science Xiangtan University Hunan Xiangtan411105 China

Solving high-wavenumber and heterogeneous Helmholtz equations presents a longstanding challenge in scientific computing. In this paper, we introduce a deep learning-enhanced multigrid solver to address this issue. By conducting error analysis on standard multigrid applied to a discrete Helmholtz equation, we devise a strategy to handle errors with different frequencies separately. For error components with frequencies distant from the wavenumber, we perform simple smoothing based on local operations at different levels to eliminate them. On the other hand, to address error components with frequencies near the wavenumber, we utilize another multigrid V-cycle to solve an advection-diffusion-reaction (ADR) equation at a coarse scale. The resulting solver, named Wave-ADR-NS, involves parameters learned through unsupervised training. Numerical results demonstrate that Wave-ADR-NS effectively resolves heterogeneous 2D Helmholtz equation with wavenumber up to 2000. Comparative experiments against classical multigrid preconditioners and existing deep learning-based multigrid preconditioners reveals the superior performance of *** Codes 65N22, 65N55, 68T07 Copyright © 2024, The Authors. All rights reserved.

关键词： Helmholtz equation

来源：评论

学校读者我要写书评

暂无评论

Teaching Early Warning Approach for Teachers based on cognitive Diagnosis and Long Short-term Memory

Teaching Early Warning Approach for Teachers based on Cognit...

引用

International Conference on Computer Supported Cooperative Work in Design

作者： Hua Ma Peiji Huang Xi Luo Qiong Huang Xiangru Fu Wensheng Tang College of Information Science and Engineering Hunan Normal University Changsha China Hunan Provincial Key Laboratory of Intelligent Computing and Language Information Processing Hunan Normal University Changsha China

ISBN: (数字)9798350349184

ISBN: (纸本)9798350349191

Teaching early warning is of great significance for avoiding teaching risks and continuously improving teaching quality. However, none of existing approaches assess the degree of course goals attainment and teacher's teaching quality from the perspective of cognitive diagnosis. This poses a challenge in providing accurate teaching early warning. This paper proposed an early warning approach for teachers based on cognitive diagnosis and long short-term memory (LSTM). First, this approach accurately evaluates students' cognitive status on knowledge concepts using a cognitive diagnosis model to assess their knowledge understanding degree and knowledge application ability. Second, the cognitive status on knowledge concepts is utilized to assess students' attainment degree of course goals and teachers' teaching quality. Third, the teachers' teaching quality is predicted in the future by using the LSTM network to mine students' learning process data, Finally, an accurate teaching early warning is provided to teachers based on a four-level early warning evaluation rule. In experiments, the real datasets are used and the results reveal that the proposed approach can accurately diagnose students' cognitive status and effectively predict teachers' teaching quality. This approach can provide an accurate teaching early warning service for teachers.

关键词： Accuracy Fluctuations Federated learning Computational modeling Education Predictive models Data mining

来源：评论

学校读者我要写书评

暂无评论

A spring pair method of finding saddle points using the minimum energy path as a compass

arXiv

引用

arXiv 2024年

作者： Cui, Gang Jiang, Kai Hunan Key Laboratory for Computation and Simulation in Science and Engineering Key Laboratory of Intelligent Computing and Information Processing Ministry of Education School of Mathematics and Computational Science Xiangtan University Hunan Xiangtan411105 China

Finding index-1 saddle points is crucial for understanding phase transitions. In this work, we propose a simple yet efficient approach, the spring pair method (SPM), to accurately locate saddle points. Without requiring Hessian information, SPM evolves a single pair of spring-coupled particles on the potential energy surface. By cleverly designing complementary drifting and climbing dynamics based on gradient decomposition, the spring pair converges onto the minimum energy path (MEP) and spontaneously aligns its orientation with the MEP tangent, providing a reliable ascent direction for efficient convergence to saddle points. SPM fundamentally differs from traditional surface walking methods, which rely on the eigenvectors of Hessian that may deviate from the MEP tangent, potentially leading to convergence failure or undesired saddle points. The efficiency of SPM for finding saddle points is verified by ample examples, including high-dimensional Lennard-Jones cluster rearrangement and the Landau energy functional involving quasicrystal phase *** Codes 82B26 Copyright © 2024, The Authors. All rights reserved.

关键词： Quantum chemistry

来源：评论

学校读者我要写书评

暂无评论

Few-shot Class-Incremental Semantic Segmentation via Pseudo-Labeling and Knowledge Distillation

arXiv

引用

arXiv 2023年

作者： Jiang, Chengjia Wang, Tao Li, Sien Wang, Jinyang Wang, Shirui Antoniou, Antonios Fujian Provincial Key Laboratory of Information Processing and Intelligent Control Minjiang University Fuzhou China The Key Laboratory of Cognitive Computing and Intelligent Information Processing of Fujian Education Institutions Wuyi University Wuyishan China College of Computer and Data Science Fuzhou University Fuzhou China Department of Computer Science and Engineering European University Cyprus Nicosia Cyprus

We address the problem of learning new classes for semantic segmentation models from few examples, which is challenging because of the following two reasons. Firstly, it is difficult to learn from limited novel data to capture the underlying class distribution. Secondly, it is challenging to retain knowledge for existing classes and to avoid catastrophic forgetting. For learning from limited data, we propose a pseudo-labeling strategy to augment the few-shot training annotations in order to learn novel classes more effectively. Given only one or a few images labeled with the novel classes and a much larger set of unlabeled images, we transfer the knowledge from labeled images to unlabeled images with a coarse-to-fine pseudo-labeling approach in two steps. Specifically, we first match each labeled image to its nearest neighbors in the unlabeled image set at the scene level, in order to obtain images with a similar scene layout. This is followed by obtaining pseudo-labels within this neighborhood by applying classifiers learned on the few-shot annotations. In addition, we use knowledge distillation on both labeled and unlabeled data to retain knowledge on existing classes. We integrate the above steps into a single convolutional neural network with a unified learning objective. Extensive experiments on the Cityscapes and KITTI datasets validate the efficacy of the proposed approach in the self-driving domain. Code is available from https://***/ChasonJiang/FSCILSS. Copyright © 2023, The Authors. All rights reserved.

关键词： Distillation

来源：评论

学校读者我要写书评

暂无评论

Few-Shot Class-Incremental Semantic Segmentation via Pseudo-Labeling and Knowledge Distillation

Few-Shot Class-Incremental Semantic Segmentation via Pseudo-...

引用

information Science, Parallel and Distributed Systems (ISPDS), International Conference on

作者： Chengjia Jiang Tao Wang Sien Li Jinyang Wang Shirui Wang Antonios Antoniou Fujian Provincial Key Laboratory of Information Processing and Intelligent Control Minjiang University Fuzhou China The Key Laboratory of Cognitive Computing and Intelligent Information Processing Fujian Education Institutions Wuyi University Wuyishan China College of Computer and Data Science Fuzhou University Fuzhou China Department of Computer Science and Engineering European University Cyprus Nicosia Cyprus

关键词：

来源：评论

学校读者我要写书评

暂无评论

Suppress Content Shift: Better Diffusion Features via Off-the-Shelf Generation Techniques 38

Suppress Content Shift: Better Diffusion Features via Off-th...

引用

38th Conference on Neural information processing Systems, NeurIPS 2024

作者： Meng, Benyuan Xu, Qianqian Wang, Zitai Yang, Zhiyong Cao, Xiaochun Huang, Qingming Institute of Information Engineering CAS China School of Cyber Security University of Chinese Academy of Sciences China Key Lab. of Intelligent Information Processing Institute of Computing Technology CAS China Peng Cheng Laboratory China School of Computer Science and Tech. University of Chinese Academy of Sciences China School of Cyber Science and Tech. Shenzhen Campus of Sun Yat-sen University China Key Laboratory of Big Data Mining and Knowledge Management CAS China

Diffusion models are powerful generative models, and this capability can also be applied to discrimination. The inner activations of a pre-trained diffusion model can serve as features for discriminative tasks, namely, diffusion feature. We discover that diffusion feature has been hindered by a hidden yet universal phenomenon that we call content shift. To be specific, there are content differences between features and the input image, such as the exact shape of a certain object. We locate the cause of content shift as one inherent characteristic of diffusion models, which suggests the broad existence of this phenomenon in diffusion feature. Further empirical study also indicates that its negative impact is not negligible even when content shift is not visually perceivable. Hence, we propose to suppress content shift to enhance the overall quality of diffusion features. Specifically, content shift is related to the information drift during the process of recovering an image from the noisy input, pointing out the possibility of turning off-the-shelf generation techniques into tools for content shift suppression. We further propose a practical guideline named GATE to efficiently evaluate the potential benefit of a technique and provide an implementation of our methodology. Despite the simplicity, the proposed approach has achieved superior results on various tasks and datasets, validating its potential as a generic booster for diffusion features. Our code is available at this url. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Using Rough Sets to Improve the High-dimensional Data Anomaly Detection Method Based on Extended Isolation Forest 26

Using Rough Sets to Improve the High-dimensional Data Anomal...

引用

26th International Conference on Computer Supported Cooperative Work in Design, CSCWD 2023

作者： Liu, Hanlin Zhou, Jiantao Li, Hua Inner Mongolia University College of Computer Science Hohhot China Natl. Loc. Jt. Eng. Research Center of Intelligent Information Processing Technology for Mongolian Engineering Research Center of Ecological Big Data Ministry of Education Inner Mongolia Engineering Laboratory for Cloud Computing and Service Software Inner Mongolia Key Laboratory of Social Computing and Data Processing Inner Mongolia Key Laboratory of Discipline Inspection and Supervision Big Data Inner Mongolia Engineering Laboratory for Big Data Analysis Technology Hohhot China

ISBN: (纸本)9798350331684

Anomaly detection refers to the identification of data objects that deviate from the general data distribution. One of the important challenges in anomaly detection is handling high-dimensional data, especially when it contains a large number of redundant attributes. Although traditional Isolation Forest (iForest) and Extended Isolation Forest (EIF) have performed well in anomaly detection, the detection accuracy is still extremely influenced by redundant attributes. In this paper, we propose a two-tier architecture named RS-EIF, to alleviate the negative impact of redundant attributes. Specifically, the RS-EIF combines the rough set theory and EIF algorithm and provides an effective basis for the EIF-based anomaly detection method by removing redundant attributes with rough set theory. Experimental results show that the RS-EIF algorithm performs better than the iForest and EIF algorithms in terms of anomaly detection rate, and the results of the combination of rough set theory and EIF are more prominent compared to the other combination methods. © 2023 IEEE.

关键词： Anomaly detection

来源：评论

学校读者我要写书评

暂无评论

TWO-GRID ALGORITHM OF H^(1)-GALERKIN MIXED FINITE ELEMENT METHODS FOR SEMILINEAR PARABOLIC INTEGRO-DIFFERENTIAL EQUATIONS

引用

Journal of Computational Mathematics 2022年第5期40卷 667-685页

作者： Tianliang Hou Chunmei Liu Chunlei Dai Luoping Chen Yin Yang School of Mathematics and Statistics Beihua UniversityJilin 132013China College of Science Hunan University of Science and EngineeringYongzhou 425199China School of Mathematics Southwest Jiaotong UniversityChengdu 611756China Hunan Key Laboratory for Computation and Simulation in Science and Engineering Key Laboratory of Intelligent Computing&Information Processing of Ministry of EducationSchool of Mathematics and Computational ScienceXiangtan UniversityXiangtan 411105China

In this paper,we present a two-grid discretization scheme for semilinear parabolic integro-differential equations by H1-Galerkin mixed finite element *** use the lowest order Raviart-Thomas mixed finite elements and continuous linear finite element for spatial discretization,and backward Euler scheme for temporal ***,a priori error estimates and some superclose properties are ***,a two-grid scheme is presented and its convergence is *** the proposed two-grid scheme,the solution of the nonlinear system on a fine grid is reduced to the solution of the nonlinear system on a much coarser grid and the solution of two symmetric and positive definite linear algebraic equations on the fine grid and the resulting solution still maintains optimal ***,a numerical experiment is implemented to verify theoretical results of the proposed *** theoretical and numerical results show that the two-grid method achieves the same convergence property as the one-grid method with the choice h=H^(2).

关键词： Semilinear parabolic integro-differential equations H^(1)-Galerkin mixed finite element method A priori error estimates Two-grid Superclose.

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：