检索结果-内蒙古大学图书馆

31st International Conference on Computational Linguistics, COLING 2025

作者： Shen, Tiesunlong Wang, Jin Zhang, Xuejie Cambria, Erik School of Information Science and Engineering Yunnan University Kunming China College of Computing and Data Science Nanyang Technological University Singapore

ISBN: (纸本)9798891761964

Recent advancements in large language models (LLMs) have shown remarkable progress in reasoning capabilities, yet they still face challenges in complex, multi-step reasoning tasks. This study introduces Reasoning with Trees (RwT), a novel framework that synergistically integrates LLMs with knowledge graphs (KGs) to enhance reasoning performance and interpretability. RwT reformulates knowledge graph question answering (KGQA) as a discrete decision-making problem, leveraging Monte Carlo Tree Search (MCTS) to iteratively refine reasoning paths. This approach mirrors human-like reasoning by dynamically integrating the LLM's internal knowledge with external KG information. We propose a real-data guided iteration technique to train an evaluation model that assesses action values, improving the efficiency of MCTS. Experimental results on two benchmark KGQA datasets demonstrate that RwT significantly outperforms existing state-of-the-art methods, with an average performance improvement of 9.81%. Notably, RwT achieves these improvements without requiring complete LLM retraining, offering a more efficient and adaptable approach to enhancing LLM reasoning capabilities. © 2025 Association for Computational Linguistics.

关键词： Knowledge graph

来源：评论

学校读者我要写书评

暂无评论

Estimation of Neurological Diseases and Age Using Brain MRI 4th

Estimation of Neurological Diseases and Age Using Brain MRI

引用

4th International Conference on Smart Systems: Innovations in computing, SSIC 2023

作者： Ashokkumar, K. Dharshan, K. Ragupathi, T. Pritam, Anem Sagar, Amujuru Gnana Department of Computer Science Engineering Sathyabama Institute of Science and Technology Chennai India School of Computing and Mathematical Sciences University of Leicester Leicester United Kingdom Data Science and Business systems School of Computing SRM Institute of Science and Science and Technology Kattankulathur Chennai India

ISBN: (纸本)9789819736898

Leveraging D-NN trained on neuroimaging data, we can effectively estimate the chronological ages of normal persons;this projected brain age has potential as a biomarker for identifying age-related disorders. The suggested technique employs a CNN cascade network from DL and the Support Vector Machine (SVM) algorithm from ML (SVM). These techniques have been employed to train MRI scans of the brain, classifying them into regular (unaffected by illness), Alzheimer’s disorder (AD), and neurocognitive disability. That we also have the ability to determine ages thanks to the age classifications on the photos. The brain MRI collection is trained using CNN and SVM, on which the classifications and age estimate will be carried out. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Reactor field reconstruction from sparse and movable sensors using Voronoi tessellation-assisted convolutional neural networks

引用

Nuclear science and Techniques 2024年第5期35卷 173-185页

作者： He-Lin Gong Han Li Dunhui Xiao Sibo Cheng Paris Elite Institute of Technology Shanghai Jiao Tong UniversityShanghai 200240China School of Mathematical Sciences Tongji UniversityShanghai 200092China Department of Computing Data Science InstituteImperial College LondonLondon SW72AZUK

The aging of operational reactors leads to increased mechanical vibrations in the reactor *** vibration of the incore sensors near their nominal locations is a new problem for neutronic field *** field-reconstruction methods fail to handle spatially moving *** this study,we propose a Voronoi tessellation technique in combination with convolutional neural networks to handle this *** from movable in-core sensors were projected onto the same global field structure using Voronoi tessellation,holding the magnitude and location information of the *** convolutional neural networks were used to learn maps from observations to the global *** proposed method reconstructed multi-physics fields(including fast flux,thermal flux,and power rate)using observations from a single field(such as thermal flux).Numerical tests based on the IAEA benchmark demonstrated the potential of the proposed method in practical engineering applications,particularly within an amplitude of 5 cm around the nominal locations,which led to average relative errors below 5% and 10% in the L_(2) and L_(∞)norms,respectively.

关键词： Voronoi tessellation Field reconstruction Nuclear reactors Reactor physics On-line monitoring

来源：评论

学校读者我要写书评

暂无评论

Performance analysis of various classification algorithms for providing competency training to workplace risk prevention

引用

Multimedia Tools and Applications 2025年第15期84卷 15123-15149页

作者： Garg, Shruti Murugan, Prabhu Manimaran, A. Sundar, Ramesh Dakshinamoorthy, Prabakar Rajaram, Gnanajeyaraman Birla Institute of Technology Ranchi Mesra India Department of ECE Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Saveetha University Chennai602105 India Department of Computer Science and Engineering Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Saveetha University Chennai602105 India Department of Networking and Communication School of Computing SRM Institute of Science and Technology SRM Nagar Kattankulathur India Department of Data Science and Business Systems School of Computing SRM Institute of Science and Technology SRM Nagar Kattankulathur India

In the workplace, risk prevention helps detect the risks and prevent accidents. To achieve this, workers' mental and physical parameters related to their health should be focused on and analyzed. It helps improve the workers' mental health and thus improves organizational performance. There are a lot of mental illnesses due to excess work and a lack of professional knowledge. It affects the performance of the worker. So, the organization needs to conduct competency training programs to improve their professional skills and the mindset to tackle the work pressure. There are several competency training programs given in various organizations to mold the workers, and it considerably reduces workplaces risks. Competency training in the workplace teaches integrity, honesty, managerial skills, and other workers. Developing organizational skills is the primary concern in this competency training. This paper enabled one of the best machine learning algorithms to be chosen to predict the hazards in the workplace and provide a healthy environment to the workers. For that, several classification methods such as Logistic Regression, Decision trees, AdaBoost classifier, Random Forest, Gradient Boosting classifier, and XGBoost classifier are implemented experimented with, and the performance is verified with python software. From the comparison, it has been found that the XGBoost classifier is selected as the best classifier and identified that it is highly suitable for analyzing and predicting workplace risks data. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Occupational risks

来源：评论

学校读者我要写书评

暂无评论

End-to-end Compilation is All FPGAs Need: A Unified Overlay-based FPGA Compiler for Deep Learning 25

End-to-end Compilation is All FPGAs Need: A Unified Overlay-...

引用

30th Asia and South Pacific Design Automation Conference, ASP-DAC 2025

作者： Qian, Kai Lu, Haodong Liu, Yinqiu Zhang, Zexu Wang, Kun School of Microelectronics Fudan University China College of Computing and Data Science Nanyang Technological University Singapore

ISBN: (纸本)9798400706356

Field-Programmable Gate Array (FPGA) has shown great application potential in deploying Neural Networks (NNs) due to the characteristics of programmability, low power consumption, etc. However, deploying NNs on FPGA is non-trivial because (1) Mainstream NNs pose significant FPGA architecture design challenges due to their large number of parameters, complex operations, and the need for data optimization, and (2) Supporting the deployment of different machine learning frameworks to FPGA requires significant manual effort, consuming a large amount of time. In this paper, we propose AutoCompiler, a unified compiler for mapping NNs to different FPGAs, along with overlay techniques to enable fast and efficient implementation. To the best of our knowledge, we are the first work to support both Deep Neural Networks (DNNs) and Transformer-based networks for overlay-based FPGA deployment. AutoCompiler comprises three integrated enablers: (1) Model Translator, built on top of a topology-based NNs representation, which can optimize the topology and data representation of the models from an algorithmic level based on different hardware configurations, e.g., DSP utilization, (2) Instruction Generator, which generates pipeline data streams according to various FPGA resource configurations by manipulating the instruction set at the upper level rapidly, and (3) End-to-end optimization, which moves as much of the computational processes as possible onto the FPGA chip and minimizes the interaction between CPU and FPGA. Extensive experiments on various Xilinx FPGAs show that AutoCompiler outperforms state-of-the-art overlay-based compiler by 1.2× - 1.35× and same-level GPUs by 1.15× - 1.59× for classic DNN models, and ViT inference, respectively. © 2025 Copyright is held by the owner/author(s). Publication rights licensed to ACM.

关键词： Program compilers

来源：评论

学校读者我要写书评

暂无评论

A Universal Low-Dimensional Subspace Structure in Beamforming Design: Theory and Applications

引用

IEEE Transactions on Signal Processing 2025年 73卷 1775-1791页

作者： Zhao, Xiaotong Shi, Qingjiang Tongji University School of Computer Science and Technology Shanghai201804 China Shenzhen Research Institute of Big Data Shenzhen518172 China

Beamforming design plays a crucial role in multi-antenna systems, with numerous methods proposed to optimize key performance metrics such as spectral efficiency and power consumption. However, these methods often face two major challenges: high computational complexity and excessive communication overhead in distributed implementations. This paper addresses these challenges by analyzing a general beamforming optimization framework—referred to as the standard-form beam-forming problem—which encompasses various beamforming design tasks. We prove that any positive stationary point of this problem exhibits a low-dimensional subspace (LDS) structure, enabling the development of low-complexity and communication-efficient beamforming algorithms. As an illustrative example, we leverage the LDS structure to propose a computationally efficient beamforming algorithm for weighted sum rate maximization in coordinated multi-cell systems, with provable convergence to stationary points. Furthermore, we decentralize the algorithm for distributed coordinated beamforming, ensuring low interaction costs independent of the number of base station antennas. Notably, the proposed LDS structure is broadly applicable to a wide range of beamforming problems, including integrated sensing and communication (ISAC), intelligent reflecting surfaces (IRS), and beyond. Extensive numerical simulations validate the effectiveness and versatility of our approach, particularly the general applicability of the LDS structure. © 1991-2012 IEEE.

关键词： Multibeam antennas

来源：评论

学校读者我要写书评

暂无评论

An in-depth investigation of sparse rate reduction in transformer-like models 24

An in-depth investigation of sparse rate reduction in transf...

引用

Proceedings of the 38th International Conference on Neural Information Processing Systems

作者： Yunzhe Hu Difan Zou Dong Xu School of Computing and Data Science The University of Hong Kong School of Computing and Data Science & Institute of Data Science The University of Hong Kong

ISBN: (纸本)9798331314385

Deep neural networks have long been criticized for being black-box. To unveil the inner workings of modern neural architectures, a recent work [45] proposed an information-theoretic objective function called Sparse Rate Reduction (SRR) and interpreted its unrolled optimization as a Transformer-like model called Coding Rate Reduction Transformer (CRATE). However, the focus of the study was primarily on the basic implementation, and whether this objective is optimized in practice and its causal relationship to generalization remain elusive. Going beyond this study, we derive different implementations by analyzing layer-wise behaviors of CRATE, both theoretically and empirically. To reveal the predictive power of SRR on generalization, we collect a set of model variants induced by varied implementations and hyperparameters and evaluate SRR as a complexity measure based on its correlation with generalization. Surprisingly, we find out that SRR has a positive correlation coefficient and outperforms other baseline measures, such as path-norm and sharpness-based ones. Furthermore, we show that generalization can be improved using SRR as regularization on benchmark image classification datasets. We hope this paper can shed light on leveraging SRR to design principled models and study their generalization ability.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Accurate and efficient floor localization with scalable spiking graph neural networks

引用

Satellite Navigation 2024年第1期5卷 191-206页

作者： Fuqiang Gu Fangming Guo Fangwen Yu Xianlei Long Chao Chen Kai Liu Xuke Hu Jianga Shang Songtao Guo College of Computer Science Chongqing UniversityChongqingChina Department of Precision Instrument Tsinghua UniversityBeijingChina Institute of Data Science German Aerospace Center(DLR)JenaGermany School of Computer Science China University of GeosciencesWuhanChina

Floor localization is crucial for various applications such as emergency response and rescue,indoor positioning,and recommender *** existing floor localization systems have many drawbacks,like low accuracy,poor scalability,and high computational *** this paper,we first frame the problem of floor localization as one of learning node embeddings to predict the floor label of a ***,we introduce FloorLocator,a deep learning-based method for floor localization that integrates efficient spiking neural networks with powerful graph neural *** approach offers high accuracy,easy scalability to new buildings,and computational *** results on using several public datasets demonstrate that FloorLocator outperforms state-of-the-art ***,in building B0,FloorLocator achieved recognition accuracy of 95.9%,exceeding state-of-the-art methods by at least 10%.In building B1,it reached an accuracy of 82.1%,surpassing the latest methods by at least 4%.These results indicate FloorLocator’s superiority in multi-floor building environment localization.

关键词： Indoor positioning Deep learning Floor localization Spiking neural networks Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

Media Power Measuring via Emotional Contagion

引用

Journal of Social computing 2024年第1期5卷 15-35页

作者： Xue Lin Hong Huang Zongya Li Hai Jin National Engineering Research Center for Big Data Technology and System Services Computing Technology and System LabCluster and Grid Computing LabSchool of Computer Science and TechnologyHuazhong University of Science and TechnologyWuhan 430074China School of Journalism Huazhong University of Science and TechnologyWuhan 430074China

Media power,the impact that media have on public opinion and perspectives,plays a significant role in maintaining internal stability,exerting external influence,and shaping international dynamics for nations/***,prior research has primarily concentrated on news content and reporting time,resulting in limitations in evaluating media *** more accurately assess media power,we use news content,news reporting time,and news emotion simultaneously to explore the emotional contagion between *** use emotional contagion to measure the mutual influence between media and regard the media with greater impact as having stronger media *** propose a framework called Measuring Media Power via Emotional Contagion(MMPEC)to capture emotional contagion among media,enabling a more accurate assessment of media power at the media and national/regional *** also interprets experimental results through correlation and causality analyses,ensuring *** analyses confirm the higher accuracy of MMPEC compared to other baseline models,as demonstrated in the context of COVID-19-related news,yielding compelling and interesting insights.

关键词： explainability media power emotional contagion

来源：评论

学校读者我要写书评

暂无评论

Multilingual Synopses of Movie Narratives: A dataset for Vision-Language Story Understanding

Multilingual Synopses of Movie Narratives: A Dataset for Vis...

引用

2024 Conference on Empirical Methods in Natural Language Processing, EMNLP 2024

作者： Sun, Yidan Yu, Jianfei Li, Boyang College of Computing and Data Science Nanyang Technological University Singapore School of Computer Science and Engineering Nanjing University of Science and Technology China

ISBN: (纸本)9798891761681

Story video-text alignment, a core task in computational story understanding, aims to align video clips with corresponding sentences in their descriptions. However, progress on the task has been held back by the scarcity of manually annotated video-text correspondence and the heavy concentration on English narrations of Hollywood movies. To address these issues, in this paper, we construct a large-scale multilingual video story dataset named Multilingual Synopses of Movie Narratives (M-SYMON), containing 13,166 movie summary videos from 7 languages, as well as manual annotation of fine-grained video-text correspondences for 101.5 hours of video. Training on the human annotated data from M-SYMON outperforms the SOTA methods by 15.7 and 16.2 percentage points on Clip Accuracy and Sentence IoU scores, respectively, demonstrating the effectiveness of the annotations. As benchmarks for future research, we create 6 baseline approaches with different multilingual training strategies, compare their performance in both intra-lingual and cross-lingual setups, exemplifying the challenges of multilingual video-text alignment. The dataset is released at: https://***/insundaycathy/M-SyMoN. © 2024 Association for Computational Linguistics.

关键词： Visual languages

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：