检索结果-内蒙古大学图书馆

20th International Joint Conference on Computer Science and Software Engineering, JCSSE 2023

作者： Chanyachatchawan, Sapa Nasingkun, Krich Tumsangthong, Patipat Chata, Porntiwa Buranarach, Marut Socharoentum, Monsak National Electronics and Computer Technology Center Leveraging Technology Solutions Section Bangkok Thailand National Electronics and Computer Technology Center Strategic Analytics Networks with Machine Learning and Ai Research Bangkok Thailand National Electronics and Computer Technology Center Data Science and Analytics Research Group Bangkok Thailand Digital Government Development Agency Bangkok Thailand

ISBN: (纸本)9798350300505

In the current era of extensive data usage across industries, data collection, preservation, utilization, and organization has become more challenging and nuanced because it is necessary to consider critical concerns such as data security, privacy, and legal issues, apart from efficiency issues. As a result, Thai government initiated the idea and effort to implement data governance throughout the government agency. This paper showcases the implementation of data governance in a governmental research organization with highly diverse structured and unstructured data. The implementation follows international standards and the guidelines of the Digital Government Development Agency (DGA). The executives set up the working body, including the Data Governance Council and Data Stewards, responsible for setting up and deploying policies and regulations. Creating awareness and the necessary infrastructure are the main focuses in the first-year phase. The metadata was designed to extend DGA's version and match the organization's unique requirements. A data catalog platform was developed accordingly. We organized activities to boost employee awareness and participation, including advertising and data catalog platform training. By the end of the first year of implementation, every organization unit had registered at least one data record into the data catalog. © 2023 IEEE.

关键词： Metadata

来源：评论

学校读者我要写书评

暂无评论

UGENet: learning Discriminative Embeddings for Unconstrained Gaze Estimation Network via Self-Attention Mechanism in Human-Computer Interaction 24

UGENet: Learning Discriminative Embeddings for Unconstrained...

引用

5th International Conference on Computer Information and Big Data Applications, CIBDA 2024

作者： Liu, Hai Song, Yu Liu, Tingting Ju, Jianping Tang, Jianying School of Information and Artificial Intelligence Nanchang Institute of Science and Technology Nanchang330108 China National Engineering Research Center for E-Learning Central China Normal University Wuhan430079 China

ISBN: (纸本)9798400718106

Gaze estimation plays an important role for indicating the human behavior and intention. It has developed rapidly with the field of computer vision, enabling it to be used in a variety of applications, such as virtual reality and human-computer interaction. However, gaze estimation in the field is still challenging due to different head postures, lighting conditions and eye appearances. In this work, we propose a novel gaze estimation model with framework based on ResNet-50, which improves its estimation accuracy. In addition, the same loss function for each predicted angle is used to improve the generalization performance of the model. Finally, the proposed model is validated on the two most unconstrained popular datasets, such as MPIIGAZE and GAZE360. The experimental results show the proposed approach performs better compared to other better methods. © 2024 ACM.

关键词： Computer vision

来源：评论

学校读者我要写书评

暂无评论

Bye, Bye, Maintenance Work? Using Model Cloning to Approximate the Behavior of Legacy Tools 18

Bye, Bye, Maintenance Work? Using Model Cloning to Approxima...

引用

18th Conference on Natural Language Processing, KONVENS 2022

作者： Aggarwal, Piush Zesch, Torsten Catalpa - Center for Advanced Technology-Assisted Learning and Predictive Analytics Computational Linguistics FernUniversitat in Hagen Germany

A lot of NLP tools are not maintained anymore, but might still provide some unique functionality. We investigate whether such legacy tools could be replaced by a neural network that closely imitates the original behavior. For this purpose, we propose model cloning that can be performed by solely looking at the output of the original model, which makes the cloning possible also for black-box systems. Using a single neural architecture for cloning legacy models, caries other benefits like ease-of-use, continued maintenance, and expected speed increase. As a proof-of-concept, we clone 9 models from 5 POS tagger implementations of different complexity. The cloned models all learn to perform POS tagging on par with the legacy models, but seem not to learn the specific tagging patterns of individual legacy models. © KONVENS 2022 . All rights reserved.

关键词： Cloning

来源：评论

学校读者我要写书评

暂无评论

HGAMLP: Heterogeneous Graph Attention MLP with De-Redundancy Mechanism 40

HGAMLP: Heterogeneous Graph Attention MLP with De-Redundancy...

引用

40th IEEE International Conference on Data Engineering, ICDE 2024

作者： Liang, Yuxuan Zhang, Wentao Sheng, Zeang Yang, Ling Jiang, Jiawei Tong, Yunhai Cui, Bin School of Intelligence Science and Technology Peking University China Center for Machine Learning Research Peking University China School of Computer Science Wuhan University China Peking University China China

ISBN: (纸本)9798350317152

Heterogeneous graphs contain rich semantic information that can be exploited by heterogeneous graph neural networks (HGNNs). However, scaling HGNNs to large graphs is challenging due to the high computational cost. Existing non-parametric HGNNs use general subgraphs construction method and mean aggregator before training to reduce the complexity. Despite their success, they ignore two key characteristics of heterogeneous graphs, leading to low predictive performance. First, they adopt fixed local and global knowledge extractor for the feature aggregation and the semantic fusion. Besides, they bury the graph structure information of the higher-order meta-paths and fail to explore deeper graph structure information. In this paper, we address these two limitations and propose a new non-parametric HGNN framework called Heterogeneous Graph Attention Multi-Layer Perceptron (HGAMLP). Our framework employs the local multi-knowledge extractor to enhance the node representation, and leverages the de-redundancy mechanism to extract the pure graph structure information from higher-order meta-paths. Besides, it adopts a node-adaptive weight adjustment mechanism as an efficiency training model to fuse global knowledge and local knowledge. We evaluate our framework on ten commonly used heterogeneous graph datasets and show that it outperforms the state-of-the-art baselines in both accuracy and speed. Notably, our framework achieves the best performance on the large public heterogeneous graph dataset (i.e., Ogbn-mag) of Open Graph Benchmark. https://***/docs/leader-nodeprop. © 2024 IEEE.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

Variational learning is Effective for Large Deep Networks 41

Variational Learning is Effective for Large Deep Networks

引用

41st International Conference on Machine learning, ICML 2024

作者： Shen, Yuesong Daheim, Nico Cong, Bai Nickl, Peter Marconi, Gian Maria Bazan, Clement Yokota, Rio Gurevych, Iryna Cremers, Daniel Khan, Mohammad Emtiyaz Möllenhoff, Thomas Technical University of Munich Munich Center for Machine Learning Munich Germany UKP Lab Technical University of Darmstadt & hessian.AI Darmstadt Germany Tokyo Institute of Technology Tokyo Japan RIKEN Center for AI Project Tokyo Japan

We give extensive empirical evidence against the common belief that variational learning is ineffective for large neural networks. We show that an optimizer called Improved Variational Online Newton (IVON) consistently matches or outperforms Adam for training large networks such as GPT-2 and ResNets from scratch. IVON's computational costs are nearly identical to Adam but its predictive uncertainty is better. We show several new use cases of IVON where we improve finetuning and model merging in Large Language Models, accurately predict generalization error, and faithfully estimate sensitivity to data. We find overwhelming evidence that variational learning is effective. Code is available at https://***/team-approx-bayes/ivon. Copyright 2024 by the author(s)

关键词： Contrastive learning

来源：评论

学校读者我要写书评

暂无评论

Roles, applications, and research designs of robots in science education: a systematic review and bibliometric analysis of journal publications from 1996 to 2020

引用

Interactive learning Environments 2024年第5期32卷 1834-1859页

作者： Chiu, Min-Chi Hwang, Gwo-Jen Tu, Yun-Fang Graduate Institute of Applied Science and Technology National Taiwan University of Science and Technology Taipei Taiwan Graduate Institute of Digital Learning and Education National Taiwan University of Science and Technology Taipei Taiwan Department of Library and Information Science Research and Development Center for Physical Education Health and Information Technology Fu Jen Catholic University New Taipei City Taiwan

This research reviews 56 robots in science education (RSE) research articles published in SSCI (Social Sciences Citation Index) journals in the Web of Science (WoS) database. The analysis results showed that there were three clusters of RSE studies: robots in elementary science education, robot-based STEM activities, and robot-facilitated computational thinking. In terms of the research issues, more studies were conducted across-disciplines. Regarding thematic classifications, “general benefits of educational robots” was the most frequently investigated issue, while “diversity and broadening participation,” and “creativity and motivation” were less frequently discussed. The most adopted research methods were quantitative and mixed methods, focusing on measuring learners’ cognition and affect. Most of the interventions in the empirical studies adopted pedagogical interventions. In terms of the interaction issue, LEGO was adopted the most, followed by self-made robots;moreover, robots frequently played the role of tools in science education. From the perspective of specific robotics content knowledge, “control” (e.g. programming) comprised the majority. The most adopted learning strategy was project-based learning, followed by issue-based discussion. Regarding assessment issues, the most adopted evaluation approaches to evaluating students’ performance were questionnaires, observation, verbal interviews, and artifacts to assess the quality of learning activities. © 2022 Informa UK Limited, trading as Taylor & Francis Group.

关键词： Bibliometric analysis robots science education STEM systematic review

来源：评论

学校读者我要写书评

暂无评论

GEOMETRY-AWARE RL FOR MANIPULATION OF VARYING SHAPES AND DEFORMABLE OBJECTS

arXiv

引用

arXiv 2025年

作者： Hoang, Tai Le, Huy Becker, Philipp Vien, Ngo Anh Neumann, Gerhard Autonomous Learning Robots Karlsruhe Institute of Technology Germany Bosch Center for Artificial Intelligence

Manipulating objects with varying geometries and deformable objects is a major challenge in robotics. Tasks such as insertion with different objects or cloth hanging require precise control and effective modelling of complex dynamics. In this work, we frame this problem through the lens of a heterogeneous graph that comprises smaller sub-graphs, such as actuators and objects, accompanied by different edge types describing their interactions. This graph representation serves as a unified structure for both rigid and deformable objects tasks, and can be extended further to tasks comprising multiple actuators. To evaluate this setup, we present a novel and challenging reinforcement learning benchmark, including rigid insertion of diverse objects, as well as rope and cloth manipulation with multiple end-effectors. These tasks present a large search space, as both the initial and target configurations are uniformly sampled in 3D space. To address this issue, we propose a novel graph-based policy model, dubbed Heterogeneous Equivariant Policy (HEPi), utilizing SE(3) equivariant message passing networks as the main backbone to exploit the geometric symmetry. In addition, by modeling explicit heterogeneity, HEPi can outperform Transformer-based and non-heterogeneous equivariant policies in terms of average returns, sample efficiency, and generalization to unseen objects. Our project page is available here. © 2025, CC BY.

关键词： End effectors

来源：评论

学校读者我要写书评

暂无评论

The Influence of Knowledge-Building-Based Collaborative Argumentation Instruction on High School Students' Online Collaborative Argumentation Performance and Behavioral Patterns Regarding Socio-Scientific Issues 16

The Influence of Knowledge-Building-Based Collaborative Argu...

引用

16th International Conference on Computer-Supported Collaborative learning, CSCL 2023

作者： Wang, Li-Jen Wu, Ying-Tien Language Teaching and Research Center National Yang Ming Chiao Tung University Taiwan Graduate Institute of Network Learning Technology National Central University Taiwan

ISBN: (纸本)9781737330684

Argumentation on socio-scientific issues (SSI) is challenging for high school students, this study attempted to adopt the knowledge-building (KB) pedagogy in SSI-based collaborative argumentation instruction design and further explored its effects on high school students' SSI-based online argumentation. This study revealed that the students in the experimental group benefited more from the KB-based instruction in their online SSI-based argumentation performance. Also, two groups of students revealed different online collaborative argumentation behavioral patterns after instructions. © 2023 International Society of the learning Sciences (ISLS). All rights reserved.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

The effect of real-time pose recognition on badminton learning performance

引用

Interactive learning Environments 2023年第8期31卷 4772-4786页

作者： Lin, Kuo-Chin Ko, Cheng-Wen Hung, Hui-Chun Chen, Nian-Shing Center for Physical and Health Education National Sun Yat-sen University Kaohsiung Taiwan Department of Computer Science and Engineering National Sun Yat-sen University Kaohsiung Taiwan Graduate Institute of Network Learning Technology National Central University Chung-Li Taiwan Institute for Research Excellence in Learning Sciences and Program of Learning Sciences National Taiwan Normal University Taipei Taiwan

Badminton is a very popular subject in Physical Education (PE). Many students enroll badminton courses in every semester which pose a tremendous teaching load to the instructors. The one-on-one guiding/feedback time provided by the instructor to each student is also greatly reduced. To overcome this challenge, some studies have tried to adopt pose recognition technique in teaching badminton. However, the lack of mobility and recognition accuracy problems hinder its applicability. To address this issue, a new pose recognition technique, OpenPose, was employed to develop a real-time pose recognition badminton teaching APP in this study. The APP was then installed on a mobile device to enhance badminton smash skill learning performance. The scores distribution of the experimental group shows majority of students achieved satisfactory performance, this implies the badminton teaching APP is helpful to all students no matter what their initial skill levels are. © 2021 Informa UK Limited, trading as Taylor & Francis Group.

关键词： badminton teaching motor skill learning physical education Pose recognition real-time feedback

来源：评论

学校读者我要写书评

暂无评论

CLAMBER: A Benchmark of Identifying and Clarifying Ambiguous Information Needs in Large Language Models 62

CLAMBER: A Benchmark of Identifying and Clarifying Ambiguous...

引用

62nd Annual Meeting of the Association for Computational Linguistics, ACL 2024

作者： Zhang, Tong Qin, Peixin Deng, Yang Huang, Chen Liang, Hongru Liu, Junhong Jin, Dingnan Lei, Wenqiang Chua, Tat-Seng College of Computer Science Sichuan University China Engineering Research Center of Machine Learning and Industry Intelligence Ministry of Education China National University of Singapore Singapore University of Electronic Science and Technology China

ISBN: (纸本)9798891760943

Large language models (LLMs) are increasingly used to meet user information needs, but their effectiveness in dealing with user queries that contain various types of ambiguity remains unknown, ultimately risking user trust and satisfaction. To this end, we introduce CLAMBER, a benchmark for evaluating LLMs using a well-organized taxonomy. Building upon the taxonomy, we construct ~ 12K high-quality data to assess the strengths, weaknesses, and potential risks of various off-the-shelf LLMs. Our findings indicate the limited practical utility of current LLMs in identifying and clarifying ambiguous user queries, even enhanced by chain-of-thought (CoT) and few-shot prompting. These techniques may result in overconfidence in LLMs and yield only marginal enhancements in identifying ambiguity. Furthermore, current LLMs fall short in generating high-quality clarifying questions due to a lack of conflict resolution and inaccurate utilization of inherent knowledge. In this paper, CLAMBER presents a guidance and promotes further research on proactive and trustworthy LLMs. Our dataset is available at https://***/SCUNLP/CLAMBER. © 2024 Association for Computational Linguistics.

关键词： Risk assessment

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：