检索结果-内蒙古大学图书馆

UPB Scientific Bulletin, Series C: Electrical Engineering and computer science 2022年第4期84卷 3-8页

作者： Olteanu, Mircea Ştefan, Radu Department of Mathematical Methods and Models Faculty of Applied Sciences University "Politehnica" of Bucharest Romania Department of Automatic Control and Systems Engineering Faculty of Automatic Control and Computer Science University "Politehnica" of Bucharest Romania

来源：评论

学校读者我要写书评

暂无评论

REASONER: An Explainable Recommendation Dataset with Multi-aspect Real User Labeled Ground Truths Towards more Measurable Explainable Recommendation

arXiv

引用

arXiv 2023年

作者： Chen, Xu Zhang, Jingsen Wang, Lei Dai, Quanyu Dong, Zhenhua Tang, Ruiming Zhang, Rui Chen, Li Wen, Ji-Rong Beijing Key Laboratory of Big Data Management and Analysis Methods Beijing China Gaoling School of Artificial Intelligence Renmin University of China Beijing China Huawei Noah’s Ark Lab China Department of Computer Science Hong Kong Baptist University Hong Kong

Explainable recommendation has attracted much attention from the industry and academic communities. It has shown great potential for improving the recommendation persuasiveness, informativeness and user satisfaction. Despite a lot of promising explainable recommender models have been proposed in the past few years, the evaluation strategies of these models suffer from several limitations. For example, the explanation ground truths are not labeled by real users, the explanations are mostly evaluated based on only one aspect and the evaluation strategies can be hard to unify. To alleviate the above problems, we propose to build an explainable recommendation dataset with multi-aspect real user labeled ground truths. In specific, we firstly develop a video recommendation platform, where a series of questions around the recommendation explainability are carefully designed. Then, we recruit about 3000 users with different backgrounds to use the system, and collect their behaviors and feedback to our questions. In this paper, we detail the construction process of our dataset and also provide extensive analysis on its characteristics. In addition, we develop a library, where ten well-known explainable recommender models are implemented in a unified framework. Based on this library, we build several benchmarks for different explainable recommendation tasks. At last, we present many new opportunities brought by our dataset, which are expected to shed some new lights to the explainable recommendation field. Our dataset, library and the related documents have been released at https://***/. Copyright © 2023, The Authors. All rights reserved.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Equivariant spatio-temporal attentive graph networks to simulate physical dynamics 23

Equivariant spatio-temporal attentive graph networks to simu...

引用

Proceedings of the 37th International Conference on Neural Information Processing Systems

作者： Liming Wu Zhichao Hou Jirui Yuan Yu Rong Wenbing Huang Gaoling School of Artificial Intelligence Renmin University of China and Beijing Key Laboratory of Big Data Management and Analysis Methods Beijing China Department of Computer Science North Carolina State University Institute for AI Industry Research (AIR) Tsinghua University Tencent AI Lab

Learning to represent and simulate the dynamics of physical systems is a crucial yet challenging task. Existing equivariant Graph Neural Network (GNN) based methods have encapsulated the symmetry of physics, e.g., translations, rotations, etc, leading to better generalization ability. Nevertheless, their frame-to-frame formulation of the task overlooks the non-Markov property mainly incurred by unobserved dynamics in the environment. In this paper, we reformulate dynamics simulation as a spatio-temporal prediction task, by employing the trajectory in the past period to recover the Non-Markovian interactions. We propose Equivariant Spatio-Temporal Attentive Graph Networks (ESTAG), an equivariant version of spatio-temporal GNNs, to fulfill our purpose. At its core, we design a novel Equivariant Discrete Fourier Transform (EDFT) to extract periodic patterns from the history frames, and then construct an Equivariant Spatial Module (ESM) to accomplish spatial message passing, and an Equivariant Temporal Module (ETM) with the forward attention and equivariant pooling mechanisms to aggregate temporal message. We evaluate our model on three real datasets corresponding to the molecular-, protein- and macro-level. Experimental results verify the effectiveness of ESTAG compared to typical spatio-temporal GNNs and equivariant GNNs.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Kepler problem and chiral effective dynamics

引用

Physical Review E 2022年第6期106卷 064207-064207页

作者： Katarzyna Bolonek-Lasoń Joanna Gonera Piotr Kosiński Department of Statistical Methods Faculty of Economics and Sociology University of Lodz 41/43 Rewolucji 1905 Street 90-214 Lodz Poland Department of Computer Science Faculty of Physics and Applied Informatics University of Lodz 149/153 Pomorska Street 90-236 Lodz Poland

It is shown that by an appropriate canonical transformation, Kepler dynamics can be put in the form which allows one to exhibit the structure of the symmetry transformations related to the superintegrability. They appear to fit nicely into a general scheme of nonlinear realizations. In new coordinates, the Kepler dynamics results from dimensional reduction of that describing low-energy mesons with spontaneously broken chiral symmetry.

关键词： Mathematical physics

来源：评论

学校读者我要写书评

暂无评论

Balanced Audiovisual Dataset for Imbalance Analysis

arXiv

引用

arXiv 2023年

作者： Xia, Wenke Zhao, Xu Pang, Xincheng Zhang, Changqing Hu, Di Gaoling School of Artificial Intelligence Renmin University of China Beijing China School of Computer Science and Engineering Northeastern University Shenyang China College of Intelligence and Computing Tianjin University Tianjin China Beijing Key Laboratory of Big Data Management and Analysis Methods Beijing China

The imbalance problem is widespread in the field of machine learning, whichalso exists in multimodal learning areas caused by the intrinsic discrepancybetween modalities of samples. Recent works have attempted to solve themodality imbalance problem from algorithm perspective, however, they do notfully analyze the influence of modality bias in datasets. Concretely, existingmultimodal datasets are usually collected under specific tasks, where onemodality tends to perform better than other ones in most conditions. In thiswork, to comprehensively explore the influence of modality bias, we first splitexisting datasets into different subsets by estimating sample-wise modalitydiscrepancy. We surprisingly find that: the multimodal models with existingimbalance algorithms consistently perform worse than the unimodal one onspecific subsets, in accordance with the modality bias. To further explore theinfluence of modality bias and analyze the effectiveness of existing imbalancealgorithms, we build a balanced audiovisual dataset, with uniformly distributedmodality discrepancy over the whole dataset. We then conduct extensiveexperiments to re-evaluate existing imbalance algorithms and draw someinteresting findings: existing algorithms only provide a compromise betweenmodalities and suffer from the large modality discrepancy of samples. We hopethat these findings could facilitate future research on the modality imbalanceproblem. Copyright © 2023, The Authors. All rights reserved.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

The KANDY Benchmark: Incremental Neuro-Symbolic Learning and Reasoning with Kandinsky Patterns

arXiv

引用

arXiv 2024年

作者： Lorello, Luca Salvatore Lippi, Marco Melacci, Stefano Department of Computer Science University of Pisa Largo B. Pontecorvo 3 Pisa56127 Italy Department of Sciences and Methods for Engineering University of Modena and Reggio Emilia via Amendola 2 Reggio Emilia42122 Italy Department of Information Engineering and Mathematics University of Siena via Roma 56 Siena53100 Italy

Artificial intelligence is continuously seeking novel challenges and benchmarks to effectively measure performance and to advance the state-of-the-art. In this paper we introduce KANDY, a benchmarking framework that can be used to generate a variety of learning and reasoning tasks inspired by Kandinsky patterns. By creating curricula of binary classification tasks with increasing complexity and with sparse supervisions, KANDY can be used to implement benchmarks for continual and semi-supervised learning, with a specific focus on symbol compositionality. Classification rules are also provided in the ground truth to enable analysis of interpretable solutions. Together with the benchmark generation pipeline, we release two curricula, an easier and a harder one, that we propose as new challenges for the research community. With a thorough experimental evaluation, we show how both state-of-the-art neural models and purely symbolic approaches struggle with solving most of the tasks, thus calling for the application of advanced neuro-symbolic methods trained over time. © 2024, CC BY-NC-SA.

关键词： Curricula

来源：评论

学校读者我要写书评

暂无评论

Demographics, Approaches, and Conceptions: Understanding computer science Learning

Journal of Computing Sciences in Colleges

引用

Journal of Computing sciences in Colleges 2024年第1期40卷

作者： Bokai Yang Ling Hao Yuqi Song Xin Zhang Fei Zuo Xianshan Qu Department of Computer Science University of Wisconsin - Eau Claire Eau Claire WI School of Teaching & Learning Illinois State University Normal IL Department of Computer Science University of Southern Maine Portland ME Department of Computer Science University of Central Oklahoma Edmond OK

Understanding students' computer science learning conception and learning approach is essential for improving their learning experience and performance. By applying qualitative content analysis, machine learning techniques and a descriptive approach, this study explores the associations between demographic characteristics, computer science learning approaches, and conceptions among undergraduate students. The findings of this study reveal associations between students' learning approaches and demographic factors such as grades, gender, and parents' education. Moreover, the study highlights discrepancies between students' learning approaches and their motivation and strategy for learning.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Edge Detection of SAR Images Based on Shearlet 7th

Edge Detection of SAR Images Based on Shearlet

引用

7th China High-resolution Earth Observation Conference, CHREOC 2020

作者： Sun, Zengguo Zhao, Guodong Chen, Weirong Damaševičius, Robertas Woźniak, Marcin Key Laboratory of Modern Teaching Technology Ministry of Education Xi’an China School of Computer Science Shaanxi Normal University Xi’an China China Centre for Resources Satellite Data and Application Beijing China Department of Applied Informatics Vytautas Magnus University Kaunas Lithuania Faculty of Applied Mathematics Silesian University of Technology Kaszubska 23 Gliwice44-100 Poland

ISBN: (纸本)9789811657344

Synthetic aperture radar (SAR) has the characteristics of all-weather imaging and is widely used in various fields. However, owe to coherent imaging mechanism, speckle appears in SAR images, which seriously affects the interpretation of images. Due to merits of the strong directional sensitivity and the optimal sparsity, shearlet is used to construct an edge detector for SAR images. The detector firstly converts the constructed even symmetric shearlet into odd symmetry by Hilbert transform, then determines the main direction of the edge according to the odd symmetric shearlet coefficient of the SAR image, and calculates the possibility of edge existence according to both odd and even symmetric shearlet coefficient. Experiments show that, in comparison with the traditional difference-based edge detectors, the proposed edge detector has stronger ability of anti-speckle interference, and can better detect the edge information in SAR images. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Speckle

来源：评论

学校读者我要写书评

暂无评论

Intensionalizing Abstract Meaning Representations: Non-Veridicality and Scope 15

Intensionalizing Abstract Meaning Representations: Non-Verid...

引用

Joint 15th Linguistic Annotation Workshop and 3rd Designing Meaning Representations Workshop, LAW-DMR 2021

作者： Williamson, Gregor Elliott, Patrick Ji, Yuxin Department of Computer Science Emory University AtlantaGA30322 United States Department of Linguistics and Philosophy Massachusetts Institute of Technology CambridgeMA02139 United States Department of Quantitative Theory and Methods Emory University AtlantaGA30322 United States

ISBN: (纸本)9781954085855

Meaning Representation (AMR) is a graphical meaning representation language designed to represent propositional information about argument structure. However, at present it is unable to satisfyingly represent non-veridical intensional contexts, often licensing inappropriate inferences. In this paper, we show how to resolve the problem of non-veridicality without appealing to layered graphs through a mapping from AMRs into Simply-Typed Lambda Calculus (STLC). At least for some cases, this requires the introduction of a new role:content which functions as an intensional operator. The translation proposed is inspired by the formal linguistics literature on the event semantics of attitude reports. Next, we address the interaction of quantifier scope and intensional operators in so-called de re/de dicto ambiguities. We adopt a scope node from the literature and provide an explicit multidimensional semantics utilizing Cooper storage which allows us to derive the de re and de dicto scope readings as well as intermediate scope readings which prove difficult for accounts without a scope node. © 2021 Association for Computational Linguistics.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Use of digital platforms for enhancing academic performance. Systematic Review

Use of digital platforms for enhancing academic performance....

引用

International IEEE Conference and Workshop: Óbuda on Electrical and Power Engineering (CANDO-EPE)

作者： Cristina Anamaria Costescu Mălina Șogor Sabina Pălimariu Jozsef Katona Ioana Tufar Carla Maria Avram Special Education Department Babeș-Bolyai University Cluj-Napoca Romania Institute of Electronics and Communication Systems Kandó Kálmán Faculty of Electrical Engineering Obuda University Budapest Hungary Department of Software Development and Application Institute of Computer Engineering University of Dunaujvaros Dunaujvaros Hungary GAMF Faculty of Engineering and Computer Science John Von Neumann University Kecskemet Hungary Department of Applied Quantitative Methods Faculty of Finance and Accountancy Budapest Business University Budapest Hungary

ISBN: (数字)9798331531119

ISBN: (纸本)9798331531126

The purpose of this study was to determine the effect of technology-based interventions on academic performance. To achieve this purpose a systematic review was conducted. Within the scope of this study EBSCO, Springer, ProQuest, science Direct, Wiley Online Library, Taylor and Francis Online, databases were scanned, and 18 studies were included in the review. Our results show that the iPad is the most preferred digital device for enhancing math and reading skills and significant results can be seen when used. Similar positive effects were observed with other technological devices, reinforcing the effectiveness of technology as a tool for supporting academic performance. This evidence underscores the value of incorporating digital devices in educational strategies, particularly for improving key academic skills.

关键词： Performance evaluation Power engineering Databases Personal digital devices Tablet computers Libraries

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：