检索结果-内蒙古大学图书馆

arXiv 2020年

作者： Trebing, Kevin Mehrkanoon, Siamak Department of Data Science and Knowledge Engineering Maastricht University Netherlands

Weather forecasting is dominated by numerical weather prediction that tries to model accurately the physical properties of the atmosphere. A downside of numerical weather prediction is that it is lacking the ability for short-term forecasts using the latest available information. By using a data-driven neural network approach we show that it is possible to produce an accurate precipitation nowcast. To this end, we propose SmaAt-UNet, an efficient convolutional neural networks based on the well known UNet architecture equipped with attention modules and depthwise-separable convolutions. We evaluate our approach on a real-life dataset using precipitation maps from the region of the Netherlands. The experimental results show that in terms of accuracy the proposed model is comparable to other examined models while only using a quarter of the trainable parameters. Copyright © 2020, The Authors. All rights reserved.

关键词： Weather forecasting

来源：评论

学校读者我要写书评

暂无评论

Document-level Relation Extraction with Relation Correlations

arXiv

引用

arXiv 2022年

作者： Han, Ridong Peng, Tao Wang, Benyou Liu, Lu Wan, Xiang College of Computer Science and Technology Jilin University China Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education China College of Software Jilin University China Shenzhen Research Institute of Big Data The Chinese University of Hong Kong Shenzhen China School of Data Science The Chinese University of Hong Kong Shenzhen China

Document-level relation extraction faces two overlooked challenges: long-tail problem and multi-label problem. Previous work focuses mainly on obtaining better contextual representations for entity pairs, hardly address the above challenges. In this paper, we analyze the co-occurrence correlation of relations, and introduce it into DocRE task for the first time. We argue that the correlations can not only transfer knowledge between data-rich relations and data-scarce ones to assist in the training of tailed relations, but also reflect semantic distance guiding the classifier to identify semantically close relations for multi-label entity pairs. Specifically, we use relation embedding as a medium, and propose two co-occurrence prediction sub-tasks from both coarse- and fine-grained perspectives to capture relation correlations. Finally, the learned correlation-aware embeddings are used to guide the extraction of relational facts. Substantial experiments on two popular DocRE datasets are conducted, and our method achieves superior results compared to baselines. Insightful analysis also demonstrates the potential of relation correlations to address the above challenges. Copyright © 2022, The Authors. All rights reserved.

关键词： Extraction

来源：评论

学校读者我要写书评

暂无评论

Research on Penetration Strategy of UAV 2020

Research on Penetration Strategy of UAV

引用

Proceedings of the 2020 International Conference on Cyberspace Innovation of Advanced Technologies

作者： Daojun Han Hongzhen Xiang Haolin Chen Yi Xie Institute of Data and Knowledge Engineering Henan University Kaifeng PR China School of Computer and Information Engineering Henan University Kaifeng PR China Henan Key Laboratory of Big Data Analysis and Processing Henan University Kaifeng PR China

ISBN: (纸本)9781450387828

Taking a military operation as an example, this paper makes an in-depth study of what tactics a single UAV should adopt when facing the interception of multiple enemy UAV groups. According to the analysis of the impact diagram, the aerial range of the UAV standoff defines a threat area, that is, when the UAV arrives at the threat area, it needs to adopt a strategy for penetration, or it will be intercepted. The strategy adopted by UAV in the threat area is analyzed, and the decision control method is made.

关键词： Decision control Threat area Influence chart analysis UAV penetration

来源：评论

学校读者我要写书评

暂无评论

On sorting with a network of two stacks 19

On sorting with a network of two stacks

引用

19th Symposium on Algorithmic Approaches for Transportation Modelling, Optimization, and Systems, ATMOS 2019

作者： Mihalák, Matúš Pont, Marc Department of Data Science and Knowledge Engineering Maastricht University Netherlands

ISBN: (纸本)9783959771283

Sorting with stacks is a collection of problems that deal with sorting a sequence of numbers by pushing and popping the numbers to and from a given set of stacks. Multiple concrete decision or optimization questions are formed by restricting the access to the stacks. The motivation comes, e.g., from shunting train wagons in shunting yards, shunting trams in depots, or in stacking cargo containers on cargo ships or storage yards in transshipment terminals. We consider the problem of sorting a permutation of n integers 1, 2, . . ., n using k ≥ 2 stacks. In this problem, elements from the input sequence are pushed one-by-one (in the order of the elements in the sequence) to one of the k stacks. At any time, an element from a stack can be popped and pushed to another stack;such an operation is called a shuffle. Also, at any time, an element can be popped from a stack and placed to the output sequence. We can only place the elements to the output in the increasing order of their value such that at the end the output is the ordered sequence of the elements. The problem asks to minimize the number of shuffles in the process. It is known that for k ≥ 4, the problem is NP-hard, and that there is no approximation algorithm unless P=NP. For k ≥ 3, it is known that at most O(n log n) shuffles are needed for any input sequence. For the case when k = 2, there exist input sequences that require Ω(n2−Ε) shuffles, for any Ε > 0. Nothing substantially more is known for the case of k = 2. In this paper, we study the following variant of the problem with k = 2 stacks: no shuffle and no placement to the output sequence can happen before every element is in one of the two stacks. We show that our problem can be seen as the MinUnCut problem by providing a polynomial-time reduction, and thus we show that there exists a randomized O(√log n)-approximation algorithm and a deterministic O(log n)-approximation algorithm for our problem. © Matúš Mihalák and Marc Pont;licensed under Creative Comm

关键词： Optimization

来源：评论

学校读者我要写书评

暂无评论

Search Result Diversification Framework Based on Dual Star-shaped Self-Attention Network 20

Search Result Diversification Framework Based on Dual Star-s...

引用

20th Chinese National Conference on Computational Linguistics, CCL 2021

作者： Qin, Xubo Dou, Zhicheng Zhu, Yutao Wen, Ji-Rong School of Information Renmin University Gaoling School of Artificial Intelligence Renmin University of China Université de Montréal Beijing Key Laboratory of Big Data Management and Analysis Methods Key Laboratory of Data Engineering and Knowledge Engineering MOE

Research shows that most queries issued by users are short queries. Those queries may be ambiguous or broad for specifying users' actual information need. The same query issued by different users may lead to different information needs. In order to satisfy different users' needs, the search engines need to rank the search result document diversely. This leads to the search result diversification technology. For those previous diversification approaches based on global document interactions, fully-connected self-attention networks are used for capturing the interactions among all the candidate documents, leading to well performance. However, those models only take the document interactions into consideration, ignoring the relevance signals of candidate documents. As the annotated datasets are not enough for model training, the effectiveness of the model will be limited. In this paper we prove a new implicit diversification framework based on self-attention network in the shape of dual-star. A star-shaped topological structure is deployed with an external query node, in order to effectively extract the global interaction signals relevant to the query. Using self-attention to learn the similarity between each document, this model can be trained easily, and perform significantly better than the state-of-the-art implicit approach indicating the potential of implicit methods. © 2021 China National Conference on Computational Linguistics Published under Creative Commons Attribution 4.0 International License

关键词： Search engines

来源：评论

学校读者我要写书评

暂无评论

GenF: A longevity predicting framework to aid public health sectors

引用

Informatics in Medicine Unlocked 2021年 26卷

作者： Khalid, Sadia Rasheed, Uzair Qamar, Usman Knowledge & Data Science Centre Department of Computer and Software Engineering College of Electrical and Mechanical Engineering National University of Sciences and Technology Islamabad Pakistan

Life expectancy at older ages has seen an increment in the past 100 years and factors influencing longevity are since being studied. Public health sectors (PHS) across the globe are trying hard to understand longevity trends to improve living conditions and provide necessary medical facilities;but there is no single tool that can help the overall cause of recording and/or measuring and/or predicting human longevity. The objectives of this study are to help PHS understand longevity-influencing factors and to offer a framework to record and predict longevity trends in any population around the globe. This study has gathered fifteen longevity-influencing factors from literature between 2000 and 2020;with a special focus on APOE genotype;and based on them, has developed a framework GenF, including a rule base dataset of 73,728 rules, to predict longevity. Furthermore, the study has also used GenF to perform feature selection on the rule base and generate another rule base for customized longevity predictions. Models, using four different machine learning classifiers, are then trained on both rule bases to predict longevity. © 2021 The Authors

关键词： Healthy aging Human longevity Public health Rule based classifier Supervised learning

来源：评论

学校读者我要写书评

暂无评论

A Survey on Fairness in Large Language Models

arXiv

引用

arXiv 2023年

作者： Li, Yingji Du, Mengnan Song, Rui Wang, Xin Wang, Ying College of Computer Science and Technology Jilin University Changchun130012 China Department of Data Science New Jersey Institute of Technology Newark United States School of Artificial Intelligence Jilin University Changchun130012 China Key Laboratory of Symbol Computation and Knowledge Engineering Jilin University Ministry of Education Changchun130012 China

Large Language Models (LLMs) have shown powerful performance and development prospects and are widely deployed in the real world. However, LLMs can capture social biases from unprocessed training data and propagate the biases to downstream tasks. Unfair LLM systems have undesirable social impacts and potential harms. In this paper, we provide a comprehensive review of related research on fairness in LLMs. Considering the influence of parameter magnitude and training paradigm on research strategy, we divide existing fairness research into oriented to medium-sized LLMs under pre-training and fine-tuning paradigms and oriented to large-sized LLMs under prompting paradigms. First, for medium-sized LLMs, we introduce evaluation metrics and debiasing methods from the perspectives of intrinsic bias and extrinsic bias, respectively. Then, for large-sized LLMs, we introduce recent fairness research, including fairness evaluation, reasons for bias, and debiasing methods. Finally, we discuss and provide insight on the challenges and future directions for the development of fairness in LLMs. Copyright © 2023, The Authors. All rights reserved.

关键词： Computational linguistics

来源：评论

学校读者我要写书评

暂无评论

A generative policy gradient approach for learning to play text-based adventure games 31

A generative policy gradient approach for learning to play t...

引用

31st Benelux Conference on Artificial Intelligence and the 28th Belgian Dutch Conference on Machine Learning, BNAIC/BENELEARN 2019

作者： Raab, René Driessens, Kurt Department of Data Science and Knowledge Engineering Maastricht University Netherlands

来源：评论

学校读者我要写书评

暂无评论

Deep multi-stations weather forecasting: Explainable recurrent convolutional neural networks

arXiv

引用

arXiv 2020年

作者： Abdellaoui, Ismail Alaoui Mehrkanoon, Siamak Department of Data Science and Knowledge Engineering Maastricht University Netherlands

Deep learning applied to weather forecasting has started gaining popularity because of the progress achieved by data-driven models. The present paper compares two different deep learning architectures to perform weather prediction on daily data gathered from 18 cities across Europe and spanned over a period of 15 years. We propose the Deep Attention Unistream Multistream (DAUM) networks that investigate different types of input representations (i.e. tensorial unistream vs. multistream) as well as the incorporation of the attention mechanism. In particular, we show that adding a self-attention block within the models increases the overall forecasting performance. Furthermore, visualization techniques such as occlusion analysis and score maximization are used to give an additional insight on the most important features and cities for predicting a particular target feature of target cities. © 2020, CC BY-SA.

关键词： Weather forecasting

来源：评论

学校读者我要写书评

暂无评论

Deep shared representation learning for weather elements forecasting 31

Deep shared representation learning for weather elements for...

引用

31st Benelux Conference on Artificial Intelligence and the 28th Belgian Dutch Conference on Machine Learning, BNAIC/BENELEARN 2019

作者： Mehrkanoon, Siamak Department of Data Science and Knowledge Engineering Maastricht University Netherlands

This paper introduces a data-driven predictive model based on deep convolutional neural networks (CNN) architecture for wind speed prediction in weather data. The model exploits the spatio-temporal multivariate weather data for learning shared representations and forecasting weather elements for a number of user defined weather stations simultaneously in an end-to-end fashion. The embedded feature learning component of the model as well as coupling the learned features of different input layers have shown to have a significant impact on the prediction task. An experimental setup has been considered based on a high temporal resolution dataset collected from the National Climatic data Center (NCDC) at five stations located in Denmark. The experiment concerns wind speed prediction at three weather stations located in Denmark for 6 and 12 hours ahead. © 2019 for this paper by its authors.

关键词： Deep neural networks

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：