检索结果-内蒙古大学图书馆

您好，读者！请登录

内蒙古大学图书馆

首页
概况
党建
资源
服务
科研支持
- 论文收录引用证明
- 科技查新
知识产权
档案馆
帮助

咨询与建议

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

您的常用邮箱：*

您的手机号码：*

问题描述：

当前已输入0个字，您还可以输入200个字

全部搜索
期刊论文
图书
学位论文
标准
纸本馆藏
外文资源发现
数据库导航
超星发现

高级检索

时间限定

出版年份：

文献类型

图书期刊文献学位论文多媒体

馆藏选择

电子馆藏纸本馆藏

核心期刊

全部期刊 SCI 收录期刊 SSCI 收录期刊 EI 收录期刊 CSCD 收录期刊 CSSCI 收录期刊

语言

中文英文

文献类型

期刊文献图书学位论文标准纸本馆藏

帮助

文字说明：

T=题名（书名、题名），A=作者（责任者），K=主题词，P=出版物名称，PU=出版社名称，O=机构（作者单位、学位授予单位、专利申请人），L=中图分类号，C=学科分类号，U=全部字段，Y=年（出版发行年、学位年度、标准发布年）

检索规则说明：

AND代表“并且”；OR代表“或者”；NOT代表“不包含”；(注意必须大写,运算符两边需空一格)

检索范例：

范例一：(K=图书馆学 OR K=情报学) AND A=范并思 AND Y=1982-2016
范例二：P=计算机应用与软件 AND (U=C++ OR U=Basic) NOT K=Visual AND Y=2011-2016

分类表

所选分类

>> <<

限定检索结果

文献类型

1,541 篇 会议
670 篇 期刊文献
1 册 图书

馆藏范围

2,212 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

1,214 篇 工学
- 918 篇 计算机科学与技术...
- 785 篇 软件工程
- 280 篇 信息与通信工程
- 269 篇 控制科学与工程
- 186 篇 生物工程
- 154 篇 生物医学工程（可授...
- 150 篇 电气工程
- 141 篇 光学工程
- 106 篇 电子科学与技术（可...
- 85 篇 安全科学与工程
- 82 篇 网络空间安全
- 71 篇 机械工程
- 67 篇 交通运输工程
- 64 篇 仪器科学与技术
- 60 篇 化学工程与技术
- 53 篇 动力工程及工程热...
674 篇 理学
- 322 篇 数学
- 215 篇 生物学
- 194 篇 物理学
- 141 篇 统计学（可授理学、...
- 97 篇 化学
327 篇 管理学
- 209 篇 管理科学与工程(可...
- 133 篇 图书情报与档案管...
- 101 篇 工商管理
177 篇 医学
- 138 篇 临床医学
- 125 篇 基础医学(可授医学...
- 102 篇 公共卫生与预防医...
- 66 篇 药学(可授医学、理...
75 篇 法学
- 67 篇 社会学
50 篇 经济学
- 50 篇 应用经济学
49 篇 农学
25 篇 教育学
9 篇 文学
1 篇 哲学
1 篇 历史学
1 篇 军事学
1 篇 艺术学

主题

226 篇 accuracy
139 篇 deep learning
136 篇 real-time system...
114 篇 machine learning
98 篇 training
93 篇 convolutional ne...
89 篇 predictive model...
84 篇 feature extracti...
76 篇 computational mo...
62 篇 medical services
61 篇 support vector m...
57 篇 machine learning...
57 篇 data models
56 篇 internet of thin...
49 篇 reliability
48 篇 optimization
45 篇 artificial intel...
43 篇 reviews
40 篇 prediction algor...
39 篇 monitoring

机构

134 篇 lamarr institute...
59 篇 nitte meenakshi ...
53 篇 university of bo...
52 篇 department of ar...
41 篇 lovely professio...
35 篇 division of arti...
33 篇 the lamarr insti...
31 篇 lamarr institute...
31 篇 department of co...
29 篇 center for robot...
22 篇 machine learning...
21 篇 department of ar...
21 篇 department of ar...
20 篇 department of ar...
20 篇 machine learning...
19 篇 east west instit...
19 篇 department of co...
19 篇 artificial intel...
18 篇 department of ar...
18 篇 australian insti...

作者

60 篇 müller klaus-rob...
51 篇 piyush kumar par...
50 篇 stachniss cyrill
48 篇 pareek piyush ku...
41 篇 prateek verma
35 篇 gall juergen
31 篇 cyrill stachniss
30 篇 behley jens
28 篇 bennewitz maren
24 篇 behnke sven
22 篇 mohsen guizani
18 篇 von lilienfeld o...
18 篇 jens behley
18 篇 verma prateek
16 篇 uma reddy
16 篇 montavon grégoir...
16 篇 magistri federic...
15 篇 cao jiuwen
14 篇 amandeep nagpal
14 篇 maren bennewitz

语言

1,267 篇 英文
943 篇 其他
9 篇 中文
1 篇 斯洛文尼亚文

检索条件"机构=Lamarr Institute for Machine Learning and Artificial Intelligence"

共 2212 条记录，以下是1-10 订阅

全选清除本页清除全部题录导出标记到"检索档案"

详细简洁

排序：

Online Adaptive Local Interpretable Tree Ensembles for Time Series Forecasting 24

Online Adaptive Local Interpretable Tree Ensembles for Time ...

引用

24th IEEE International Conference on Data Mining Workshops, ICDMW 2024

作者： Saadallah, Amal TU Dortmund Lamarr Institute for Machine Learning and Artificial Intelligence Germany

ISBN: (纸本)9798331530631

Thanks to their inherent interpretability, tree models are widely utilized in various learning tasks, including time series forecasting. However, single tree models often suffer from overfitting, limiting their applicability to real-world scenarios. To address this issue, ensembles of tree models are commonly employed. Yet, ensemble construction must account for the dynamic nature of time series, which can be subject to significant changes and the so-called concept drift phenomenon. In this paper, we develop local tree ensembles by specializing individual trees across specific regions in the input time series. We select the trees based on the most recent local pattern and manage their interdependence explicitly to ensure diversity in the ensemble. This is achieved through a carefully designed weighting schema. The trees are updated in an informed manner over time following concept drift detection in the time series. In addition, our approach supports explainability in forecasting tasks. Through extensive empirical evaluation on diverse real-world datasets, our method demonstrates comparable or superior performance to state-of-the-art approaches and several baseline methods. © 2024 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

How to Be Fast and Not Furious: Looking Under the Hood of CPU Cache Prefetching 20

How to Be Fast and Not Furious: Looking Under the Hood of CP...

引用

20th International Workshop on Data Management on New Hardware, DaMoN 2024

作者： Kühn, Roland Mühlig, Jan Teubner, Jens Tu Dortmund University Lamarr Institute for Machine Learning and Artificial Intelligence Germany

ISBN: (纸本)9798400706677

Software-based prefetching is a powerful method for tolerating access penalties that are encountered by data processing systems: memory latency. Although the idea appears straightforward - -simply informing the CPU about upcoming data accesses - -the intricacies of its implementation remain insufficiently understood. Existing works demonstrate how to rewrite algorithms for prefetching, yet they often overlook the limitations and hardware implications of bringing data into the cache hierarchy. In this paper, we examine software-based prefetching thoroughly by delving into its implementation and identifying pitfalls across various platforms. Furthermore, we provide actionable insights and recommendations for developers seeking to boost their applications through this technique. © 2024 Owner/Author.

关键词： Data handling

来源：评论

学校读者我要写书评

暂无评论

DAG Scheduling with Execution Groups 30

DAG Scheduling with Execution Groups

引用

30th IEEE Real-Time and Embedded Technology and Applications Symposium, RTAS 2024

作者： Shi, Junjie Gtinzel, Mario Ueter, Niklas Der Bruggen, Georg Von Chen, Jian-Jia TU Dortmund University Germany Lamarr Institute for Machine Learning and Artificial Intelligence Germany

ISBN: (纸本)9798350358414

In many modern safety-critical cyber-physical sys-Tems, such as in the automotive or robotic domain, the appli-cation complexity requires the use of multi-core platforms to execute all workloads under strict hard real-Time constraints. The sporadic DAG task model is a parallel task model adept at representing tasks comprised of subtasks, which possess internal data flow and precedence constraints induced by synchronization. A significant challenge to the system's performance and its real-Time verification stems from the communication-centric nature of applications in these domains. Inter-core communication, required for data sharing among sub tasks across different cores, depends on either a shared bus or a network-on-chip, culminating in significant overhead due to latency, congestion, and synchronization. To improve performance and reduce these overheads, it is advantageous to execute subtasks, those that either exchange large volumes of data or access the same data, on a singular physical processor, thereby utilizing more efficient intra-core communication. In this paper, we tackle this issue by introducing the DAG task model with execution groups, incorporating a constraint that mandates the execution of grouped sub tasks on the same pro-cessor. We provide an analysis of worst-case response times and propose optimizations for our DAG task model with execution groups, subsequently evaluating our approach against existing solutions. The evaluation results demonstrate that our approach, even with the imposition of group execution constraints, remains competitive in comparison to existing approaches that do not take group execution constraints into account. Additionally, we explore implementation strategies and potential extensions for multi-Task systems. © 2024 IEEE.

关键词： Real time systems

来源：评论

学校读者我要写书评

暂无评论

Online Explainable Forecasting using Regions of Competence

Online Explainable Forecasting using Regions of Competence

引用

2024 Workshop on Explainable AI for Time Series and Data Streams, TempXAI 2024

作者： Saadallah, Amal Jakobs, Matthias Lamarr Institute for Machine Learning and Artificial Intelligence TU Dortmund University Dortmund Germany

Several machine learning models have been applied to time series forecasting. However, it is generally acknowledged that none of these models is universally valid for every application and over time. This is due to the complex and changing nature of time series data that may involve non-stationary processes but can also be explained by the fact that different models have varying expected regions of expertise or so-called Regions of Competence (RoCs) over the time series. Therefore, adequate and adaptive online model selection is often required. In this work, we review online model selection works that exploit the notion of RoCs by summarizing their methods and highlighting their strengths as well as limitations. In particular, we present a taxonomy of these methods and show how they can be exploited for both single model selection and ensemble of models pruning. We additionally discuss how the RoCs can promote explainability. Finally, we suggest future directions to provide useful research guidance. © 2024 CEUR-WS. All rights reserved.

关键词： Prediction models

来源：评论

学校读者我要写书评

暂无评论

Evaluation of Document Deduplication Algorithms for Large Text Corpora 10th

Evaluation of Document Deduplication Algorithms for Large ...

引用

10th International Conference on machine learning, Optimization, and Data Science, LOD 2024

作者： Leveling, Johannes Helmer, Lennard Stein, Benny Joerg Wegener, Dennis Sheikh, Zoha Fernandes, Elanton Abdelwahab, Hammam Sankt Augustin Germany Lamarr Institute for Machine Learning and Artificial Intelligence Sankt Augustin Germany

ISBN: (纸本)9783031824807

Performance of large language models (LLMs) is correlated with diverse and high-quality training data. One aspect of data quality is the presence of duplicate documents in the training data. In this paper, we evaluate five algorithms for deduplicating large data sets, namely MinHash/LSH, Exact Hashes, SimHash, Scalable Bloom filter, and Suffix Array. We report on their precision, recall, memory requirements and runtime on deduplicating OpenSubtitles and Oscar data for five languages (EN, DE, ES, FR, IT). We find that the best overall performance is achieved by using a MinHash/LSH, but other options such as Scalable Bloom filter can be more suitable in resource-critical situations. While precision varies between 0.833 and 0.985 across algorithms, recall varies between 0.247 and 0.989, indicating different levels of aggressiveness. We conclude that MinHash/LSH is the most suitable algorithm to deduplicate pretraining data for LLMs. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Data assimilation

来源：评论

学校读者我要写书评

暂无评论

Sync or Sink' the Robustness of Sensor Fusion Against Temporal Misalignment 30

Sync or Sink' the Robustness of Sensor Fusion Against Tempor...

引用

30th IEEE Real-Time and Embedded Technology and Applications Symposium, RTAS 2024

作者： Kuhse, Daniel Holscher, Nils Gunzel, Mario Teper, Harun Von Der Bruggen, Georg Chen, Jian-Jia Lin, Ching-Chi TU Dortmund University Germany Lamarr Institute for Machine Learning and Artificial Intelligence Germany

ISBN: (纸本)9798350358414

Sensor fusion is the process of combining data from multiple sensors for acquiring a more accurate and comprehensive understanding of the observed environment. However, temporal misalignments between sensors can lead to incorrect fusion results, while the temporal robustness of sensor fusion algorithms is still a relatively unexplored research topic. To address this gap, we define three types of temporal robustness for sensor fusion: reference-point-based, strong sample-point-based, and weak sample-point-based temporal robustness. These definitions provide a framework to quantitatively evaluate the temporal robustness of sensor fusion functions. We also investigate the case where only a part of the sensors are misaligned. Furthermore, we consider potential probabilistic aspects for the proposed definitions. We assess the temporal robustness of a state-of-The-Art fusion method in the context of 3D object detection, where camera and LiDAR data are fused. Our empirical evaluation shows that the examined fusion methods exhibit moderate robustness against temporal misalignment of images, but are especially sensitive to LiDAR misalignment. Our findings call attention to the necessity of providing robustness guarantees for sensor fusion functions against temporal misalignment. © 2024 IEEE.

关键词： Timing circuits

来源：评论

学校读者我要写书评

暂无评论

Finite Combinatory Logic with Predicates 29

Finite Combinatory Logic with Predicates

引用

29th International Conference on Types for Proofs and Programs, TYPES 2023

作者： Dudenhefner, Andrej Stahl, Christoph Chaumet, Constantin Laarmann, Felix Rehof, Jakob TU Dortmund University Germany Lamarr Institute for Machine Learning and Artificial Intelligence Dortmund Germany

ISBN: (纸本)9783959773324

Type inhabitation in extensions of Finite Combinatory Logic (FCL) is the mechanism underlying various component-oriented synthesis frameworks. In FCL inhabitant sets correspond to regular tree languages and vice versa. Therefore, it is not possible to specify non-regular properties of inhabitants, such as (dis)equality of subterms. Additionally, the monomorphic nature of FCL oftentimes hinders concise specification of components. We propose a conservative extension to FCL by quantifiers and predicates, introducing a restricted form of polymorphism. In the proposed type system (FCLP) inhabitant sets correspond to decidable term languages and vice versa. As a consequence, type inhabitation in FCLP is undecidable. Based on results in tree automata theory, we identify a fragment of FCLP with the following two properties. First, the fragment enjoys decidable type inhabitation. Second, it allows for specification of local (dis)equality constraints for subterms of inhabitants. For empirical evaluation, we implement a semi-decision procedure for type inhabitation in FCLP. We compare specification capabilities, scalability, and performance of the implementation to existing FCL-based approaches. Finally, we evaluate practical applicability via a case study, synthesizing mechanically sound robotic arms. © Andrej Dudenhefner, Christoph Stahl, Constantin Chaumet, Felix Laarmann, and Jakob Rehof.

关键词： Computer circuits

来源：评论

学校读者我要写书评

暂无评论

Do Multilingual Large Language Models Mitigate Stereotype Bias 2

Do Multilingual Large Language Models Mitigate Stereotype Bi...

引用

2nd Workshop on Cross-Cultural Considerations in NLP, C3NLP 2024

作者： Nie, Shangrui Fromm, Michael Welch, Charles Görge, Rebekka Karimi, Akbar Plepi, Joan Mowmita, Nazia Afsan Flores-Herr, Nicolas Ali, Mehdi Flek, Lucie Lab University of Bonn Germany Germany Lamarr Institute for Machine Learning and Artificial Intelligence Germany

ISBN: (纸本)9798891761469

While preliminary findings indicate that multilingual LLMs exhibit reduced bias compared to monolingual ones, a comprehensive understanding of the effect of multilingual training on bias mitigation, is lacking. This study addresses this gap by systematically training six LLMs of identical size (2.6B parameters) and architecture: five monolingual models (English, German, French, Italian, and Spanish) and one multilingual model trained on an equal distribution of data across these languages, all using publicly available data. To ensure robust evaluation, standard bias benchmarks were automatically translated into the five target languages and verified for both translation quality and bias preservation by human annotators. Our results consistently demonstrate that multilingual training effectively mitigates bias. Moreover, we observe that multilingual models achieve not only lower bias but also superior prediction accuracy when compared to monolingual models with the same amount of training data, model architecture, and size. © 2024 Association for Computational Linguistics.

关键词： Translation (languages)

来源：评论

学校读者我要写书评

暂无评论

Identifying Spatio-Temporal Drivers of Extreme Events 38

Identifying Spatio-Temporal Drivers of Extreme Events

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Hakam, Mohamad Eddin, Shams Gall, Juergen Institute of Computer Science University of Bonn Lamarr Institute for Machine Learning and Artificial Intelligence United States

The spatio-temporal relations of impacts of extreme events and their drivers in climate data are not fully understood and there is a need of machine learning approaches to identify such spatio-temporal relations from data. The task, however, is very challenging since there are time delays between extremes and their drivers, and the spatial response of such drivers is inhomogeneous. In this work, we propose a first approach and benchmarks to tackle this challenge. Our approach is trained end-to-end to predict spatio-temporally extremes and spatio-temporally drivers in the physical input variables jointly. By enforcing the network to predict extremes from spatio-temporal binary masks of identified drivers, the network successfully identifies drivers that are correlated with extremes. We evaluate our approach on three newly created synthetic benchmarks, where two of them are based on remote sensing or reanalysis climate data, and on two real-world reanalysis datasets. The source code and datasets are publicly available at the project page https://***/IDE. © 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

Epipolar Attention Field Transformers for Bird's Eye View Semantic Segmentation

Epipolar Attention Field Transformers for Bird's Eye View Se...

引用

2025 IEEE/CVF Winter Conference on Applications of Computer Vision, WACV 2025

作者： Witte, Christian Behley, Jens Stachniss, Cyrill Raaijmakers, Marvin Cariad Se Germany University of Bonn Center for Robotics Germany Lamarr Institute for Machine Learning and Artificial Intelligence Germany

ISBN: (纸本)9798331510831

Spatial understanding of the semantics of the surroundings is a key capability needed by autonomous cars to enable safe driving decisions. Recently, purely vision-based solutions have gained increasing research interest. In particular, approaches extracting a bird's eye view (BEV) from multiple cameras have demonstrated great performance for spatial understanding. This paper addresses the dependency on learned positional encodings to correlate image and BEV feature map elements for transformer-based methods. We propose leveraging epipolar geometric constraints to model the relationship between cameras and the BEV by Epipolar Attention Fields. They are incorporated into the attention mechanism as a novel attribution term, serving as an alternative to learned positional encodings. Experiments show that our method EAFormer outperforms previous BEV approaches by 2% mIoU for map semantic segmentation and exhibits superior generalization capabilities compared to implicitly learning the camera configuration. © 2025 IEEE.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

没有更多数据了...

全选清除本页清除全部题录导出标记到“检索档案”

共222页 << < 1 2 3 4 5 6 7 8 9 10 > >>

检索报告对象比较合并检索0

隐藏清空

合并搜索

回到顶部

执行限定条件

内容：

评分：

请选择保存的检索档案：

请选择收藏分类：

订阅名称：

通借通还

温馨提示：

图书名称：

借书校区：

取书校区：

手机号码：

邮箱地址：

一卡通帐号：

电话和邮箱必须正确填写，我们会与您联系确认。

联系人：

所在院系：

联系邮箱：

联系电话：

内蒙古自治区呼和浩特市赛罕区大学西街235号邮编: 010021

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：