检索结果-内蒙古大学图书馆

Proceedings of the 41st International Conference on Machine Learning

作者： Dimitri von Rütte Sotiris Anagnostidis Gregor Bachmann Thomas Hofmann Data Analytics Lab Department of Computer Science ETH Zurich

Concept guidance has emerged as a cheap and simple way to control the behavior of language models by probing their hidden representations for concept vectors and using them to perturb activations at inference time. While the focus of previous work has largely been on truthfulness, in this paper we extend this framework to a richer set of concepts such as appropriateness, humor, creativity and quality, and explore to what degree current detection and guidance strategies work in these challenging settings. To facilitate evaluation, we develop a novel metric for concept guidance that takes into account both the success of concept elicitation as well as the potential degradation in fluency of the guided model. Our extensive experiments reveal that while some concepts such as truthfulness more easily allow for guidance with current techniques, novel concepts such as appropriateness or humor either remain difficult to elicit, need extensive tuning to work, or even experience confusion. Moreover, we find that probes with optimal detection accuracies do not necessarily make for the optimal guides, contradicting previous observations for truthfulness. Our work warrants a deeper investigation into the interplay between detectability, guidability, and the nature of the concept, and we hope that our rich experimental test-bed for guidance research inspires stronger follow-up approaches.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Privacy-Preserving E-Voting System Using Blockchain and Linkable Ring Signatures 1

A Privacy-Preserving E-Voting System Using Blockchain and Li...

引用

1st International Conference on Innovative and Intelligent Information Technologies, IC3IT 2024

作者： Berkani, Ahmed-Sami Moumen, Hamouma Benharzallah, Saber Achouri, Youssouf Kechadi, Mohand Tahar Lamie Laboratory University of Batna 2 Department of Computer Science Batna Algeria LaSTIC Laboratory University of Batna 2 Department of Computer Science Batna Algeria School of Computer Science University College Dublin Insight Centre for Data Analytics Belfield Ireland

ISBN: (纸本)9798331541064

In this work we propose a privacy-preserving, blockchain-enabled e-voting system that integrates Linkable Ring Signatures (LRS) to ensure a secure, scalable, and privacypreserving solution for modern e-voting, providing a framework for trusted and transparent electoral processes in the digital age. Our system ensures voter anonymity while preventing double voting through the use of a linkability tag, while blockchain technology is employed to provide an immutable and transparent ledger for vote recording. The InterPlanetary File System (IPFS) is utilized for decentralized and GDPR-compliant storage of public keys. Performance analysis shows scalability challenges for LRS in large elections, but the system remains efficient for small scale use. Future work will focus on optimizing scalability for larger deployments. © 2024 IEEE.

关键词： Differential privacy

来源：评论

学校读者我要写书评

暂无评论

Deciphering boundary layer dynamics in high-Rayleigh-number convection using 3360 GPUs and a high-scaling in-situ workflow

arXiv

引用

arXiv 2025年

作者： Bode, Mathis Alvarez, Damian Fischer, Paul Frouzakis, Christos E. Göbbert, Jens Henrik Insley, Joseph A. Lan, Yu-Hsiang Mateevitsi, Victor A. Min, Misun Papka, Michael E. Rizzi, Silvio Samuel, Roshan J. Schumacher, Jörg Jülich Supercomputing Centre Forschungszentrum Jülich GmbH Jülich52425 Germany Siebel School of Computing and Data Science University of Illinois at Urbana-Champaign 201 N Goodwin Ave UrbanaIL61801 United States Mathematics and Computer Science Division Argonne National Laboratory 9700 S Cass Ave LemontIL60439 United States CAPS Laboratory Department of Mechanical and Process Engineering ETH Zürich Zürich8092 Switzerland Argonne Leadership Computing Facility Argonne National Laboratory 9700 S Cass Ave LemontIL60439 United States Electronic Visualization Laboratory University of Illinois Chicago 1200 W Harrison St ChicagoIL60607 United States Institute of Thermodynamics and Fluid Mechanics Technische Universität Ilmenau P.O. Box 100565 Ilmenau98684 Germany Tandon School of Engineering New York University New York CityNY11201 United States

Turbulent heat and momentum transfer processes due to thermal convection cover many scales and are of great importance for several natural and technical flows. One consequence is that a fully resolved three-dimensional analysis of these turbulent transfers at high Rayleigh numbers, which includes the boundary layers, is possible only using supercomputers. The visualization of these dynamics poses an additional hurdle since the thermal and viscous boundary layers in thermal convection fluctuate strongly. In order to track these fluctuations continuously, data must be tapped at high frequency for visualization, which is difficult to achieve using conventional methods. This paper makes two main contributions in this context. First, it discusses the simulations of turbulent Rayleigh-Bénard convection up to Rayleigh numbers of Ra = 1012 computed with NekRS on GPUs. The largest simulation was run on 840 nodes with 3360 GPU on the JUWELS Booster supercomputer. Secondly, an in-situ workflow using ASCENT is presented, which was successfully used to visualize the high-frequency turbulent fluctuations. © 2025, CC BY.

关键词： Rayleigh number

来源：评论

学校读者我要写书评

暂无评论

A Language Model’s Guide Through Latent Space

arXiv

引用

arXiv 2024年

作者： von Rütte, Dimitri Anagnostidis, Sotiris Bachmann, Gregor Hofmann, Thomas Data Analytics Lab Department of Computer Science ETH Zurich Switzerland

关键词： Optimal detection

来源：评论

学校读者我要写书评

暂无评论

Multiresolution similarity search in time series data: An application to EEG signals 13

Multiresolution similarity search in time series data: An ap...

引用

6th ACM International Conference on PErvasive Technologies Related to Assistive Environments, PETRA 2013

作者： Charisi, Amalia Malliaros, Fragkiskos D. Zacharaki, Evangelia I. Megalooikonomou, Vasileios Department of Computer Engineering and Informatics University of Patras Greece Computer Science Laboratory École Polytechnique France Center for Data Analytics and Biomedical Informatics Temple University PA United States

ISBN: (纸本)9781450319737

Time series constitute a prevalent data type that arise in several diverse disciplines (e.g., biomedical data, sensor data, images, video data), and therefore analyzing time series is a significant task with a plethora of important applications. In this paper, we study the general problem of similarity search in time series databases and we propose a novel multiresolution indexing (i.e., representation) and retrieval method for time series similarity search. Our approach is motivated by the idea that if we examine a time series at different resolution levels, we could possibly acquire further insights about the data. The proposed algorithm adopts a combined, two-step pruning (filtering) strategy to further reduce data dimensionality by discarding irrelevant time series (i.e., false alarms). At a first level, the time series are represented by line segments and filtered by the triangular inequality property. Then, a Vector Quantization like scheme is applied to encode data and thus to reduce dimensionality. We test and demonstrate the performance of the proposed method, analyzing EEG time series data for retrieval of one of the constituent brain waveforms in EEG recordings, the K-complex, but the method can as well be applied for retrieval of other patterns of interest in time series analysis. The automatic detection and categorization of the EEG patterns will allow the advanced correlation analysis of large amounts of data and will lead to advanced decision making capabilities assisting diagnosis by medical professionals. © 2013 ACM.

关键词： Decision making

来源：评论

学校读者我要写书评

暂无评论

Factorizing time-aware multi-way tensors for enhancing semantic wearable sensing 21

Factorizing time-aware multi-way tensors for enhancing seman...

引用

21st International Conference on MultiMedia Modeling, MMM 2015

作者： Wang, Peng Smeaton, Alan F. Gurrin, Cathal National Laboratory for Information Science and Technology Department of Computer Science and Technology Tsinghua University China Insight Centre for Data Analytics Dublin City University Glasnevin Dublin 9 Ireland

ISBN: (纸本)9783319144443

Automatic concept detection is a crucial aspect of automatically indexing unstructured multimedia archives. However, the current prevalence of one-per-class detectors neglect inherent concept relationships and operate in isolation. This is insufficient when analyzing content gathered from wearable visual sensing, in which concepts occur with high diversity and with correlation depending on context. This paper presents a method to enhance concept detection results by constructing and factorizing a multi-way concept detection tensor in a time-aware manner. We derived a weighted non-negative tensor factorization algorithm and applied it to model concepts’ temporal occurrence patterns and show how it boosts overall detection performance. The potential of our method is demonstrated on lifelog datasets with varying levels of original concept detection accuracies. © Springer International Publishing Switzerland 2015.

关键词： Tensors

来源：评论

学校读者我要写书评

暂无评论

Corrections to “A Modified Singular Value Decomposition (MSVD) Approach for the Enhancement of CCTV Low-Quality Images”

引用

IEEE Access 2025年 13卷 25663-25663页

作者： Shahzada Fahad Sami Ur Rahman Fakhre Alam Muhammad Yousaf Faten S. Alamri Naveed Abbas Saeed Ali Bahaj Amjad R. Khan Department of Computer Science and IT University of Malakand Chakdara Dir Lower Khyber Pakhtunkhwa Pakistan Department of Mathematical Sciences College of Science Princess Nourah bint Abdulrahman University P.O.Box 84428 Riyadh Saudi Arabia Department of Computer Science Islamia College University Peshawar Pakistan MIS Department College of Business Administration Prince Sattam Bin Abdulaziz University Al-Kharj Saudi Arabia Artificial Intelligence and Data Analytics Laboratory (AIDA) CCIS Prince Sultan University Riyadh Saudi Arabia

Presents corrections to the paper, Corrections to “A Modified Singular Value Decomposition (MSVD) Approach for the Enhancement of CCTV Low-Quality Images”.

关键词： Singular value decomposition

来源：评论

学校读者我要写书评

暂无评论

Swarm-LSTM: Condition Monitoring of Gearbox Fault Diagnosis Based on Hybrid LSTM Deep Neural Network Optimized by Swarm Intelligence Algorithms

引用

computers, Materials & Continua 2021年第2期66卷 2041-2059页

作者： Gopi Krishna Durbhaka Barani Selvaraj Mamta Mittal Tanzila Saba Amjad Rehman Lalit Mohan Goyal School of Electrical and Electronics Sathyabama Institute of Science and TechnologyChennai600119India Department of Computer Science and Engineering G.B.Pant Government Engineering CollegeNew Delhi110020India Artificial Intelligence and Data Analytics(AIDA)Laboratory CCISPrince Sultan UniversityRiyadh11586Saudi Arabia Department of Computer Engineering J.C.Bose University of Science and TechnologyFaridabad121006India

Nowadays,renewable energy has been emerging as the major source of energy and is driven by its aggressive expansion and falling *** of the renewable energy sources involve turbines and their operation and maintenance are vital and a difficult *** monitoring and fault diagnosis have seen remarkable and revolutionary up-gradation in approaches,practices and technology during the last *** mostly do use a rotating type of machinery and analysis of those signals has been challenging to localize the *** paper proposes a new hybrid model wherein multiple swarm intelligence models have been evaluated to optimize the conventional Long Short-Term Memory(LSTM)model in classifying the faults from the vibration signals data acquired from the *** helps to analyze the performance and behavioral patterns of the system more effectively and efficiently which helps to suggest for replacement of the unit with higher *** results have demonstrated that the proposed hybrid modeling approach is effective in classifying the faults of the gearbox from the time series data and achieve higher diagnostic accuracy in comparison to the conventional LSTM methods.

关键词： Gearbox long short term memory fault classification swarm intelligence optimization condition monitoring

来源：评论

学校读者我要写书评

暂无评论

Towards training-free refinement for semantic indexing of visual media 22nd

Towards training-free refinement for semantic indexing of vi...

引用

22nd International Conference on MultiMedia Modeling, MMM 2016

作者： Wang, Peng Sun, Lifeng Yang, Shiqang Smeaton, Alan F. National Laboratory for Information Science and Technology Department of Computer Science and Technology Tsinghua University Beijing China Insight Centre for Data Analytics Dublin City University Glasnevin Dublin 9 Ireland

ISBN: (纸本)9783319276700

Indexing of visual media based on content analysis has now moved beyond using individual concept detectors and there is now a focus on combining concepts or post-processing the outputs of individual concept detection. Due to the limitations and availability of training corpora which are usually sparsely and imprecisely labeled, training-based refinement methods for semantic indexing of visual media suffer in correctly capturing relationships between concepts, including co-occurrence and ontological relationships. In contrast to training-dependent methods which dominate this field, this paper presents a training-free refinement (TFR) algorithm for enhancing semantic indexing of visual media based purely on concept detection results, making the refinement of initial concept detections based on semantic enhancement, practical and flexible. This is achieved using global and temporal neighbourhood information inferred from the original concept detections in terms of weighted nonnegative matrix factorization and neighbourhood-based graph propagation, respectively. Any available ontological concept relationships can also be integrated into this model as an additional source of external a priori knowledge. Experiments on two datasets demonstrate the efficacy of the proposed TFR solution. © Springer International Publishing Switzerland 2016.

关键词： Matrix algebra

来源：评论

学校读者我要写书评

暂无评论

What are the limits to time series based recognition of semantic concepts? 22nd

What are the limits to time series based recognition of sema...

引用

22nd International Conference on MultiMedia Modeling, MMM 2016

作者： Wang, Peng Sun, Lifeng Yang, Shiqiang Smeaton, Alan F. National Laboratory for Information Science and Technology Department of Computer Science and Technology Tsinghua University Beijing China Insight Centre for Data Analytics Dublin City University Glasnevin Dublin 9 Ireland

ISBN: (纸本)9783319276731

Most concept recognition in visual multimedia is based on relatively simple concepts, things which are present in the image or video. These usually correspond to objects which can be identified in images or individual frames. Yet there is also a need to recognise semantic concepts which have a temporal aspect corresponding to activities or complex events. These require some form of time series for recognition and also require some individual concepts to be detected so as to utilise their time-varying features, such as co-occurrence and re-occurrence patterns. While results are reported in the literature of using concept detections which are relatively specific and static, there are research questions which remain unanswered. What concept detection accuracies are satisfactory for time series recognition? Can recognition methods perform equally well across various concept detection performances? What affecting factors need to be taken into account when building concept-based high-level event/activity recognitions? In this paper, we conducted experiments to investigate these questions. Results show that though improving concept detection accuracies can enhance the recognition of time series based concepts, they do not need to be very accurate in order to characterize the dynamic evolution of time series if appropriate methods are used. Experimental results also point out the importance of concept selection for time series recognition, which is usually ignored in the current literature. © Springer International Publishing Switzerland 2016.

关键词： Time series

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：