检索结果-内蒙古大学图书馆

A fully-customized dataflow engine for 3D earthquake simulation with a complex topography

science China(Information sciences) 2022年第5期65卷 65-80页

作者： Bingwei CHEN Haohuan FU Wayne LUK Guangwen YANG Department of Computer Science and Technology Beijing National Research Center for Information Science and Technology Tsinghua University National Supercomputer Center in Wuxi Ministry of Education Key Laboratory for Earth System Modeling Department of Earth System ScienceTsinghua University Department of Computing Imperial College London

With HPC(high performance computing) evolving into the exascale era, improvements in computing performance and power efficiency have become increasingly more important. Based on our previous work on enabling earthquake simulations on a large scale on Sunway Taihu Light, we further explore other possibilities to improve the application through a fully-customized hardware design on reconfigurable FPGA(field programmable gate array) devices. We investigate the feasibility and the potential benefits of a complete fixed-point design. We first perform a coarse-resolution-based simulation to analyze the representation range and precision needed to capture both the total energy and the energy distribution of variables over space and time. We then derive a complete fixed-point design that identifies the suitable bitwidth for major categories of variables and dynamically represents the range through a dynamic scaling scheme. Finally, we use the optimized fixed-point design to run a case of the Wenchuan earthquake to demonstrate the potential of supporting large-scale scientific simulations on FPGA devices. The results demonstrate that an 18-bit fixed-point design already provides an almost identical description of the seismic events in the Wenchuan scenario down to a single-precision floating-point version and provides sustainable performance equivalent to 13.1 Intel Xeon Gold 6154 18-core CPUs or 2.10 Sunway 260-core processors, with performance per watt(power efficiency) improved by 15.3 and 3.72 times compared with the Intel Xeon Gold 6154 18-core CPUs and the Sunway 260-core processors, respectively.

关键词： reconfigurable computing earthquake simulation FPGA hardware-software co-design architecture exploration

来源：评论

学校读者我要写书评

暂无评论

Space Fusion Xgboost, from Euclidean to Poincaré

SSRN

引用

SSRN 2024年

作者： Suganthan, Ponnuthurai Nagaratnam Kong, Lingping Snášel, Václav Ojha, Varun Aly, Hussein Ahmed Hussein Zaky Department of Computer Science VSB-Technical University of Ostrava Ostrava Czech Republic KINDI Center for Computing Research College of Engineering Qatar University Doha Qatar School of Computing Newcastle University Newcastle United Kingdom

Hyperbolic space has garnered attention for its unique properties and efficient representation of hierarchical structures. Recent studies have explored hyperbolic alternatives to hyperplane-based classifiers, such as logistic regression and support vector machines. They have even fused hyperbolic into random forests by constructing data splits with horosphere, which proved effective for hyperbolic datasets. However, the existing incorporation of the horosphere leads to substantial computation times, diverting attention from its application on most datasets. Against this backdrop, we introduce an extension of Xgboost, a renowned machine learning (ML) algorithm, to hyperbolic space, denoted as PXgboost. This extension involves a redefinition of the node split concept using the Riemannian gradient and Riemannian Hessian. Through comprehensive experiments conducted on 64 datasets from the UCI ML repository and 8 datasets from WordNet, fusing both their Euclidean and hyperbolic-transformed (hyperbolic UCI) representations, our findings unveil the promising performance of PXgboost compared to algorithms in the literature. Furthermore, our findings suggest that the Euclidean metric-based classifier performs well even on hyperbolic data. Building upon the above finding, we propose a space fusion classifier, EPboost, that harmonizes data processing across various spaces and integrates probability outcomes for predictive analysis. In our comparative analysis involving 19 algorithms on the UCI dataset, our EPboost outperforms others in most cases, underscoring its efficacy and potential significance in diverse ML applications. This research marks a step forward in harnessing hyperbolic geometry for ML tasks, showcasing its potential to enhance algorithmic efficacy. © 2024, The Authors. All rights reserved.

关键词： Logistic regression

来源：评论

学校读者我要写书评

暂无评论

Prototypical Residual Networks for Anomaly Detection and Localization

Prototypical Residual Networks for Anomaly Detection and Loc...

引用

Conference on computer Vision and Pattern Recognition (CVPR)

作者： Hui Zhang Zuxuan Wu Zheng Wang Zhineng Chen Yu-Gang Jiang Shanghai Key Lab of Intell. Info. Processing School of CS Fudan University Shanghai Collaborative Innovation Center of Intelligent Visual Computing School of Computer Science Zhejiang University of Technology

Anomaly detection and localization are widely used in industrial manufacturing for its efficiency and effectiveness. Anomalies are rare and hard to collect and supervised models easily over-fit to these seen anomalies with a handful of abnormal samples, producing unsatisfactory performance. On the other hand, anomalies are typically subtle, hard to discern, and of various appearance, making it difficult to detect anomalies and let alone locate anomalous regions. To address these issues, we propose a framework called Prototypical Residual Network (PRN), which learns feature residuals of varying scales and sizes between anomalous and normal patterns to accurately reconstruct the segmentation maps of anomalous regions. PRN mainly consists of two parts: multi-scale prototypes that explicitly represent the residual features of anomalies to normal patterns; a multisize self-attention mechanism that enables variable-sized anomalous feature learning. Besides, we present a variety of anomaly generation strategies that consider both seen and unseen appearance variance to enlarge and diversify anomalies. Extensive experiments on the challenging and widely used MVTec AD benchmark show that PRN outperforms current state-of-the-art unsupervised and supervised methods. We further report SOTA results on three additional datasets to demonstrate the effectiveness and generalizability of PRN.

关键词：

来源：评论

学校读者我要写书评

暂无评论

EFFICIENT NONLINEAR MULTISCALE SPECTRAL GFEM APPLIED TO COMPOSITE AEROSPACE STRUCTURES 23

EFFICIENT NONLINEAR MULTISCALE SPECTRAL GFEM APPLIED TO COMP...

引用

23rd International Conference on Composite Materials, ICCM 2023

作者： Bénézech, J. Seelinger, L. Reinarz, A. Dodwell, T.J. Butler, R. Scheichl, R. Material & Structure Research Centre University of Bath Bath United Kingdom Interdisciplinary Center for Scientific Computing Institute for Applied Mathematics Heidelberg University Heidelberg Germany Department of Computer Science Durham University Durham United Kingdom Institute of Data Science and AI University of Exeter Exeter United Kingdom DigiLab Exeter United Kingdom

来源：评论

学校读者我要写书评

暂无评论

Cutting-Edge Predictive Methods for Enhancing Short-Term Load Prediction

Cutting-Edge Predictive Methods for Enhancing Short-Term Loa...

引用

2024 International Conference on Electrical and computer Engineering Researches, ICECER 2024

作者： Ghazal, Taher M. Janjua, Jamshaid Iqbal Abushiba, Walid Ahmad, Munir Abbas, Tahir Ateeq, Karamath College of Arts & Science Applied Science University P.O.Box 5055 Manama Bahrain Universiti Kebangsaan Malaysia Center for Cyber Security Faculty of Information Science and Technology Bangi Selangor Malaysia Lahore Pakistan College of Engineering Applied Science University Bahrain College of Informatics Korea University Seoul02841 Korea Republic of TIMES Institute Department of Computer Science Multan Pakistan School of Computing Skyline University College University City Sharjah Sharjah United Arab Emirates

ISBN: (纸本)9798331539733

Efficient management and cost-related factors in the power sector call for accurate short-term load forecasting as it enables better planning with the electric grid and achieving stability within it. This paper looks into the state-of-the-art forecasting strategies that enhance load forecasts made in shorter time frames. Such techniques include but are not limited to machine learning applications, effective data models, and multi-dimensional modeling leveraging historical, meteorological, and economic data. Their review is carried out in detail with their advantages and disadvantages and their application in practice. Furthermore, this study strives to understand the barriers that need to be overcome in the quest to increase the accuracy of the forecasting models especially concerning renewable energy sources. We illustrate how new trends relate to future developments of predictive models about supporting the decision-making in operating power systems and improving the reliability and sustainability of energy systems. © 2024 IEEE.

关键词： Prediction models

来源：评论

学校读者我要写书评

暂无评论

Adaptive Split-Fusion Transformer

Adaptive Split-Fusion Transformer

引用

IEEE International Conference on Multimedia and Expo (ICME)

作者： Zixuan Su Jingjing Chen Lei Pang Chong-Wah Ngo Yu-Gang Jiang Shanghai Key Lab of Intelligent Information Processing School of Computer Science Fudan University Shanghai Collaborative Innovation Center of Intelligent Visual Computing City University of Hong Kong Singapore Management University

Neural networks for visual content understanding have recently evolved from convolutional ones to transformers. The prior (CNN) relies on small-windowed kernels to capture the regional clues, demonstrating solid local expressiveness. On the contrary, the latter (transformer) establishes long-range global connections between localities for holistic learning. Inspired by this complementary nature, there is a growing interest in designing hybrid models which utilize both techniques. Current hybrids merely replace convolutions as simple approximations of linear projection or juxtapose a convolution branch with attention without considering the importance of local/global modeling. To tackle this, we propose a new hybrid named Adaptive Split-Fusion Transformer (ASF-former) that treats convolutional and attention branches differently with adaptive weights. Specifically, an ASF-former encoder equally splits feature channels into half to fit dual-path inputs. Then, the outputs of the dual-path are fused with weights calculated from visual cues. We also design a compact convolutional path from a concern of efficiency. Extensive experiments on standard benchmarks show that our ASF-former outperforms its CNN, transformer, and hybrid counterparts in terms of accuracy (83.9% on ImageNet-1K), under similar conditions (12.9G MACs / 56.7M Params, without large-scale pre-training). The code is available at: https://***/szx503045266/ASF-former.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Large Model for Small Data: Foundation Model for Cross-Modal RF Human Activity Recognition

arXiv

引用

arXiv 2024年

作者： Weng, Yuxuan Wu, Guoquan Zheng, Tianyue Yang, Yanbing Luo, Jun Department of Computer Science and Engineering Southern University of Science and Technology China Smart City Center Research Institute of Trustworthy Autonomous Systems Southern University of Science and Technology China College of Computer Science Sichuan University China College of Computing and Data Science Nanyang Technological University Singapore

Radio-Frequency (RF)-based Human Activity Recognition (HAR) rises as a promising solution for applications unamenable to techniques requiring computer visions. However, the scarcity of labeled RF data due to their non-interpretable nature poses a significant obstacle. Thanks to the recent breakthrough of foundation models (FMs), extracting deep semantic insights from unlabeled visual data become viable, yet these vision-based FMs fall short when applied to small RF datasets. To bridge this gap, we introduce FM-Fi, an innovative cross-modal framework engineered to translate the knowledge of vision-based FMs for enhancing RF-based HAR systems. FM-Fi involves a novel cross-modal contrastive knowledge distillation mechanism, enabling an RF encoder to inherit the interpretative power of FMs for achieving zero-shot learning. It also employs the intrinsic capabilities of FM and RF to remove extraneous features for better alignment between the two modalities. The framework is further refined through metric-based few-shot learning techniques, aiming to boost the performance for predefined HAR tasks. Comprehensive evaluations evidently indicate that FM-Fi rivals the effectiveness of vision-based methodologies, and the evaluation results provide empirical validation of FM-Fi’s generalizability across various environments. © 2024, CC BY.

关键词： Zero-shot learning

来源：评论

学校读者我要写书评

暂无评论

How Robust is GPT-3.5 to Predecessors? A Comprehensive Study on Language Understanding Tasks

arXiv

引用

arXiv 2023年

作者： Chen, Xuanting Ye, Junjie Zu, Can Xu, Nuo Zheng, Rui Peng, Minlong Zhou, Jie Gui, Tao Zhang, Qi Huang, Xuanjing School of Computer Science Fudan University Shanghai China Institute of Modern Languages and Linguistics Fudan University Shanghai China Shanghai Collaborative Innovation Center of Intelligent Visual Computing Fudan University China

The GPT-3.5 models have demonstrated impressive performance in various Natural Language Processing (NLP) tasks, showcasing their strong understanding and reasoning capabilities. However, their robustness and abilities to handle various complexities of the open world have yet to be explored, which is especially crucial in assessing the stability of models and is a key aspect of trustworthy AI. In this study, we perform a comprehensive experimental analysis of GPT-3.5, exploring its robustness using 21 datasets (about 116K test samples) with 66 text transformations from TextFlint that cover 9 popular Natural Language Understanding (NLU) tasks. Our findings indicate that while GPT-3.5 outperforms existing fine-tuned models on some tasks, it still encounters significant robustness degradation, such as its average performance dropping by up to 35.74% and 43.59% in natural language inference and sentiment analysis tasks, respectively. We also show that GPT-3.5 faces some specific robustness challenges, including robustness instability, prompt sensitivity, and number sensitivity. These insights are valuable for understanding its limitations and guiding future research in addressing these challenges to enhance GPT-3.5’s overall performance and generalization *** Codes 68-06 Copyright © 2023, The Authors. All rights reserved.

关键词： Sentiment analysis

来源：评论

学校读者我要写书评

暂无评论

Imaging Interiors: An Implicit Solution to Electromagnetic Inverse Scattering Problems

arXiv

引用

arXiv 2024年

作者： Luo, Ziyuan Shi, Boxin Li, Haoliang Wan, Renjie Department of Computer Science Hong Kong Baptist University Hong Kong National Key Laboratory for Multimedia Information Processing School of Computer Science Peking University China National Engineering Research Center of Visual Technology School of Computer Science Peking University China Department of Electrical Engineering City University of Hong Kong Hong Kong

Electromagnetic Inverse Scattering Problems (EISP) have gained wide applications in computational imaging. By solving EISP, the internal relative permittivity of the scatterer can be non-invasively determined based on the scattered electromagnetic fields. Despite previous efforts to address EISP, achieving better solutions to this problem has remained elusive, due to the challenges posed by inversion and discretization. This paper tackles those challenges in EISP via an implicit approach. By representing the scatterer’s relative permittivity as a continuous implicit representation, our method is able to address the low-resolution problems arising from discretization. Further, optimizing this implicit representation within a forward framework allows us to conveniently circumvent the challenges posed by inverse estimation. Our approach outperforms existing methods on standard benchmark datasets. Copyright © 2024, The Authors. All rights reserved.

关键词： Electromagnetic fields

来源：评论

学校读者我要写书评

暂无评论

Deep Graph Anomaly Detection: A Survey and New Perspectives

arXiv

引用

arXiv 2024年

作者： Qiao, Hezhe Tong, Hanghang An, Bo King, Irwin Aggarwal, Charu Pang, Guansong School of Computing and Information Systems Singapore Management University Singapore Department of Computer Science University of Illinois Urbana-Champaign United States College of Computing and Data Science Nanyang Technological University Singapore Department of Computer Science & Engineering Chinese University of Hong Kong Hong Kong IBM T. J. Watson Research Center United States

Graph anomaly detection (GAD), which aims to identify unusual graph instances (e.g., nodes, edges, subgraphs, or graphs), has attracted increasing attention in recent years due to its significance in a wide range of applications. Deep learning approaches, graph neural networks (GNNs) in particular, have been emerging as a promising paradigm for GAD, owing to its strong capability in capturing complex structure and/or node attributes in graph data. Considering the large number of methods proposed for GNN-based GAD, it is of paramount importance to summarize the methodologies and findings in the existing GAD studies, so that we can pinpoint effective model designs for tackling open GAD problems. To this end, in this work we aim to present a comprehensive review of deep learning approaches for GAD. Existing GAD surveys are focused on task-specific discussions, making it difficult to understand the technical insights of existing methods and their limitations in addressing some unique challenges in GAD. To fill this gap, we first discuss the problem complexities and their resulting challenges in GAD, and then provide a systematic review of current deep GAD methods from three novel perspectives of methodology, including GNN backbone design, proxy task design for GAD, and graph anomaly measures. To deepen the discussions, we further propose a taxonomy of 13 fine-grained method categories under these three perspectives to provide more in-depth insights into the model designs and their capabilities. To facilitate the experiments and validation of the GAD methods, we also summarize a collection of widely-used datasets for GAD and empirical performance comparison on these datasets. We further discuss multiple important open research problems in GAD to inspire more future high-quality research in this area. A continuously updated repository for GAD datasets, links to the codes of GAD algorithms, and empirical comparison is available at https://***/mala-lab/Awesome-Deep-G

关键词： Contrastive Learning

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：