检索结果-内蒙古大学图书馆

SSRN 2024年

作者： Zhai, Zheng Zhang, Jiali Wang, Haiyu Wu, Mingxin Yang, Keshun Qiao, Xiaoyan Sun, Qiang Beijing Normal University No.18 Jinfeng Road Guangdong Zhuhai519087 China Shandong Technology and Business University Shandong Yantai China Yantai Key Laboratory of Big Data Modeling and Intelligent Computing Shandong China Immersion Technology and Evaluation Shandong Engineering Research Center Shandong China School of Mathematics Sichuan University Chengdu China College of Liberal Arts and Sciences University of Illinois Urbana-Champaign IL United States Department of Statistical Sciences University of Toronto ON Canada Department of Computer Science University of Toronto ON Canada Department of Statistics and Data Science MBZUAI Abu Dhabi United Arab Emirates

This paper investigates the limitations of the widely adopted softmax cross-entropy loss in incremental learning problems. Specifically, we highlight how the shift-invariant property of this loss function can lead to multiple optimal solutions and imbalanced weights across different tasks, which exacerbates catastrophic forgetting. To address these issues, we propose two key modifications to the objective function: (1) regularizing or replacing the original joint distillation loss with a summation of task-specific distillation losses, and/or (2) utilizing a shift-sensitive prediction loss function, such as the binary cross-entropy loss. Numerical experiments validate the effectiveness of these proposals, demonstrating improved prediction accuracy and a significant reduction in forgetting. © 2024, The Authors. All rights reserved.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

P-FedAvg: Parallelizing federated learning with theoretical guarantees 40

P-FedAvg: Parallelizing federated learning with theoretical ...

引用

40th IEEE Conference on computer Communications, INFOCOM 2021

作者： Zhong, Zhicong Zhou, Yipeng Wu, Di Chen, Xu Chen, Min Li, Chao Sheng, Quan Z. Sun Yat-Sen University School of Computer Science and Engineering Guangzhou510006 China Guangdong Key Laboratory of Big Data Analysis and Processing Guangzhou510006 China PCL Research Center of Networks and Communications Peng Cheng Laboratory Shenzhen518000 China Department of Computing Macquarie University SydneyNSW2109 Australia School of Computer Science and Technology Huazhong University of Science and Technology Wuhan430074 China Tencent Technology Co. Ltd Shenzhen China

ISBN: (纸本)9780738112817

With the growth of participating clients, the centralized parameter server (PS) will seriously limit the scale and efficiency of Federated Learning (FL). A straightforward approach to scale up the FL system is to construct a Parallel FL (PFL) system with multiple PSes. However, it is unclear whether PFL can really achieve a faster convergence rate or not. Even if the answer is yes, it is non-trivial to design a highly efficient parameter average algorithm for a PFL system. In this paper, we propose a completely parallelizable FL algorithm called P-FedAvg under the PFL architecture. P-FedAvg extends the well-known FedAvg algorithm by allowing multiple PSes to cooperate and train a learning model together. In P-FedAvg, each PS is only responsible for a fraction of total clients, but PSes can mix model parameters in a dedicatedly designed way so that the FL model can well converge. Different from heuristic-based algorithms, P-FedAvg is with theoretical guarantees. To be rigorous, we conduct theoretical analysis on the convergence rate of P-FedAvg, and derive the optimal weights for each PS to mix parameters with its neighbors. We also examine how the overlay topology formed by PSes affects the convergence rate and robustness of a PFL system. Lastly, we perform extensive experiments with real datasets to verify our analysis and demonstrate that P-FedAvg can significantly improve convergence rates than traditional FedAvg and other competitive baselines. We believe that our work can help to lay a theoretical foundation for building more efficient PFL systems. © 2021 IEEE.

关键词： Network topology

来源：评论

学校读者我要写书评

暂无评论

Artificial intelligence for modelling infectious disease epidemics

引用

Nature 2025年第8051期638卷 623-635页

作者： Kraemer, Moritz U. G. Tsui, Joseph L.-H. Chang, Serina Y. Lytras, Spyros Khurana, Mark P. Vanderslott, Samantha Bajaj, Sumali Scheidwasser, Neil Curran-Sebastian, Jacob Liam Semenova, Elizaveta Zhang, Mengyan Unwin, H. Juliette T. Watson, Oliver J. Mills, Cathal Dasgupta, Abhishek Ferretti, Luca Scarpino, Samuel V. Koua, Etien Morgan, Oliver Tegally, Houriiyah Paquet, Ulrich Moutsianas, Loukas Fraser, Christophe Ferguson, Neil M. Topol, Eric J. Duchêne, David A. Stadler, Tanja Kingori, Patricia Parker, Michael J. Dominici, Francesca Shadbolt, Nigel Suchard, Marc A. Ratmann, Oliver Flaxman, Seth Holmes, Edward C. Gomez-Rodriguez, Manuel Schölkopf, Bernhard Donnelly, Christl A. Pybus, Oliver G. Cauchemez, Simon Bhatt, Samir Pandemic Sciences Institute University of Oxford Oxford United Kingdom Department of Biology University of Oxford Oxford United Kingdom Department of Electrical Engineering and Computer Science University of California Berkeley Berkeley CA United States UCSF UC Berkeley Joint Program in Computational Precision Health Berkeley CA United States Division of Systems Virology Department of Microbiology and Immunology The Institute of Medical Science The University of Tokyo Tokyo Japan Section of Epidemiology Department of Public Health University of Copenhagen Copenhagen Denmark Oxford Vaccine Group University of Oxford and NIHR Oxford Biomedical Research Centre Oxford United Kingdom Department of Epidemiology and Biostatistics Imperial College London London United Kingdom Department of Computer Science University of Oxford Oxford United Kingdom School of Mathematics University of Bristol Bristol United Kingdom MRC Centre for Global Infectious Disease Analysis School of Public Health Imperial College London London United Kingdom Department of Statistics University of Oxford Oxford United Kingdom Doctoral Training Centre University of Oxford Oxford United Kingdom Institute for Experiential AI Northeastern University MA Boston Thailand Santa Fe Institute Santa Fe NM United States World Health Organization Regional Office for Africa Brazzaville Congo WHO Hub for Pandemic and Epidemic Intelligence Health Emergencies Programme World Health Organization Berlin Germany Centre for Epidemic Response and Innovation (CERI) School for Data Science and Computational Thinking Stellenbosch University Stellenbosch South Africa African Institute for Mathematical Sciences (AIMS) South Africa Muizenberg Cape Town South Africa Genomics England London United Kingdom Scripps Research La Jolla CA United States Department of Biosystems Science and Engineering ETH Zürich Basel Switzerland Swiss Institute of Bioinformatics Lausanne Switzerland The Ethox Centre Nuffield

Infectious disease threats to individual and public health are numerous, varied and frequently unexpected. Artificial intelligence (ai) and related technologies, which are already supporting human decision making in economics, medicine and social science, have the potential to transform the scope and power of infectious disease epidemiology. Here we consider the application to infectious disease modelling of ai systems that combine machine learning, computational statistics, information retrieval and data science. We first outline how recent advances in ai can accelerate breakthroughs in answering key epidemiological questions and we discuss specific ai methods that can be applied to routinely collected infectious disease surveillance data. Second, we elaborate on the social context of ai for infectious disease epidemiology, including issues such as explainability, safety, accountability and ethics. Finally, we summarize some limitations of ai applications in this field and provide recommendations for how infectious disease epidemiology can harness most effectively current and future developments in ai. © Springer Nature Limited 2025.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Navigating the Noise: Bringing Clarity to ML Parameterization Design with O(100) Ensembles

arXiv

引用

arXiv 2023年

作者： Lin, Jerry Yu, Sungduk Peng, Liran Beucler, Tom Wong-Toi, Eliot Hu, Zeyuan Gentine, Pierre Geleta, Margarita Pritchard, Mike Department of Earth System Sciences University of California at Irvine IrvineCA United States Multimodal Cognitive AI Intel Labs Santa ClaraCA95054 United States Faculty of Geosciences and Environment University of Lausanne Lausanne Switzerland Expertise Center for Climate Extremes University of Lausanne Lausanne Switzerland Department of Statistics University of California at Irvine IrvineCA United States Department of Earth and Planetary Sciences Harvard University United States NVIDIA Research United States LEAP Science and Technology Center School of Engineering and Applied Sciences Climate School Columbia University United States Department of Electrical Engineering and Computer Science University of California at Berkeley BerkeleyCA United States Department of Biomedical Data Science Stanford University School of Medicine Palo AltoCA United States

Machine-learning (ML) parameterizations of subgrid processes (here of turbulence, convection, and radiation) may one day replace conventional parameterizations by emulating high-resolution physics without the cost of explicit simulation. However, uncertainty about the relationship between offline and online performance (i.e., when integrated with a large-scale general circulation model (GCM)) hinders their development. Much of this uncertainty stems from limited sampling of the noisy, emergent effects of upstream ML design decisions on downstream online hybrid simulation. Our work rectifies the sampling issue via the construction of a semi-automated, end-to-end pipeline for O(100) size ensembles of hybrid simulations, revealing important nuances in how systematic reductions in offline error manifest in changes to online error and online stability. For example, removing dropout and switching from a Mean Squared Error (MSE) to a Mean Absolute Error (MAE) loss both reduce offline error, but they have opposite effects on online error and online stability. Other design decisions, like incorporating memory, converting moisture input from specific humidity to relative humidity, using batch normalization, and training on multiple climates do not come with any such compromises. Finally, we show that ensemble sizes of O(100) may be necessary to reliably detect causally relevant differences online. By enabling rapid online experimentation at scale, we can empirically settle debates regarding subgrid ML parameterization design that would have otherwise remained unresolved in the noise. © 2023, CC BY.

关键词： Parameterization

来源：评论

学校读者我要写书评

暂无评论

Discriminative features matter: Multi-layer bilinear pooling for camera localization 30

Discriminative features matter: Multi-layer bilinear pooling...

引用

30th British Machine Vision Conference, BMVC 2019

作者： Wang, Xin Wang, Xiang Wang, Chen Bai, Xiao Wu, Jing Hancock, Edwin Robert School of Computer Science and Engineering Beijing Advanced Innovation Center for Big Data and Brain Computing Jiangxi Research Institute Beihang University Beijing China School of Computer Science and Informatics Cardiff University Cardiff United Kingdom Department of Computer Science University of York York United Kingdom

Deep learning based camera localization from a single image has been explored recently since these methods are computationally efficient. However, existing methods only provide general global representations, from which an accurate pose estimation can not be reliably derived. We claim that effective feature representations for accurate pose estimation shall be both "informative" (focusing on geometrically meaningful regions) and "discriminative" (accounting for different poses of similar images). Therefore, we propose a novel multi-layer factorized bilinear pooling module for feature aggregation. Specifically, informative features are selected via bilinear pooling, and discriminative features are highlighted via multi-layer fusion. We develop a new network for camera localization using the proposed feature pooling module. The effectiveness of our approach is demonstrated by experiments on an outdoor Cambridge Landmarks dataset and an indoor 7 Scenes dataset. The results show that focusing on discriminative features significantly improves the network performance of camera localization in most cases. Codes will be available soon. © 2019. The copyright of this document resides with its authors.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

NTIRE 2023 Challenge on Light Field Image Super-Resolution: dataset, Methods and Results

NTIRE 2023 Challenge on Light Field Image Super-Resolution: ...

引用

2023 IEEE/CVF Conference on computer Vision and Pattern Recognition Workshops, CVPRW 2023

作者： Wang, Yingqian Wang, Longguang Liang, Zhengyu Yang, Jungang Timofte, Radu Guo, Yulan Jin, Kai Wei, Zeqiang Yang, Angulia Guo, Sha Gao, Mingzhi Zhou, Xiuzhuang Van Duong, Vinh Huu, Thuc Nguyen Yim, Jonghoon Jeon, Byeungwoo Liu, Yutong Cheng, Zhen Xiao, Zeyu Xu, Ruikang Xiong, Zhiwei Liu, Gaosheng Jin, Manchang Yue, Huanjing Yang, Jingyu Gao, Chen Zhang, Shuo Chang, Song Lin, Youfang Chao, Wentao Wang, Xuechun Wang, Guanghui Duan, Fuqing Xia, Wang Wang, Yan Xia, Peiqi Wang, Shunzhou Lu, Yao Cong, Ruixuan Sheng, Hao Yang, Da Chen, Rongshan Wang, Sizhe Cui, Zhenglong Chen, Yilei Lu, Yongjie Cai, Dongjun An, Ping Salem, Ahmed Ibrahem, Hatem Yagoub, Bilel Kang, Hyun-Soo Zeng, Zekai Wu, Heng National University of Defense Technology China Aviation University of Air Force China University of Würzburg Germany Eth Zürich Switzerland Sun Yat-sen University The Shenzhen Campus of Sun Yat-sen University China Bigo Technology Pte. Ltd. Singapore Smart Medical Innovation Lab Beijing University of Posts and Telecommunications China Global Explorer Ltd. Suzhou China National Engineering Research Center of Visual Technology School of Computer Science Peking University China School of Artificial Intelligence Beijing University of Posts and Telecommunications China Department of Electrical and Computer Engineering Sungkyunkwan University Korea Republic of University of Science and Technology of China China School of Electrical and Information Engineering Tianjin University China Beijing Key Lab of Traffic Data Analysis and Mining School of Computer and Information Technology Beijing Jiaotong University China Beijing Normal University China Toronto Metropolitan University Canada Beijing Institute of Technology China Shenzhen MSU-BIT University China State Key Laboratory of Virtual Reality Technology and Systems School of Computer Science and Engineering Beihang University China Beihang Hangzhou Innovation Institute Yuhang China Faculty of Applied Sciences Macao Polytechnic University China School of Communication and Information Engineering Shanghai University China School of Information and Communication Engineering Chungbuk National University Korea Republic of Guangdong University of Technology China

ISBN: (纸本)9798350302493

In this report, we summarize the first NTIRE challenge on light field (LF) image super-resolution (SR), which aims at super-resolving LF images under the standard bicubic degradation with a magnification factor of 4. This challenge develops a new LF dataset called NTIRE-2023 for validation and test, and provides a toolbox called BasicLFSR to facilitate model development. Compared with single image SR, the major challenge of LF image SR lies in how to exploit complementary angular information from plenty of views with varying disparities. In total, 148 participants have registered the challenge, and 11 teams have successfully submitted results with PSNR scores higher than the baseline method LF-InterNet [1]. These newly developed methods have set new state-of-the-art in LF image SR, e.g., the winning method achieves around 1 dB PSNR improvement over the existing state-of-the-art method DistgSSR [2]. We report the solutions proposed by the participants, and summarize their common trends and useful tricks. We hope this challenge can stimulate future research and inspire new ideas in LF image SR. © 2023 IEEE.

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

Simulating Atmospheric Processes in Earth System Models and Quantifying Uncertainties with Deep Learning Multi-Member and Stochastic Parameterizations

arXiv

引用

arXiv 2024年

作者： Behrens, Gunnar Beucler, Tom Iglesias-Suarez, Fernando Yu, Sungduk Gentine, Pierre Pritchard, Michael Schwabe, Mierk Eyring, Veronika Institut für Physik der Atmosphäre Oberpfaffenhofen Germany Bremen Germany Faculty of Geosciences and Environment University of Lausanne Switzerland Expertise Center for Climate Extremes University of Lausanne Switzerland Predictia Intelligent Data Solutions S.L. Santander Spain Department of Earth System Science University of California Irvine IrvineCA United States Multimodal Cognitive AI Research Intel Labs Santa ClaraCA United States Department of Earth and Environmental Engineering Columbia University New YorkNY10027 United States Earth Institute and Data Science Institute Columbia University New YorkNY10027 United States NVIDIA United States

Deep learning is a powerful tool to represent subgrid processes in climate models, but many application cases have so far used idealized settings and deterministic approaches. Here, we develop stochastic parameterizations with calibrated uncertainty quantification to learn subgrid convective and turbulent processes and surface radiative fluxes of a superparameterization embedded in an Earth System Model (ESM). We explore three methods to construct stochastic parameterizations: 1) a single Deep Neural Network (DNN) with Monte Carlo Dropout;2) a multi-member parameterization;and 3) a Variational Encoder Decoder with latent space perturbation. We show that the multi-member parameterization improves the representation of convective processes, especially in the planetary boundary layer, compared to individual DNNs. The respective uncertainty quantification illustrates that methods 2) and 3) are advantageous compared to a dropout-based DNN parameterization regarding the spread of convective processes. Hybrid simulations with our best-performing multi-member parameterizations remained challenging and crash within the first days. Therefore, we develop a pragmatic partial coupling strategy relying on the superparameterization for condensate emulation. Partial coupling reduces the computational efficiency of hybrid Earth-like simulations but enables model stability over 5 months with our multi-member parameterizations. However, our hybrid simulations exhibit biases in thermodynamic fields and differences in precipitation patterns. Despite this, the multi-member parameterizations enable improvements in reproducing tropical extreme precipitation compared to a traditional convection parameterization. Despite these challenges, our results indicate the potential of a new generation of multi-member machine learning parameterizations leveraging uncertainty quantification to improve the representation of stochasticity of subgrid effects. © 2024, CC BY.

关键词： Stochastic systems

来源：评论

学校读者我要写书评

暂无评论

Neural Architecture Search for Optimization of Spatial-Temporal Brain Network Decomposition 23rd

Neural Architecture Search for Optimization of Spatial-Tempo...

引用

23rd International Conference on Medical Image Computing and computer-Assisted Intervention, MICCai 2020

作者： Li, Qing Zhang, Wei Lv, Jinglei Wu, Xia Liu, Tianming School of Artificial Intelligence Beijing Normal University Beijing China Engineering Research Center of Intelligent Technology and Educational Application Ministry of Education Beijing China Department of Computer Science and Bioimaging Research Center The University of Georgia AthensGA United States Department of Biomedical Engineering University of Melbourne ParkvilleVIC Australia

ISBN: (纸本)9783030597276

Using neural networks to explore spatial patterns and temporal dynamics of human brain activities has been an important yet challenging problem because it is hard to manually design the most optimal neural networks. There have been several promising deep learning methods that can decompose neuroscientifically meaningful spatial-temporal patterns from 4D fMRI data, e.g., the deep sparse recurrent auto-encoder (DSRAE). However, those previous studies still depend on hand-crafted neural network structures and hyperparameters, which are not optimal in various senses. In this paper, we employ evolutionary algorithms to optimize such DSRAE neural networks by minimizing the expected loss of the generated architectures on data reconstruction via the neural architecture search (NAS) framework, named NAS-DSRAE. The optimized NAS-DSRAE is evaluated by the publicly available human connectome project (HCP) fMRI datasets and our promising results showed that NAS-DSRAE has sufficient generalizability to model the spatial-temporal features and is better than the hand-crafted model. To our best knowledge, the proposed NAS-DSRAE is among the earliest NAS models that can extract connectome-scale meaningful spatial-temporal brain networks from 4D fMRI data. © 2020, Springer Nature Switzerland AG.

关键词： Recurrent neural networks

来源：评论

学校读者我要写书评

暂无评论

data mining analysis of the influences of electrocardiogram P-wave morphology parameters on atrial fibrillation

Data mining analysis of the influences of electrocardiogram ...

引用

作者： Ouyang, Chen-Sen Chen, Yenming J. Tsai, Jinn-Tsong Chang, Yiu-Jen Huang, Tian-Hsiang Hwang, Kao-Shing Ho, Yuan-Chih Ho, Wen-Hsien Department of Information Engineering I-Shou University Kaohsiung Taiwan Department of Logistics Management National Kaohsiung University of Science and Technology Kaohsiung Taiwan Department of Computer Science National Pingtung University Pingtung Taiwan Department of Healthcare Administration and Medical Informatics Kaohsiung Medical University Kaohsiung Taiwan Center for Big Data Research Kaohsiung Medical University Kaohsiung Taiwan Department of Electrical Engineering National Sun Yat-Sen University Kaohsiung Taiwan Division of Cardiology Department of Internal Medicine Yuan's General Hospital Kaohsiung Taiwan Department of Medical Research Kaohsiung Medical University Hospital Kaohsiung Taiwan

Atrial fibrillation (AF) is a type of paroxysmal cardiac disease that presents no obvious symptoms during onset, and even the electrocardiograms (ECG) results of patients with AF appear normal under a premorbid status, rendering AF difficult to detect and diagnose. However, it can result in deterioration and increased risk of stroke if not detected and treated early. This study used the ECG database provided by the Physionet website (https://***), filtered data, and employed parameter-extraction methods to identify parameters that signify ECG features. A total of 31 parameters were obtained, consisting of P-wave morphology parameters and heart rate variability parameters, and the data were further examined by implementing a decision tree, of which the topmost node indicated a significant causal relationship. The experiment results verified that the P-wave morphology parameters significantly affected the ECG results of patients with AF. © 2021-IOS Press. All rights reserved.

关键词： Electrocardiograms

来源：评论

学校读者我要写书评

暂无评论

Tacchi 2.0: A Low Computational Cost and Comprehensive Dynamic Contact Simulator for Vision-based Tactile Sensors

arXiv

引用

arXiv 2025年

作者： Sun, Yuhao Zhang, Shixin Li, Wenzhuang Zhao, Jie Shan, Jianhua Shen, Zirong Chen, Zixi Sun, Fuchun Guo, Di Fang, Bin School of Artificial Intelligence Beijing University of Posts and Telecommunications Beijing100083 China Beijing100083 China School of International Beijing University of Posts and Telecommunications Beijing100876 China School of Mechanical Engineering Anhui University of Technology China Zhili College Tsinghua University Beijing100084 China Biorobotics Institute The Department of Excellence in Robotics and AI Scuola Superiore Sant’Anna Pisa56127 Italy Institute for Artificial Intelligence Department of Computer Science and Technology Beijing National Research Center for Information Science and Technology Tsinghua University Beijing100084 China

With the development of robotics technology, some tactile sensors, such as vision-based sensors, have been applied to contact-rich robotics tasks. However, the durability of vision-based tactile sensors significantly increases the cost of tactile information acquisition. Utilizing simulation to generate tactile data has emerged as a reliable approach to address this issue. While data-driven methods for tactile data generation lack robustness, finite element methods (FEM) based approaches require significant computational costs. To address these issues, we integrated a pinhole camera model into the low computational cost vision-based tactile simulator Tacchi that used the Material Point Method (MPM) as the simulated method, completing the simulation of marker motion images. We upgraded Tacchi and introduced Tacchi 2.0. This simulator can simulate tactile images, marked motion images, and joint images under different motion states like pressing, slipping, and rotating. Experimental results demonstrate the reliability of our method and its robustness across various vision-based tactile sensors. © 2025, CC BY.

关键词： Pinhole cameras

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：