检索结果-内蒙古大学图书馆

arXiv 2025年

作者： Baxi, Saumil Cummings, Kayla Jacquillat, Alexandre Lo, Sean McDonald, Rob Mellou, Konstantina Menache, Ishai Molinaro, Marco Cloud Operations and Innovation Microsoft United States Cloud Supply Chain Sustainability Engineering Microsoft United States Sloan School of Management Operations Research Center Massachusetts Institute of Technology United States Machine Learning and Optimization Microsoft Research United States

This paper optimizes the configuration of large-scale data centers toward cost-effective, reliable and sustainable cloud supply chains. We formulate an integer optimization model that optimizes the placement of racks of servers within a data center to maximize demand coverage, adhere to space, power and cooling restrictions, and pace resource utilization for future demand. We also define a tractable single-sample online approximation (SSOA) approach to multi-stage stochastic optimization, which approximates unknown parameters with a single realization and re-optimizes decisions dynamically. Theoretical results provide strong performance guarantees of SSOA in the canonical online generalized assignment and online bin packing settings. Computational results using real-world data show that our optimization approach can enhance utilization and reduce power stranding in data centers. Following iterative improvements in collaboration with data center managers, our algorithm has been packaged into a software solution deployed in Microsoft's data centers worldwide. Deployment data indicate a significant increase in adoption, leading to improved power utilization, multi-million-dollar annual cost savings, and concomitant savings in greenhouse gas emissions. Ultimately, this paper constitutes one of the first large-scale deployments of a decision-making tool in data centers, contributing an interactive decision-making process at the human-machine *** Codes 90C11 Copyright © 2025, The Authors. All rights reserved.

关键词： Chains

来源：评论

学校读者我要写书评

暂无评论

Self-supervised Sparse to Dense Motion Segmentation 15th

Self-supervised Sparse to Dense Motion Segmentation

引用

15th Asian Conference on Computer Vision, ACCV 2020

作者： Kardoost, Amirhossein Ho, Kalun Ochs, Peter Keuper, Margret Data and Web Science Group University of Mannheim Mannheim Germany Fraunhofer Center Machine Learning Sankt Augustin Germany Fraunhofer ITWM Competence Center HPC Kaiserslautern Germany Mathematical Optimization Group Saarland University Saarbrcken Germany

ISBN: (纸本)9783030695316

Observable motion in videos can give rise to the definition of objects moving with respect to the scene. The task of segmenting such moving objects is referred to as motion segmentation and is usually tackled either by aggregating motion information in long, sparse point trajectories, or by directly producing per frame dense segmentations relying on large amounts of training data. In this paper, we propose a self supervised method to learn the densification of sparse motion segmentations from single video frames. While previous approaches towards motion segmentation build upon pre-training on large surrogate datasets and use dense motion information as an essential cue for the pixelwise segmentation, our model does not require pre-training and operates at test time on single frames. It can be trained in a sequence specific way to produce high quality dense segmentations from sparse and noisy input. We evaluate our method on the well-known motion segmentation datasets FBMS 59 and DAVIS16. © 2021, Springer Nature Switzerland AG.

关键词： Large dataset

来源：评论

学校读者我要写书评

暂无评论

Cyberattack detection for cyber physical systems security - A preliminary study 10

Cyberattack detection for cyber physical systems security - ...

引用

10th Annual Conference of the Prognostics and Health Management Society, PHM 2018

作者： Yan, Weizhong Mestha, Lalit John, Justin Holzhauer, Daniel McKinley, Marc Abbaszadeh, Masoud AI and Machine Learning GE Global Research Center NiskayunaNY12309 United States Controls and Optimization GE Global Research Center NiskayunaNY12309 United States GPS Technology GE Power SalemVA24153 United States

ISBN: (纸本)9781936263295

Cyber-physical systems (CPS) security has become an increasingly important research topic in recent years. Geared towards more advanced cyberattack detection techniques as part of strategies for enhancing the security of CPS, in this paper we propose a machine learning based cyber-attack detection scheme. The proposed scheme is a physical-domain technique;specifically, it assumes the physical measurements of the system carry sufficient information for capturing the system behavior, thus can be used for differentiating normal operation and attacks. CPS are complex in nature and the number of physical measurements available for CPS is often overwhelmingly high. Thus, accurately modeling CPS' dynamic behavior, more importantly, distinguishing normal and adversary activities based on the large number of physical measurements, can be challenging. To address the challenge, we have focused our research effort on feature engineering, that is, to intelligently derive a set of salient signatures or features from the noisy measurements. We make sure the derived features are more compact and, more importantly, have more discriminant power than the original physical measurements, thus enabling us to achieve more accurate and robust detection performance. To demonstrate the effectiveness of the proposed scheme, in our experimental study we consider gas turbines of combined cycle power plants as the cyber-physical system. Using the data from the high-fidelity simulation we show that our proposed cyberattack detection scheme is able to achieve high detection performance. © 2018 Prognostics and Health Management Society. All rights reserved.

关键词： Cyber Physical System

来源：评论

学校读者我要写书评

暂无评论

Occlusion Resilient 3D Human Pose Estimation

Occlusion Resilient 3D Human Pose Estimation

引用

International Conference on 3D Imaging, Modeling, Processing, Visualization and Transmission (3DIMPVT)

作者： Soumava Kumar Roy Ilia Badanin Sina Honari Pascal Fua Computer Vision Lab EPFL Switzerland Machine Learning and Optimization Lab EPFL Switzerland Samsung AI Center Toronto

ISBN: (数字)9798350362459

ISBN: (纸本)9798350362466

Occlusions remain one of the key challenges in 3D body pose estimation from single-camera video sequences. Temporal consistency has been extensively used to mitigate their impact but the existing algorithms in the literature do not explicitly model ***, we apply this by representing the deforming body as a spatio-temporal graph. We then introduce a refinement network that performs graph convolutions over this graph to output 3D poses. To ensure robustness to occlusions, we train this network with a set of binary masks that we use to disable some of the edges as in drop-out *** effect, we simulate the fact that some joints can be hidden for periods of time and train the network to be immune to that. We demonstrate the effectiveness of this approach compared to state-of-the-art techniques that infer poses from single-camera sequences.

关键词： Training Three-dimensional displays Pose estimation Video sequences MIMICs Robustness Immune system

来源：评论

学校读者我要写书评

暂无评论

Spectral preconditioning for gradient methods on graded non-convex functions 24

Spectral preconditioning for gradient methods on graded non-...

引用

Proceedings of the 41st International Conference on machine learning

作者： Nikita Doikov Sebastian U. Stich Martin Jaggi Machine Learning and Optimization Laboratory (MLO) EPFL Lausanne Switzerland CISPA Helmholtz Center for Information Security Saarbrücken Germany

The performance of optimization methods is often tied to the spectrum of the objective Hessian. Yet, conventional assumptions, such as smoothness, do often not enable us to make finely-grained convergence statements--particularly not for non-convex problems. Striving for a more intricate characterization of complexity, we introduce a unique concept termed graded nonconvexity. This allows to partition the class of nonconvex problems into a nested chain of subclasses. Interestingly, many traditional non-convex objectives, including partially convex problems, matrix factorizations, and neural networks, fall within these subclasses. As a second contribution, we propose gradient methods with spectral preconditioning, which employ inexact top eigenvectors of the Hessian to address the ill-conditioning of the problem, contingent on the grade. Our analysis reveals that these new methods provide provably superior convergence rates compared to basic gradient descent on applicable problem classes, particularly when large gaps exist between the top eigenvalues of the Hessian. Our theory is validated by numerical experiments executed on multiple practical machine learning problems.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Occlusion Resilient 3D Human Pose Estimation

arXiv

引用

arXiv 2024年

作者： Roy, Soumava Kumar Badanin, Ilia Honari, Sina Fua, Pascal Computer Vision Lab EPFL Switzerland Machine Learning and Optimization Lab EPFL Switzerland Samsung AI Center Toronto Canada

Occlusions remain one of the key challenges in 3D body pose estimation from single-camera video sequences. Temporal consistency has been extensively used to mitigate their impact but the existing algorithms in the literature do not explicitly model them. Here, we apply this by representing the deforming body as a spatio-temporal graph. We then introduce a refinement network that performs graph convolutions over this graph to output 3D poses. To ensure robustness to occlusions, we train this network with a set of binary masks that we use to disable some of the edges as in drop-out techniques. In effect, we simulate the fact that some joints can be hidden for periods of time and train the network to be immune to that. We demonstrate the effectiveness of this approach compared to state-of-the-art techniques that infer poses from single-camera sequences. © 2024, CC0.

关键词： Cameras

来源：评论

学校读者我要写书评

暂无评论

On convergence of incremental gradient for non-convex smooth functions 24

On convergence of incremental gradient for non-convex smooth...

引用

Proceedings of the 41st International Conference on machine learning

作者： Anastasia Koloskova Nikita Doikov Sebastian U. Stich Martin Jaggi Machine Learning and Optimization Laboratory (MLO) EPFL Lausanne Switzerland CISPA Helmholtz Center for Information Security Saarbrücken Germany

In machine learning and neural network optimization, algorithms like incremental gradient, and shuffle SGD are popular due to minimizing the number of cache misses and good practical convergence behavior. However, their optimization properties in theory, especially for nonconvex smooth functions, remain incompletely *** paper delves into the convergence properties of SGD algorithms with arbitrary data ordering, within a broad framework for non-convex smooth functions. Our findings show enhanced convergence guarantees for incremental gradient and single shuffle SGD. Particularly if n is the training set size, we improve n times the optimization term of convergence guarantee to reach accuracy ε from O(n/ε) to O(1/ε).

关键词：

来源：评论

学校读者我要写书评

暂无评论

Self-supervised sparse to dense motion segmentation

arXiv

引用

arXiv 2020年

作者： Kardoost, Amirhossein Ho, Kalun Ochs, Peter Keuper, Margret Data and Web Science Group University of Mannheim Germany Fraunhofer Center Machine Learning Germany Fraunhofer ITWM Competence Center HPC Kaiserslautern Germany Mathematical Optimization Group Saarland University Germany

Observable motion in videos can give rise to the definition of objects moving with respect to the scene. The task of segmenting such moving objects is referred to as motion segmentation and is usually tackled either by aggregating motion information in long, sparse point trajectories, or by directly producing per frame dense segmentations relying on large amounts of training data. In this paper, we propose a self supervised method to learn the densification of sparse motion segmentations from single video frames. While previous approaches towards motion segmentation build upon pre-training on large surrogate datasets and use dense motion information as an essential cue for the pixelwise segmentation, our model does not require pre-training and operates at test time on single frames. It can be trained in a sequence specific way to produce high quality dense segmentations from sparse and noisy input. We evaluate our method on the well-known motion segmentation datasets FBMS59 and DAVIS16. Copyright © 2020, The Authors. All rights reserved.

关键词： Motion analysis

来源：评论

学校读者我要写书评

暂无评论

Analysis of the Research Status of Information Technology Education Literature in China and Abroad 24

Analysis of the Research Status of Information Technology Ed...

引用

24th IEEE International Conference on High Performance Computing and Communications, 8th IEEE International Conference on Data Science and Systems, 20th IEEE International Conference on Smart City and 8th IEEE International Conference on Dependability in Sensor, Cloud and Big Data Systems and Application, HPCC/DSS/SmartCity/DependSys 2022

作者： Zhao, Yulin Liu, Kai Li, Junke School of Information Engineering Suqian University Jiangsu Suqian223800 China School of Computer and Information Qiannan Normal University for Nationalities Duyun558000 China Jiangsu Province Engineering Research Center of Smart Poultry Farming and Intelligent Equipment Jiangsu 223800 China Key Laboratory of Machine Learning and Unstructured Data Processing of Qiannan Duyun558000 China Key Laboratory of Complex Systems and Intelligent Optimization of Guizhou Duyun558000 China

ISBN: (纸本)9798350319934

Information technology education contributes to the development of national education. Understanding the research status of information technology education at home and abroad is helpful to the implementation of education informatization. This paper takes the information technology education research literature collected by CNKI and the Web of Science database as the object and uses the bibliometric method to analyze the literature characteristics of information technology education at home and abroad. Specifically, the paper mainly carries out statistical analysis from the time distribution of literature, journal distribution, and hot keywords, and visually describes the literature features of the information technology education discipline, providing references for the research of information technology education discipline at home and abroad. © 2022 IEEE.

关键词： Informatization

来源：评论

学校读者我要写书评

暂无评论

The Utilization of Different Classifiers to Perform Drug Repositioning in Inclusion Body Myositis Supports the Concept of Biological Invariance 19th

The Utilization of Different Classifiers to Perform Drug Rep...

引用

19th International Conference on Artificial Intelligence and Soft Computing, ICAISC 2020

作者： Álvarez-Machancoses, Óscar deAndrés-Galiana, Enrique Fernández-Martínez, Juan Luis Kloczkowski, Andrzej Group of Inverse Problems Optimization and Machine Learning. Department of Mathematics University of Oviedo C. Federico García Lorca 18 Oviedo33007 Spain Department of Computer Science University of Oviedo C. Federico García Lorca 18 Oviedo33007 Spain Battelle Center for Mathematical Medicine Nationwide Children’s Hospital ColumbusOH United States Department of Pediatrics The Ohio State University ColumbusOH United States

ISBN: (纸本)9783030614003

In this research work, we introduce several novel methods to identify the defective pathways in highly uncertain phenotype prediction problems. More specifically, we applied these methodologies for phenotype prediction associated with drug repositioning for rare diseases such as the Inclusion Body Myositis and obtained a better understanding of the disease mechanism. The novelty of our research is based on the fact that the classifiers utilized to build the genetic signatures were based on completely different approaches, namely;gene Fisher ratios, generation of random genetic networks or genetic network likelihoods to sample and relate the altered genes to possible drugs via the connectivity maps. This scheme provides a more effective drug design/repositioning since it helps to understand the disease mechanisms and to establish an optimum mechanism of action of the designed drugs. By comparing the different classifiers, we conclude that the Fisher’s ratio, Holdout and Random Forest samplers are the most effective, since they provide similar insights into the genetic mechanisms of the disease and bear low computational costs. Furthermore, our work supports the concept of Biological Invariance, assuming that the results of the analysis of the altered pathways should be independent of the sampling method utilized for the assessment of the inference. However, the effectiveness of the candidate drugs and the gene targets predicted by our approach should be pre-clinically studied and clinically tested. © 2020, Springer Nature Switzerland AG.

关键词： Forecasting

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：