检索结果-内蒙古大学图书馆

Optimization for Deep Learning:An Overview

Journal of the Operations Research Society of China 2020年第2期8卷 249-294页

作者： Ruo-Yu Sun Department of Industrial and Enterprise Systems Engineering and affiliated to Coordinated Science LaboratoryUniversity of Illinois at Urbana-ChampaignUrbanaIL 61801USA Department of Electrical and Computer Engineering University of Illinois at Urbana-ChampaignUrbanaIL 61801USA

Optimization is a critical component in deep *** think optimization for neural networks is an interesting topic for theoretical research due to various ***,its tractability despite non-convexity is an intriguing question and may greatly expand our understanding of tractable ***,classical optimization theory is far from enough to explain many ***,we would like to understand the challenges and opportunities from a theoretical perspective and review the existing research in this ***,we discuss the issue of gradient explosion/vanishing and the more general issue of undesirable spectrum and then discuss practical solutions including careful initialization,normalization methods and skip ***,we review generic optimization methods used in training neural networks,such as stochastic gradient descent and adaptive gradient methods,and existing theoretical ***,we review existing research on the global issues of neural network training,including results on global landscape,mode connectivity,lottery ticket hypothesis and neural tangent kernel.

关键词： Deep learning Non-convex optimization Neural networks Convergence Landscape

来源：评论

学校读者我要写书评

暂无评论

Screening cognitive impairment in patients with atrial fibrillation: A deep learning model based on retinal fundus photographs

引用

Heart Rhythm O2 2025年第5期6卷 678-686页

作者： Wang, Zhen Li, Mingxiao Xia, Peng Jiang, Chao Shen, Ting Ma, Jiaming Bai, Yu Zhang, Suhui Lai, Yiwei Li, Sitong Xu, Hui Xu, Yang Ma, Tong Ju, Lie He, Liu Dong, Li Sang, Caihua Long, Deyong Chen, Yuzhong Du, Xin Ge, Zongyuan Dong, Jianzeng Wei, Wen-Bin Ma, Changsheng Department of Cardiology Beijing Anzhen Hospital Capital Medical University Beijing China Engineering Research Center of Medical Devices for Cardiovascular Diseases Ministry of Education Capital Medical University Beijing China National Clinical Research Center for Cardiovascular Diseases Beijing China Beijing Airdoc Technology Co. Ltd. Beijing China Department of Electrical and Computer Systems Engineering Faculty of Engineering Monash University Clayton Australia Yale School of Medicine New Haven Connecticut United States School of Clinical Medicine Peking Union Medical College and Chinese Academy of Medical Science Beijing China Beijing Tongren Eye Center Beijing Key Laboratory of Intraocular Tumor Diagnosis and Treatment Beijing Ophthalmology & Visual Sciences Key Lab Medical Artificial Intelligence Research and Verification Key Laboratory of the Ministry of Industry and Information Technology Beijing Tongren Hospital Capital Medical University Beijing China Monash e-Research Center Monash University Clayton Australia

Background: Patients with atrial fibrillation (AF) have a higher risk of cognitive impairment (CI). However, complexity of CI diagnosis and lack of simple screening approaches limited early screening and intervention of CI in AF patients. Objective: Our study aimed to develop deep learning models based on fundus photographs for easy screening of CI in AF patients. Methods: From May 2021 to April 2023, patients who completed fundus examination and cognitive function evaluation in the Chinese Atrial Fibrillation Registry Study were included. The training and validation sets were randomly split at an 8:2 ratio. Participants from the Beijing Eye Study served as the external validation set. Different deep learning models were trained, and their CI detection ability was validated. Results: A total of 899 patients in the Chinese Atrial Fibrillation Registry Study were included. In the validation set, the vision-ensemble model based on fundus images alone had an area under the receiver-operating characteristic curve (AUROC) of 0.855 (95% confidence interval 0.816–0.894) for CI screening. The multimodal model (AUROC 0.861, 95% confidence interval 0.823–0.898), based on fundus photographs and 4 clinical variables, performed comparably to the vision-ensemble model. The AUROC of the vision-ensemble model for CI screening achieved 0.773 (95% confidence interval 0.709–0.837) in the external test set. In the saliency map, the vision-ensemble model focused on areas around retinal vessels and the optic disc. Conclusion: A vision-ensemble model based on fundus images might be practical for preliminary screening of CI in AF patients. © 2025 Heart Rhythm Society

关键词： Artificial intelligence Atrial fibrillation Cognitive impairment Deep learning Fundus photography

来源：评论

学校读者我要写书评

暂无评论

A Real-Time Limit Order Book as a Market Mechanism for Transactive Energy systems

A Real-Time Limit Order Book as a Market Mechanism for Trans...

引用

IEEE General Meeting Power& Energy Society

作者： Akshay Sreekumar Adhithyan Sakthivelu Rimvydas Baltaduonis Lynne Kiesling Seth Hoedl David P. Chassin Electrical and Computer Engineering University of California Los Angeles Civil and Environmental Engineering Stanford University Department of Economics Gettysburg College Institute for Regulatory Law and Economics University of Colorado Denver Post Road Foundation SLAC National Accelerator Laboratory Grid Integration Systems and Mobility

This paper presents a limit order book (LOB) market mechanism design for transactive energy systems. The proposed design is planned for deployment in New Hampshire and Maine under a US department of Energy Connected Communities project. The new LOB mechanism is intended to replace or work in conjunction with the conventional transactive energy double auction mechanisms designed for retail real-time electricity price discovery, and will facilitate significant scaling of transactive energy systems. The paper provides LOB market rules, clearing algorithm, and illustrative examples and discusses clearing algorithm performance and reliability. The proposed LOB design includes support for discovering prices arising from wholesale electricity markets, distribution system asset constraints, distributed energy resource constraints, and consumer willingness to consume or produce at a reservation price.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Learning Reduced-Order Linear Parameter-Varying Models of Nonlinear systems

arXiv

引用

arXiv 2023年

作者： Koelewijn, Patrick J.W. Singh, Rajiv Seiler, Peter Tóth, Roland Sioux Technologies B.V. Eindhoven Netherlands Control Systems Group Eindhoven University of Technology Eindhoven Netherlands The MathWorks Inc. Natick United States Department of Electrical Engineering and Computer Science University of Michigan Ann Arbor United States Systems and Control Laboratory HUN-REN Institute for Computer Science and Control Budapest Hungary

In this paper, we consider the learning of a Reduced-Order Linear Parameter-Varying Model (ROLPVM) of a nonlinear dynamical system based on data. This is achieved by a two-step procedure. In the first step, we learn a projection to a lower dimensional state-space. In step two, an LPV model is learned on the reduced-order state-space using a novel, efficient parameterization in terms of neural networks. The improved modeling accuracy of the method compared to an existing method is demonstrated by simulation examples. Copyright © 2023, The Authors. All rights reserved.

关键词： Nonlinear dynamical systems

来源：评论

学校读者我要写书评

暂无评论

Inverse-designed multi-wavelength, multi-mode optical interconnects using soliton microcombs

Inverse-designed multi-wavelength, multi-mode optical interc...

引用

CLEO: Science and Innovations, S and I 2022

作者： Yang, K.Y. White, A.D. Ashtiani, F. Shirpurkar, C. Pericherla, S.V. Chang, L. Song, H. Zou, K. Zhou, H. Pang, K. Yang, J. Guidry, M.A. Lukin, D.M. Hao, H. Trask, L. Ahn, G.H. Netherton, A. Briles, T.C. Stone, J.R. Rechtman, L. Stone, J.S. Van Gasse, K. Skarda, J.L. Su, L. Vercruysse, D. MacLean, J.P.W. Aghaeimeibodi, S. Li, M.-J. Miller, D.A.B. Marom, D.M. Papp, S.B. Willner, A.E. Bowers, J.E. Delfyett, P.J. Aflatouni, F. Vučković, J. E.L.Ginzton Laboratory Stanford University StanfordCA United States Department of Electrical and Systems Engineering University of Pennsylvania PhiladelphiaPA United States The College of Optics and Photonics University of Central Florida OrlandoFL32816 United States Department of Electrical and Computer Engineering University of California Santa BarbaraCA United States Department of Electrical Engineering University of Southern California Los AngelesCA United States Time and Frequency Division National Institute of Standards and Technology BoulderCO United States Applied Physics Department The Hebrew University of Jerusalem Jerusalem Israel Corning Incorporated CorningNY United States Department of Physics University of Colorado BoulderCO United States

We demonstrate 130 Gbps transmission in each of 4 spatial modes using Si3N4 soliton microcombs and inverse-designed silicon mode multiplexers. Out of 52 carriers, 42 data channels show natively error-free data transmi... 详细信息

ISBN: (纸本)9781557528209

关键词： Solitons

来源：评论

学校读者我要写书评

暂无评论

Texture Preserving Deep Learning-Based Noise Reduction for Anatomical Magnetic Resonance Images and its Impact on Imaging Features

Texture Preserving Deep Learning-Based Noise Reduction for A...

引用

International Symposium on Applied Computational Intelligence and Informatics ( SACI)

作者： Eleftherios Trivizakis Eugenia Mylona Katerina Nikiforaki Dimitrios I. Zaridis Manolis Tsiknakis Dimitrios I. Fotiadis Nikolaos Tachos Daniele Regge Nikolaos Papanikolaou Kostas Marias Computational BioMedicine Laboratory (CBML) Foundation for Research and Technology Hellas Heraklion GREECE Biomedical Research Institute (BRI) Foundation for Research and Technology Hellas Ioannina GREECE Biomedical Engineering Laboratory School of Medicine School of Electrical & Computer Engineering National Technical University of Athens Athens GREECE Dpt. Electrical & Computer Engineering Computational BioMedicine Laboratory Foundation for Research and Technology Hellas / Hellenic Mediterranean University Heraklion GREECE Biomedical Research Institute (BRI)/ Unit of Medical Technology and Intelligent Information Systems Foundation for Research and Technology Hellas Ioannina/ University of Ioannina GREECE Procancer-I Consortium Department of Radiology Candiolo Cancer Institute FPO-IRCCS Candiolo Turin ITALY Computational Clinical Imaging Group Centre of the Unknown Champalimaud Foundation PORTUGAL Dpt. Electrical & Computer Engineering Computational BioMedicine Laboratory Foundation for Research and Technology Hellas / Hellenic Mediterranean University Heraklion

ISBN: (数字)9798331515478

ISBN: (纸本)9798331515485

Anatomical magnetic resonance images are affected by different types of noise, including thermal, motion, radio interference, and magnetic field inhomogeneities. In a clinical setting, acquiring MR images of the highest quality is not always feasible. Quantitative and artificial intelligencebased decision support tools require high-quality data to accurately differentiate among pathological conditions, avoiding diminishing the clinical relevance of a diagnostic model. A fully convolutional model with no pooling layers was trained on a set of noisy images, with the ground truth being the original image without the noise. Different levels of noise were incorporated into the training set. The experiments showed a reduction in noise levels, but it can impact quantification tasks when T2ws without noise are provided to the model. Six types of pairs of original T2w image slices and the corresponding slices with synthetic noise were generated with various thresholds of Gaussian noise, spanning from 4% to 14%. In total, 38500 pairs were utilized for convergence and evaluation of the proposed

关键词： Deep learning Training Pathology Noise reduction Magnetic resonance Nonhomogeneous media Thermal noise Noise measurement Radiomics Noise level

来源：评论

学校读者我要写书评

暂无评论

Port-Hamiltonian Modeling and Control of Electric Vehicle Charging Stations

arXiv

引用

arXiv 2024年

作者： Gernandt, Hannes Severino, Bernardo Zhang, Xinyi Mehrmann, Volker Strunz, Kai The Department of Mathematics Bergische Universität Wuppertal Wuppertal42119 Germany The Fraunhofer Research Insitution for Energy Infrastructures and Geothermal Systems IEG Cottbus03046 Germany The Department of Mathematics Technische Universität Berlin Berlin10623 Germany The SENSE Laboratory Department of Electrical Engineering and Computer Sciences Technische Universität Berlin Berlin10587 Germany

Electric vehicles (EV) are an important part of future sustainable transportation. The increasing integration of EV charging stations (EVCSs) in the existing power grids require new scaleable control algorithms that maintain the stability and resilience of the grid. Here, we present such a control approach using an averaged port-Hamiltonian model. In this approach, the underlying switching behavior of the power converters is approximated by an averaged non-linear system. The averaged models are used to derive various types of stabilizing controllers, including the typically used PI controllers. The pH modeling is showcased by means of a generic setup of an EVCS, where the battery of the vehicle is connected to an AC grid via power lines, converters, and filters. Finally, the control design methods are compared for the averaged pH system and validated using a simulation model of the switched charging station. © 2024, CC BY.

关键词： Electric vehicles

来源：评论

学校读者我要写书评

暂无评论

Tractable Data Enriched Distributionally Robust Chance-Constrained CVR

arXiv

引用

arXiv 2022年

作者： Zhang, Qianzhi Bu, Fankun Guo, Yi Wang, Zhaoyu Department of Electrical and Computer Engineering Iowa State University AmesIA50011 United States Power Systems Laboratory ETH Zürich Zürich8092 Switzerland

This paper proposes a tractable distributionally robust chance-constrained conservation voltage reduction (DRCC-CVR) method with enriched data-based ambiguity set in unbalanced three-phase distribution systems. The increasing penetration of distributed renewable energy not only brings clean power but also challenges the voltage regulation and energy-saving performance of CVR by introducing high uncertainties to distribution systems. In most cases, the conventional robust optimization methods for CVR only provide conservative solutions. To better consider the impacts of load and PV generation uncertainties on CVR implementation in distribution systems and provide less conservative solutions, this paper develops a data-based DRCC-CVR model with tractable reformulation and data enrichment method. Even though the uncertainties of load and photovoltaic (PV) can be captured by data, the availability of smart meters (SMs) and micro-phasor measurement units (PMUs) is restricted by cost budget. The limited data access may hinder the performance of the proposed DRCC-CVR. Thus, we further present a data enrichment method to statistically recover the high-resolution load and PV generation data from low-resolution data with Gaussian Process Regression (GPR) and Markov Chain (MC) models, which can be used to construct a data-based moment ambiguity set of uncertainty distributions for the proposed DRCC-CVR. Finally, the nonlinear power flow and voltage dependant load models and DRCC with moment-based ambiguity set are reformulated to be computationally tractable and tested on a real distribution feeder in Midwest U. S. to validate the effectiveness and robustness of the proposed method. © 2022, CC BY.

关键词： Energy conservation

来源：评论

学校读者我要写书评

暂无评论

Hierarchical Resilience Planning for Networked Microgrids: A Case Study of Puerto Rico

Hierarchical Resilience Planning for Networked Microgrids: A...

引用

IEEE Industry Applications Society Annual Meeting (IAS)

作者： Jitendra Thapa Bikash Poudel Michael Stadler Muhammad Mansoor Timothy R. McJunkin C. P. Smith Mohammed Benidris Department of Electrical and Computer Engineering Michigan State University East Lansing MI Idaho National Laboratory Power and Energy Systems Idaho Falls Idaho U.S.A. Xendee Corporation La Jolla CA USA Cooperativa Hidroeléctrica de la Montaña Puerto Rico

ISBN: (数字)9798350372717

ISBN: (纸本)9798350372724

Microgrids can be designed to enhance the energy resilience of communities and critical infrastructures, such as hospitals, data centers, and communication networks, which are vulnerable to frequent weather-related disruption. Coordinating multiple microgrids in a network can leverage the geographical diversity of load and generation resources while enabling resilient and cost-effective planning of the distribution system. Designing a networked microgrid is complex, involving intricate technical assessment, cost-benefit analysis, site-specific requirements, and the evaluation of existing resources. Therefore, this paper proposes a hierarchical resilience planning framework and performs an extensive techno-economic analysis for the design of a networked microgrid. Hierarchical resilience planning involves technology sizing at an individual community level to meet the critical load and satisfy resilience criteria, and resource optimization at networked microgrid level to provide a higher level of resilience and energy adequacy. A real-world case of Puerto Rico's cooperative microgrid “Microrred de la Montaña” is investigated considering localized electricity tariffs, site-specific demand profiles, solar generation, and existing hydro resources. Multiple optimization scenarios are developed based on the resiliency requirement to estimate the capacity of solar photovoltaic and battery energy storage (BES) to be installed at each substation. The results provide the optimal sizing for individual community and networked microgrid to withstand 1day and 3-day outages along with the criteria for critical load.

关键词： Photovoltaic systems Technical management Substations Tariffs Microgrids Planning Batteries Optimization System analysis and design Resilience

来源：评论

学校读者我要写书评

暂无评论

GAT: GENERATIVE ADVERSARIAL TRAINING FOR ADVERSARIAL EXAMPLE DETECTION AND ROBUST CLASSIFICATION 8

GAT: GENERATIVE ADVERSARIAL TRAINING FOR ADVERSARIAL EXAMPLE...

引用

8th International Conference on Learning Representations, ICLR 2020

作者： Yin, Xuwang Kolouri, Soheil Rohde, Gustavo K. Department of Electrical and Computer Engineering University of Virginia United States Information and Systems Sciences Laboratory HRL Laboratories LLC

The vulnerabilities of deep neural networks against adversarial examples have become a significant concern for deploying these models in sensitive domains. Devising a definitive defense against such attacks is proven to be challenging, and the methods relying on detecting adversarial samples are only valid when the attacker is oblivious to the detection mechanism. In this paper we propose a principled adversarial example detection method that can withstand norm-constrained white-box attacks. Inspired by one-versus-the-rest classification, in a K class classification problem, we train K binary classifiers where the i-th binary classifier is used to distinguish between clean data of class i and adversarially perturbed samples of other classes. At test time, we first use a trained classifier to get the predicted label (say k) of the input, and then use the k-th binary classifier to determine whether the input is a clean sample (of class k) or an adversarially perturbed example (of other classes). We further devise a generative approach to detecting/classifying adversarial examples by interpreting each binary classifier as an unnormalized density model of the class-conditional data. We provide comprehensive evaluation of the above adversarial example detection/classification methods, and demonstrate their competitive performances and compelling properties. © 2020 8th International Conference on Learning Representations, ICLR 2020. All rights reserved.

关键词： Deep neural networks

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：