检索结果-内蒙古大学图书馆

37th International Conference on Machine Learning, ICML 2020

作者： Xiong, Ruibin Yang, Yunchang He, Di Zheng, Kai Zheng, Shuxin Xing, Chen Zhang, Huishuai Lan, Yanyan Wang, Liwei Liu, Tie-Yan CAS Key Laboratory of Network Data Science and Technology Institute of Computing Technolog Chinese Academy of Sciences China University of Chinese Academy of Sciences China Center for Data Science Peking University Beijing Institute of Big Data Research China Key Laboratory of Machine Perception MOE School of EECS Peking University China Microsoft Research College of Computer Science Nankai University China

ISBN: (纸本)9781713821120

The Transformer is widely used in natural language processing tasks. To train a Transformer however, one usually needs a carefully designed learning rate warm-up stage, which is shown to be crucial to the final performance but will slow down the optimization and bring more hyperparameter tunings. In this paper, we first study theoretically why the learning rate warm-up stage is essential and show that the location of layer normalization matters. Specifically, we prove with mean field theory that at initialization, for the original-designed Post-LN Transformer, which places the layer normalization between the residual blocks, the expected gradients of the parameters near the output layer are large. Therefore, using a large learning rate on those gradients makes the training unstable. The warm-up stage is practically helpful for avoiding this problem. On the other hand, our theory also shows that if the layer normalization is put inside the residual blocks (recently proposed as Pre-LN Transformer), the gradients are well-behaved at initialization. This motivates us to remove the warm-up stage for the training of Pre-LN Transformers. We show in our experiments that Pre-LN Transformers without the warm-up stage can reach comparable results with baselines while requiring significantly less training time and hyper-parameter tuning on a wide range of applications. Copyright 2020 by the author(s).

关键词： Mean field theory

来源：评论

学校读者我要写书评

暂无评论

A Predictive-Trend-Aware and Critical-Path-Estimation-Based Method for Workflow Scheduling Upon Cloud Services

A Predictive-Trend-Aware and Critical-Path-Estimation-Based ...

引用

IEEE International Conference on Services computing (SCC)

作者： Yi Pan Xiaoning Sun Yunni Xia Wanbo Zheng Xin Luo College of Computer Science Chongqing University Chongqing China Data Science Research Center Faculty of Science Kunming University of Science and Technology Kunming China Chongqing Engineering Research Center of Big Data Application for Smart Cities Chongqing Key Laboratory of Big Data and Intelligent Computing Chongqing Institute of Green and Intelligent Technology Chinese Academy of Sciences Chongqing China Hengrui (Chongqing) Artificial Intelligence Research Center Cloudwalk China

ISBN: (数字)9781728187891

ISBN: (纸本)9781728187907

The cloud computing paradigm is featured by its ability to offer elastic computational resource provisioning patterns and deliver on-demand and versatile services. It's thus getting increasingly popular to build business process and workflow-based applications upon cloud computing platforms. However, it remains a difficulty to guarantee cost-effectiveness and quality of service of cloud-based workflows because real-world cloud services are usually subject to real-time performance variations or fluctuations. Existing researches mainly consider that cloud are with constant performance and formulate the scheduling decision-making as a static optimization problem. In this work, instead, we consider that scientific computing processes to be supported by decentralized cloud infrastructures are with fluctuating QoS and aim at managing the monetary cost of workflows with the completion-time constraint to be satisfied. We address the performance-trend-aware workflow scheduling problem by leveraging a time-series-based prediction model and a Critical-Path-Duration-Estimation-based (CPDE for short) scheduling strategy. The proposed method is capable of exploiting real-time trends of performance changes of cloud infrastructures and generating dynamic workflow scheduling plans. To prove the effectiveness of our proposed method, we build a large-prime-number-generation workflow supported by real-world third-party commercial clouds and show that our method clearly beats existing approaches in terms of cost, workflow completion time, and Service-Level-Agreement (SLA) violation rate.

关键词： Cloud computing Processor scheduling Computational modeling Quality of service Predictive models Dynamic scheduling Real-time systems

来源：评论

学校读者我要写书评

暂无评论

LQR Control Method based on Improved Antlion Algorithm

LQR Control Method based on Improved Antlion Algorithm

引用

Chinese Control Conference (CCC)

作者： Zhe Sun Zhi Wen Lei Xu Guangfu Gong Xiangpeng Xie Zhixin Sun Post Industry Technology Research and Development Center of the State Posts Bureau (Internet of Things Technology) Nanjing University of Posts and Telecommunications Nanjing P.R. China Post Big Data Technology and Application Engineering Research Center of Jiangsu Province Nanjing University of Posts and Telecommunications Nanjing China Key Lab of Broadband Wireless Communication and Sensor Network Technology Ministry of Education Nanjing University of Posts and Telecommunications Nanjing P.R. China Anhui Yougu Express Intelligent Technology Co. LTD Nanling Anhui P.R. China

In the face of the increasing demand of crane transportation speed and stability, an improved Ant-lion algorithm is proposed in this paper. On the original basis, the quasi-reverse learning method is used to improve the stability of the algorithm and make the initial data distributed evenly. Furthermore, an elite ant-lion growth mechanism is introduced to accelerate the convergence speed of the simulation and improve the simulation accuracy. Finally, the proposed algorithm is verified in the double pendulum system of crane based on LQR controller, and the feasibility and effectiveness of the proposed algorithm are proved by experiments.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A WOA Based Switching PID Control for Overhead Crane

A WOA Based Switching PID Control for Overhead Crane

引用

Chinese Control Conference (CCC)

作者： Haoyong Yu Zhe Sun Yuhua Xu Lei Xu Guangfu Gong Xiangpeng Xie Zhixin Sun Post Industry Technology Research and Development Center of the State Posts Bureau (Internet of Things Technology) Nanjing University of Posts and Telecommunications Nanjing P.R. China Post Big Data Technology and Application Engineering Research Center of Jiangsu Province Nanjing University of Posts and Telecommunications Nanjing China Key Lab of Broadband Wireless Communication and Sensor Network Technology Ministry of Education Nanjing University of Posts and Telecommunications Nanjing P.R. China Anhui Yougu Express Intelligent Technology Co. LTD Nanling Anhui P.R. China

Aiming at the problem that the amplitude of load oscillation is not easy to control in the movement process of overhead crane, this paper designs a switching PID control method based on whale optimization algorithm(WOA) to improve the performance of position control and anti-swing control for overhead crane. WOA is used to better adjust the parameters of PID controllers. The switching control is realized by a switching module, which defaults to the output of the Position PID Controller to provide control force for the trolley. When the absolute value of the load swing angle fed back by the crane system exceeds the warning value, the switching module immediately blocks the output of the Position PID Controller, and uses the Angle PID Controller to determine the control force. In addition, through theoretical analysis and simulation experiments under different conditions, the results verify the effectiveness of the WOA based switching control in position control and anti-swing control for overhead crane. Improve the efficiency and safety of overhead crane in practical industrial applications.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Non-invasive estimation of pulmonary hypertension and clinical deterioration risk in pediatric congenital heart disease:Development and validation of predictive tools

引用

Chinese Medical Journal 2024年第11期137卷 1384-1386页

作者： Ting Wang Dansha Zhou Yuqin Chen Suhua Kuang Yue Xing Qijian Yi Zhengxia Pan Weibin Xu Jiao Rao Yunqi Liu Guoliang Lu Ziying Lin Xiang Li Yi Xie Yulong Wu Peng An Xiaoxiao Deng Jiayue He Jiayi Xie Chenxi Li Gang Geng Daiyin Tian Enmei Liu Jingsi Huang Zhou Fu Jian Wang Department of Respiratory Chongqing Higher Institution Engineering Research Center of Children’s Medical Big Data Intelligent ApplicationNational Clinical Research Center for Child Health and DisordersMinistry of Education Key Laboratory of Child Development and DisordersChildren’s Hospital of Chongqing Medical UniversityChongqing 400014China State Key Laboratory of Respiratory Diseases National Center for Respiratory MedicineGuangdong Key Laboratory of Vascular DiseasesNational Clinical Research Center for Respiratory DiseasesGuangzhou Institute of Respiratory Healththe First Affiliated Hospital of Guangzhou Medical UniversityGuangzhou Medical UniversityGuangzhouGuangdong 510120China Department of Cardiac Surgery The First Affiliated Hospital of Guangzhou Medical UniversityGuangzhou Medical UniversityGuangzhouGuangdong 510120China Department of Cardiovascular Medicine Children’s Hospital of Chongqing Medical University National Clinical Research Center for Child Health and DisordersMinistry of Education Key Laboratory of Child Development and DisordersChildren’s Hospital of Chongqing Medical UniversityChongqing 400014China Department of Thoracic and Cardiac Surgery Children’s Hospital of Chongqing Medical University National Clinical Research Center for Child Health and DisordersMinistry of Education Key Laboratory of Child Development and DisordersChildren’s Hospital of Chongqing Medical UniversityChongqing 400014China Department of Cardiac Center of Guangdong Women and Children Hospital Guangzhou GuangzhouGuangdong 511400China Department of Guangzhou Laboratory Guangzhou International Bio IslandGuangzhouGuangdong 510005China

To the Editor:Owing to the heterogeneity of congenital heart disease-associated pulmonary hypertension(CHDPH)disease and the development of the pulmonary vascular system in pediatric patients,the management of CHD-PH in children is signicantly different from that in adults.[1]Early identication and intervention of CHD-PH are of great signicance for disease management in children with CHD,and non-invasive,accurate clinical tools are urgently needed to predict PH risk in children with ***,the applicability of the current risk-scoring system to pediatric CHD-PH remains ***,there are presently no user-friendly,non-invasive online tools available for predicting CHD-PH,and there is a scarcity of related studies in Asian *** study aimed to develop and validate the prediction tools for estimating the risk of pulmonary hypertension and clinical deterioration in children with congenital heart disease.

关键词： pediatric congenital hypertension

来源：评论

学校读者我要写书评

暂无评论

BEFD: Boundary enhancement and feature denoising for vessel segmentation

arXiv

引用

arXiv 2021年

作者： Zhang, Mo Yu, Fei Zhao, Jie Zhang, Li Li, Quanzheng Center for Data Science Peking University Beijing100871 China Center for Data Science in Health and Medicine Peking University Beijing100871 China Laboratory for Biomedical Image Analysis Beijing Institute of Big Data Research Beijing100871 China Center for Advanced Medical Computing and Analysis MGH/BWH Center for Clinical Data Science Department of Radiology Massachusetts General Hospital Harvard Medical School BostonMA02115 United States

Blood vessel segmentation is crucial for many diagnostic and research applications. In recent years, CNN-based models have leaded to breakthroughs in the task of segmentation, however, such methods usually lose high-frequency information like object boundaries and subtle structures, which are vital to vessel segmentation. To tackle this issue, we propose Boundary Enhancement and Feature Denoising (BEFD) module to facilitate the network ability of extracting boundary information in semantic segmentation, which can be integrated into arbitrary encoder-decoder architecture in an end-to-end way. By introducing Sobel edge detector, the network is able to acquire additional edge prior, thus enhancing boundary in an unsupervised manner for medical image segmentation. In addition, we also utilize a denoising block to reduce the noise hidden in the low-level features. Experimental results on retinal vessel dataset and angiocarpy dataset demonstrate the superior performance of the new BEFD module. © 2021, CC BY-NC-SA.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Vflh: A Following-the-Leader-History Based Algorithm for Adaptive Online Convex Optimization with Stochastic Constraints

SSRN

引用

SSRN 2022年

作者： Yang, Yifan Chen, Lin Zhou, Pan Ding, Xiaofeng Department of Computer Science University of California Santa BarbaraCA93106 United States National Engineering Research Center for Big Data Technology and System Lab Services Computing Technology and System Lab Cluster and Grid Computing Lab School of Computer Science and Technology Huazhong University of Science and Technology Wuhan430074 China School of Cyber Science and Engineering Huazhong University of Science and Technology Hubei Wuhan430072 China

This paper considers online convex optimization (OCO) with generated i.i.d. stochastic constraints, where the distribution of environment is changing and the performance is measured by \textit{adaptive regret}. The stochastic constraints are disclosed at each round to the learner after the decision is made. Different from the previous non-adaptive constrained OCO algorithm which is generalized based on the traditional online gradient descent algorithm, we propose a novel \textit{Virtual queue based Following-the-Leader-History} (VFLH) strategy to make the constrained OCO algorithm adaptive and design the VFLH algorithm. In this setting, the algorithm firstly generalizes all the experts in the specified time interval, then decides the optimal decision with each expert and gives out the final choice by combining the predictions of active experts. In terms of the algorithm performance, there are two performance metrics to be evaluated, i.e., the bounds of constraint violation and regret. For the constraint violation, we bring in the multi-objective drift analysis approach to deal with the constraints via a virtual queue which provides a new method to bound the constraints violations. For the regret, we give out its upper bound and then achieve a corresponding lower bound that proves the upper bound is sufficiently tight. Finally, we provide some numerical experiments to validate the feasibility of our algorithm. © 2022, The Authors. All rights reserved.

关键词： Stochastic systems

来源：评论

学校读者我要写书评

暂无评论

Overview of the Tenth Dialog System Technology Challenge: DSTC10

引用

IEEE/ACM Transactions on Audio Speech and Language Processing 2024年 32卷 765-778页

作者： Yoshino, Koichiro Chen, Yun-Nung Crook, Paul Kottur, Satwik Li, Jinchao Hedayatnia, Behnam Moon, Seungwhan Fei, Zhengcong Li, Zekang Zhang, Jinchao Feng, Yang Zhou, Jie Kim, Seokhwan Liu, Yang Jin, Di Papangelis, Alexandros Gopalakrishnan, Karthik Hakkani-Tur, Dilek Damavandi, Babak Geramifard, Alborz Hori, Chiori Shah, Ankit Zhang, Chen Li, Haizhou Sedoc, Joao D'haro, Luis F. Banchs, Rafael Rudnicky, Alexander Guardian Robot Project R-IH RIKEN 2-2-2 Hikaridai Seika Shoraku619-0288 Japan Information Science Nara Institute of Science and Technology Ikoma630-0101 Japan Computer Science and Information Engineering National Taiwan University Taipei10617 Taiwan Inc. Palo AltoCA95054 United States Alexa AI *** Inc. SunnyvaleCA94089 United States Meta Seattle RedmondWA98052 United States Institute of Computing Technology Chinese Academy of Sciences Beijing100190 China Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing100190 China Tencent AI Lab Beijing Beijing China Kexueyuan South Road Zhongguancun Beijing100190 China Beijing 100190 China Alexa AI *** Inc. SunnyvaleCA United States 1120 Enterprise way Sunnyvale94089 United States *** Inc. SeattleWA United States Menlo Park CA United States Audio and Speech Group Mitsubishi Electric Research Laboratories CambridgeMA02139-1955 United States Carnegie Mellon University Department of Language and Information Technologies or just Carnegie Mellon University Pittsburgh United States National University of Singapore Singapore Singapore Department of Electrical and Computer Engineering National University of Singapore Singapore Singapore Shenzhen Research Institute of Big Data School of Data Science Chinese University of Hong Kong Shenzhen518172 China New York University New YorkNY United States ETSI de Telecomunicacion - Speech Technology and Machine Learning Group Universidad Politecnica de Madrid Ciudad Universitaria Madrid28040 Spain Nanyang Technological University Singapore Singapore Carnegie Mellon University PittsburghPA United States

This article introduces the Tenth Dialog System Technology Challenge (DSTC-10). This edition of the DSTC focuses on applying end-to-end dialog technologies for five distinct tasks in dialog systems, namely 1. Incorporation of Meme images into open domain dialogs, 2. Knowledge-grounded Task-oriented Dialogue Modeling on Spoken Conversations, 3. Situated Interactive Multimodal dialogs, 4. Reasoning for Audio Visual Scene-Aware Dialog, and 5. Automatic Evaluation and Moderation of Open-domainDialogue Systems. This article describes the task definition, provided datasets, baselines, and evaluation setup for each track. We also summarize the results of the submitted systems to highlight the general trends of the state-of-the-art technologies for the tasks. © 2023 The Authors.

关键词： Job analysis

来源：评论

学校读者我要写书评

暂无评论

AID-DTI: ACCELERATING HIGH-FIDELITY DIFFUSION TENSOR IMAGING WITH DETAIL-PRESERVING MODEL-BASED DEEP LEARNING

arXiv

引用

arXiv 2024年

作者： Fan, Wenxin Cheng, Jian Li, Cheng Ma, Xinrui Yang, Jing Zou, Juan Wu, Ruoyou Liu, Qiegen Wang, Shanshan Paul C. Lauterbur Research Center for Biomedical Imaging Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Guangdong Shenzhen China University of Chinese Academy of Sciences Beijing China State Key Laboratory of Software Development Environment Beihang University Beijing China Key Laboratory of Data Science and Intelligent Computing Institute of International Innovation Beihang University Zhejiang Hangzhou China Peng Cheng Laboratory Guangdong Shenzhen China Nan Chang University Jiang Xi Nan Chang China

Deep learning has shown great potential in accelerating diffusion tensor imaging (DTI). Nevertheless, existing methods tend to suffer from Rician noise and detail loss in reconstructing the DTI-derived parametric maps especially when sparsely sampled q-space data are used. This paper proposes a novel method, AID-DTI (Accelerating hIgh fiDelity Diffusion Tensor Imaging), to facilitate fast and accurate DTI with only six measurements. AID-DTI is equipped with a newly designed Singular Value Decomposition (SVD)-based regularizer, which can effectively capture fine details while suppressing noise during network training. Experimental results on Human Connectome Project (HCP) data consistently demonstrate that the proposed method estimates DTI parameter maps with fine-grained details and outperforms three state-of-the-art methods both quantitatively and qualitatively. Copyright © 2024, The Authors. All rights reserved.

关键词： Singular value decomposition

来源：评论

学校读者我要写书评

暂无评论

Extraction of Typical Operating Scenarios of New Power System Based on Deep Time Series Aggregation

arXiv

引用

arXiv 2024年

作者： Qu, Zhaoyang Zhang, Zhenming Qu, Nan Zhou, Yuguang Li, Yang Jiang, Tao Li, Min Long, Chao School of Electrical Engineering Northeast Electric Power University Jilin132012 China Jilin Province Technology Research Center of Power Big Data Intelligent Processing Jilin132012 China State Grid Jiangsu Electric Power Co. Ltd. Nanjing Power Supply Branch Nanjing210008 China State Grid Jilin Electric Power Co. Ltd. Changchun130022 China Department of Electrical Engineering and Electronics University of Liverpool LiverpoolL69 3GJ United Kingdom

Extracting typical operational scenarios is essential for making flexible decisions in the dispatch of a new power system. This study proposed a novel deep time series aggregation scheme (DTSAs) to generate typical operational scenarios, considering the large amount of historical operational snapshot data. Specifically, DTSAs analyze the intrinsic mechanisms of different scheduling operational scenario switching to mathematically represent typical operational scenarios. A gramian angular summation field (GASF) based operational scenario image encoder was designed to convert operational scenario sequences into high-dimensional spaces. This enables DTSAs to fully capture the spatiotemporal characteristics of new power systems using deep feature iterative aggregation models. The encoder also facilitates the generation of typical operational scenarios that conform to historical data distributions while ensuring the integrity of grid operational snapshots. Case studies demonstrate that the proposed method extracted new fine-grained power system dispatch schemes and outperformed the latest high-dimensional feature-screening methods. In addition, experiments with different new energy access ratios were conducted to verify the robustness of the proposed method. DTSAs enables dispatchers to master the operation experience of the power system in advance, and actively respond to the dynamic changes of the operation scenarios under the high access rate of new energy. Copyright © 2024, The Authors. All rights reserved.

关键词： Image coding

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：