检索结果-内蒙古大学图书馆

arXiv 2019年

作者： Zheng, Guanhua Sang, Jitao Li, Houqiang Yu, Jian Xu, Changsheng University of Science and Technology of China School of Computer and Information Technology Beijing Key Laboratory of Traffic Data Analysis and Mining Beijing Jiaotong University Beijing100044 China Chinese Academy of Sciences Key Laboratory of Technology in Geo-Spatial Information Processing and Application System Hefei230026 China National Lab of Pattern Recognition Institute of Automation CAS Beijing100190 China University of Chinese Academy of Sciences

—Existing generalization theories analyze the generalization performance mainly based on the model complexity and training process. The ignorance of the task properties, which results from the widely used IID assumption, makes these theories fail to interpret many generalization phenomena or guide practical learning tasks. In this paper, we propose a new Independent and Task-Identically Distributed (ITID) assumption, to consider the task properties into the data generating process. The derived generalization bound based on the ITID assumption identifies the significance of hypothesis invariance in guaranteeing generalization performance. Based on the new bound, we introduce a practical invariance enhancement algorithm from the perspective of modifying data distributions. Finally, we verify the algorithm and theorems in the context of image classification task on both toy and real-world datasets. The experimental results demonstrate the reasonableness of the ITID assumption and the effectiveness of new generalization theory in improving practical generalization performance. Copyright © 2019, The Authors. All rights reserved.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

Author Correction: Enhanced oxygen reduction with single-atomic-site iron catalysts for a zinc-air battery and hydrogen-air fuel cell

引用

Nature communications 2022年第1期13卷 921页

作者： Yuanjun Chen Shufang Ji Shu Zhao Wenxing Chen Juncai Dong Weng-Chon Cheong Rongan Shen Xiaodong Wen Lirong Zheng Alexandre I Rykov Shichang Cai Haolin Tang Zhongbin Zhuang Chen Chen Qing Peng Dingsheng Wang Yadong Li Department of Chemistry Tsinghua University 100084 Beijing China. Beijing Guyue New Materials Research Institute Beijing University of Technology 100124 Beijing China. Beijing Synchrotron Radiation Facility Institute of High Energy Physics Chinese Academy of Sciences 100049 Beijing China. State Key Laboratory of Coal Conversion Institute of Coal Chemistry Chinese Academy of Sciences 030001 Taiyuan China. Mössbauer Effect Data Center Dalian Institute of Chemical Physics Chinese Academy of Sciences 116023 Dalian China. State Key Laboratory of Advanced Technology for Materials Synthesis and Processing Wuhan University of Technology 430070 Wuhan China. State Key Lab of Organic-Inorganic Composites and Beijing Advanced Innovation Center for Soft Matter Science and Engineering Beijing University of Chemical Technology 100029 Beijing China. Department of Chemistry Tsinghua University 100084 Beijing China. wangdingsheng@***.

来源：评论

学校读者我要写书评

暂无评论

Exploring Structural Sparsity of Deep networks via Inverse Scale Spaces

arXiv

引用

arXiv 2019年

作者： Fu, Yanwei Liu, Chen Li, Donghao Zhong, Zuyuan Sun, Xinwei Zeng, Jinshan Yao, Yuan School of Data Science Shanghai Key Lab of Intelligent Information Processing Fudan University Fudan ISTBI-ZJNU Algorithm Centre for Brain-Inspired Intelligence Zhejiang Normal University Jinhua China The School of Computer and Information Engineering Jiangxi Normal University China Hong Kong University of Science and Technology Hong Kong

The great success of deep neural networks is built upon their over-parameterization, which smooths the optimization landscape without degrading the generalization ability. Despite the benefits of over-parameterization, a huge amount of parameters makes deep networks cumbersome in daily life applications. On the other hand, training neural networks without over-parameterization faces many practical problems, e.g., being trapped in the local optimal. Though techniques such as pruning and distillation are developed, they are expensive in fully training a dense network as backward selection methods;and there is still a void on systematically exploring forward selection methods for learning structural sparsity in deep networks. To fill in this gap, this paper proposes a new approach based on differential inclusions of inverse scale spaces. Specifically, our method can generate a family of models from simple to complex ones along the dynamics via coupling a pair of parameters, such that over-parameterized deep models and their structural sparsity can be explored simultaneously. This kind of differential inclusion scheme has a simple discretization, dubbed Deep structure splitting Linearized Bregman Iteration (DessiLBI), whose global convergence in learning deep networks could be established under the Kurdyka-Lojasiewicz framework. Particularly, we explore several applications of DessiLBI, including finding sparse structures of networks directly via the coupled structure parameter and growing networks from simple to complex ones progressively. Experimental evidence shows that our method achieves comparable and even better performance than the competitive optimizers in exploring the sparse structure of several widely used backbones on the benchmark datasets. Remarkably, with early stopping, our method unveils "winning tickets" in early epochs: the effective sparse network structures with comparable test accuracy to fully trained over-parameterized models, that are further t

关键词： Linearization

来源：评论

学校读者我要写书评

暂无评论

Interactive Ontology Matching Based on Evolutionary Algorithm

Interactive Ontology Matching Based on Evolutionary Algorith...

引用

International Conference on Computational Intelligence and Security

作者： Xingsi Xue Junfeng Chen Aihong Ren College of Information Science and Engineering Intelligent Information Processing Research Center Fujian Key Lab for Automotive Electronics and Electric Drive Fujian Provincial Key Laboratory of Big Data Mining and Applications Fujian University of Technology Fuzhou China College of IOT Engineering Hohai University ChanZhou China School of Mathematics and Information Science Baoji University of Arts and Sciences Baoji China

ISBN: (数字)9781728160924

ISBN: (纸本)9781728160931

Since different ontologies are mostly developed independently, establishing meaningful links between their entities, so-called ontology matching, is critical to ensure their communication. Due to the complexity of the ontology matching problem, Evolutionary Algorithm (EA) can present a good methodology for determining ontology alignments. However, since none of the similarity measure can distinguish all the identical ontology entities in any context, ontology alignments generated by the automatic matching tools should be validated by the users to ensure their qualities. To improve the quality of the ontology alignment, in this work, a similarity measure is first proposed to calculate the similarity value of two ontology entities; then, an optimal model for ontology matching problem is constructed; after that, an EA-based automatic matcher is presented to solve the ontology matching problem, which can also adaptively determine the timing of getting user involved; and finally, the ontology concept hierarchy graph based reasoning approaches are proposed to tradeoff the user's workload and his work's effect. The experiment is conducted on the Interactive track provided by the Ontology Alignment Evaluation Initiative (OAEI), and the comparisons with OAEI's participants show the effectiveness of our proposal.

关键词： Ontologies Graph theory Pattern matching Evolutionary computation

来源：评论

学校读者我要写书评

暂无评论

Learning a deep listwise context model for ranking refinement

arXiv

引用

arXiv 2018年

作者： Ai, Qingyao Bi, Keping Guo, Jiafeng Croft, W. Bruce College of Information and Computer Sciences University of Massachusetts Amherst AmherstMA United States CAS Key Lab of Network Data Science and Technology Institute of Computing Technology Chinese Academy of Sciences Beijing China

Learning to rank has been intensively studied and widely applied in information retrieval. Typically, a global ranking function is learned from a set of labeled data, which can achieve good performance on average but may be suboptimal for individual queries by ignoring the fact that relevant documents for different queries may have different distributions in the feature space. Inspired by the idea of pseudo relevance feedback where top ranked documents, which we refer as the local ranking context, can provide important information about the query's characteristics, we propose to use the inherent feature distributions of the top results to learn a Deep Listwise Context Model that helps us fine tune the initial ranked list. Specifically, we employ a recurrent neural network to sequentially encode the top results using their feature vectors, learn a local context model and use it to re-rank the top results. There are three merits with our model: (1) Our model can capture the local ranking context based on the complex interactions between top results using a deep neural network;(2) Our model can be built upon existing learning-to-rank methods by directly using their extracted feature vectors;(3) Our model is trained with an attention-based loss function, which is more effective and efficient than many existing listwise methods. Experimental results show that the proposed model can significantly improve the state-of-the-art learning to rank methods on benchmark retrieval corpora. Copyright © 2018, The Authors. 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

Age-Based Utility Maximization for Wireless Powered networks: A Stackelberg Game Approach

Age-Based Utility Maximization for Wireless Powered Networks...

引用

IEEE Global Communications Conference

作者： Haina Zheng Ke Xiong Pingyi Fan Zhangdui Zhong Khaled Ben Letaief School of Computer and Information Technology Beijing Jiaotong University Beijing China Beijing Key Laboratory of Traffic Data Analysis and Mining Beijing Jiaotong University Beijing China Department of Electronic Engineering Tsinghua University Beijing China State Key Lab of Rail Traffic Control and Safety Beijing Jiaotong University Beijing China The Hong Kong University of Science and Technology Hong Kong

ISBN: (数字)9781728109626

ISBN: (纸本)9781728109633

This paper investigates the efficient cooperation in wireless-powered communication networks, where an access point (AP) and multiple helpers first together charge up a sensor via radio-frequency (RF)-based wireless power transfer (WPT), and then the sensor uses the harvested energy to transmit real-time status updates to the AP. Due to the selfishness of the helpers, payment is provided as an incentive to them by the sensor-AP communication pair. For such a system, a Stackelberg game approach is designed to establish efficient cooperation between the helpers and the sensor-AP communication pair. An Age of Information (AoI)-based utility and a profit-based utility are defined for the sensor-AP pair and the helpers, respectively. Optimization problems are formulated to maximize their utilities. An explicit expression of the optimal transmit power of the helper is derived, with which a Dinkelbach's Programming (DP)-based algorithm is designed to jointly find the optimal payment price and transmit power at the AP, and at the same time, the Stackelberg equilibrium (SE) is achieved. Moreover, a closed-form expression of the minimum AoI of the system is also presented. Numerical results show that the more helpers there exist, the higher payment price the AP should fix, and meanwhile, the lower AoI of the sensor-AP communication pair can be achieved. Besides, it is shown that by increasing the transmit power at the AP, the optimal average AoI could not be reduced evidently.

关键词： Games Real-time systems Energy harvesting Wireless communication Measurement Batteries Wireless sensor networks

来源：评论

学校读者我要写书评

暂无评论

ConfigFile++: Automatic comment enhancement for misconfiguration prevention

ConfigFile++: Automatic comment enhancement for misconfigura...

引用

IEEE Workshop on Machine Learning Techniques for Software Quality Evaluation (MaLTeSQuE)

作者： Yuanliang Zhang Shanshan Li Xiangyang Xu Xiangke Liao Shazhou Yang Yun Xiong College of Computer Science National University of Defense Technology China Shanghai Key Lab of Data Science Fudan University China

Nowadays, misconfiguration has become one of the key factors leading to system problems. Most current research on the topic explores misconfiguration diagnosis, but is less concerned with educating users about how to configure correctly in order to prevent misconfiguration before it happens. In this paper, we manually study 22 open source software projects and summarize several observations on the comments of their configuration files, most of which lack sufficient information and are poorly formatted. Based on these observations and the general process of misconfiguration diagnosis, we design and implement a tool called ConfigFile++ that automatically enhances the comment in configuration files. By using name-based analysis and machine learning, ConfigFile++ extracts guiding information about the configuration option from the user manual and source code, and inserts it into the configuration files. The format of insert comment is also designed to make enhanced comments concise and clear. We use real-world examples of misconfigurations to evaluate our tool. The results show that ConfigFile++ can prevent 33 out of 50 misconfigurations.

关键词： Manuals Tools data mining Syntactics Software systems Open source software

来源：评论

学校读者我要写书评

暂无评论

A Performance Comparison of Big data Processing Platform Based on Parallel Clustering Algorithms

引用

Procedia Computer science 2018年 139卷 127-135页

作者： Mo Hai Yuejing Zhang Haifeng Li School of Information Central University of Finance and Economics Beijing 100081 China Network and Data Security Key Laboratory of Sichuan Province University of Electronic Science and Technology of China Chengdu 610054 China

The performance of three typical big data processing platform: Hadoop, Spark and dataMPI are compared based on different parallel clustering algorithms: parallel K-means, parallel fuzzy K-means and parallel Canopy. Experiments are performed on different text as well as numeric dataset and clusters of different scale. The results show that: (1) for the same data set, when the memory of each node is 4GB, dataMPI can achieve about 60% performance improvement compared with Hadoop, and can achieve about 32% performance improvement compared with Spark; (2) in order to obtain a high clustering performance, a cluster with 6 nodes and 6GB memory of each node should be selected.

关键词： Hadoop Spark dataMPI K-means fuzzy K-means Canopy

来源：评论

学校读者我要写书评

暂无评论

A Novel Method for ECG Signal Classification via One-Dimensional Convolutional Neural network

arXiv

引用

arXiv 2020年

作者： Hua, Xuan Han, Jungang Zhao, Chen Tang, Haipeng He, Zhuo Tang, Jinshan Chen, Qing-Hui Tang, Shaojie Zhou, Weihua College of Electronic Engineering Xi’an University of Posts and Telecommunications Xi’an710121 China Key Laboratory of Network Data Analysis and Intelligent Processing in Shaanxi Xi’an710121 China College of Computer Science and Technology Xi’an University of Posts and Telecommunications Xi’an710121 China College of Computing Michigan Technological University HoughtonMI49931 United States School of Computing University of Southern Mississippi Long Beach39560 United States Deprtment of Kinesiology and Integrative Physiology Michigan Technological University HoughtonMI49931 United States School of Automation Xi’an University of Posts and Telecommunications Xi’an710121 China

This paper presents an end-to-end ECG signal classification method based on a novel segmentation strategy via 1D Convolutional Neural networks (CNN) to aid the classification of ECG signals. The ECG segmentation strategy named R-R-R strategy (i.e., retaining ECG data between the R peaks just before and after the current R peak) for segmenting the original ECG data into segments in order to train and test the 1D CNN models. The novel strategy mimics physicians in scanning ECG to a greater extent, and maximizes the inherent information of ECG segments. The performance of the classification models for 5-class and 6-class are verified with ECG signals from 48 records of the MIT-BIH arrhythmia database. As the heartbeat types are divided into 5 classes (i.e., normal beat, left bundle branch block beat, right bundle branch block beat, ventricular ectopic beat, and paced beat) in the MIT-BIH, the best classification accuracy, the area under the curve (AUC), the sensitivity and the F1-score reach 99.24%, 0.9994, 0.99 and 0.99, respectively. As the heartbeat types are divided into 6 classes (i.e., normal beat, left bundle branch block beat, right bundle branch block beat, ventricular ectopic beat, paced beat and other beats) in the MIT-BIH, the beat classification accuracy, the AUC, the sensitivity, and the F1-score reach 97.02%, 0.9966, 0.97, and 0.97, respectively. Meanwhile, according to the recommended practice from the Association for Advancement of Medical Instrumentation (AAMI), the heartbeat types are divided into 5 classes (i.e., normal beat, supraventricular ectopic beats, ventricular ectopic beats, fusion beats, and unclassifiable beats), the beat classification accuracy, the sensitivity, and the F1-score reach 97.45%, 0.97, and 0.97, respectively. The experimental results show that the proposed method achieves better performance than the state-of-the-art methods. Copyright © 2020, The Authors. All rights reserved.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Accurate Recovery of Internet Traffic data: A Sequential Tensor Completion Approach

Accurate Recovery of Internet Traffic Data: A Sequential Ten...

引用

作者： Xie, Kun Wang, Lele Wang, Xin Xie, Gaogang Wen, Jigang Zhang, Guangxing Cao, Jiannong Zhang, Dafang College of Computer Science and Electronics Engineering Hunan University Changsha410006 China CAS Key Laboratory of Network Data Science and Technology Institute of Computing Technology Chinese Academy of Sciences Beijing100864 China Department of Electrical and Computer Engineering State University of New York at Stony Brook Stony BrookNY11794 United States Network Research Center Institute of Computing Technology Chinese Academy of Sciences Beijing100864 China Department of Computing Hong Kong Polytechnic University Hong Kong Hong Kong

The inference of traffic volume of the whole network from partial traffic measurements becomes increasingly critical for various network engineering tasks, such as capacity planning and anomaly detection. Previous studies indicate that the matrix completion is a possible solution for this problem. However, as a 2-D matrix cannot sufficiently capture the spatial-temporal features of traffic data, these approaches fail to work when the data missing ratio is high. To fully exploit hidden spatial-temporal structures of the traffic data, this paper models the traffic data as a 3-way traffic tensor and formulates the traffic data recovery problem as a low-rank tensor completion problem. However, the high computation complexity incurred by the conventional tensor completion algorithms prevents its practical application for the traffic data recovery. To reduce the computation cost, we propose a novel sequential tensor completion algorithm, which can efficiently exploit the tensor decomposition result based on the previous traffic data to derive the tensor decomposition upon arriving of new data. Furthermore, to better capture the changes of data correlation over time, we propose a dynamic sequential tensor completion algorithm. To the best of our knowledge, we are the first to propose sequential tensor completion algorithms to significantly speed up the traffic data recovery process. This facilitates the modeling of Internet traffic with the tensor to well exploit the hidden structures of traffic data for more accurate missing data inference. We have done extensive simulations with the real traffic trace as the input. The simulation results demonstrate that our algorithms can achieve significantly better performance compared with the literature tensor and matrix completion algorithms even when the data missing ratio is high. © 1993-2012 IEEE.

关键词： Tensors

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：