检索结果-内蒙古大学图书馆

arXiv 2017年

作者： Zhang, Liang Wang, Gang Giannakis, Georgios B. Chen, Jie Digital Technology Center Department of Electrical and Computer Engineering University of Minnesota MinneapolisMN55455 United States State Key Laboratory of Intelligent Control and Decision of Complex Systems Beijing100081 China School of Automation State Key Laboratory of Intelligent Control and Decision of Complex Systems Beijing Institute of Technology Beijing100081 China

The problem of reconstructing a sparse signal vector from magnitude-only measurements (a.k.a., compressive phase retrieval), emerges naturally in diverse applications, but it is NP-hard in general. Building on recent advances in nonconvex optimization, this paper puts forth a new algorithm that is termed compressive reweighted amplitude flow and abbreviated as CRAF, for compressive phase retrieval. Specifically, CRAF operates in two stages. The first stage seeks a sparse initial guess via a new spectral procedure. In the second stage, CRAF implements a few hard thresholding based iterations using reweighted gradients. When there are sufficient measurements, CRAF provably recovers the underlying signal vector exactly with high probability under suitable conditions. Moreover, its sample complexity coincides with that of the state-of-the-art procedures. Finally, substantial simulated tests showcase remarkable performance of the new spectral initialization, as well as improved exact recovery relative to competing alternatives. Copyright © 2017, The Authors. All rights reserved.

关键词： Iterative methods

来源：评论

学校读者我要写书评

暂无评论

Learning with rethinking: Recurrently improving convolutional neural networks through feedback

arXiv

引用

arXiv 2017年

作者： Li, Xin Jie, Zequn Feng, Jiashi Liu, Changsong Yan, Shuicheng State Key Laboratory of Intelligent Technology and Systems Tsinghua National Laboratory for Information Science and Technology Tsinghua National Laboratory for Information Science and Technology Department of Electronic Engineering Tsinghua University Beijing100084 China Department of Electrical and Computer Engineering National University of Singapore Singapore117583 Singapore

Recent years have witnessed the great success of convolutional neural network (CNN) based models in the field of computer vision. CNN is able to learn hierarchically abstracted features from images in an end-to-end training manner. However, most of the existing CNN models only learn features through a feedforward structure and no feedback information from top to bottom layers is exploited to enable the networks to refine themselves. In this paper, we propose a "Learning with Rethinking" algorithm. By adding a feedback layer and producing the emphasis vector, the model is able to recurrently boost the performance based on previous prediction. Particularly, it can be employed to boost any pre-trained models. This algorithm is tested on four object classification benchmark datasets: CIFAR-100, CIFAR-10, MNIST-background-image and ILSVRC-2012 dataset. These results have demonstrated the advantage of training CNN models with the proposed feedback mechanism. Copyright © 2017, The Authors. All rights reserved.

关键词： Image classification

来源：评论

学校读者我要写书评

暂无评论

Deep ranking: Triplet MatchNet for music metric learning

Deep ranking: Triplet MatchNet for music metric learning

引用

IEEE International Conference on Acoustics, Speech and Signal Processing

作者： Rui Lu Kailun Wu Zhiyao Duan Changshui Zhang Department of Automation Tsinghua University State Key Lab of Intelligent Technologies and Systems Tsinghua National Laboratory for Information Science and Technology (TNList) Beijing China Department of Electrical and Computer Engineering University of Rochester NY USA

ISBN: (纸本)9781509041183

Metric learning for music is an important problem for many music information retrieval (MIR) applications such as music generation, analysis, retrieval, classification and recommendation. Traditional music metrics are mostly defined on linear transformations of handcrafted audio features, and may be improper in many situations given the large variety of music styles and instrumentations. In this paper, we propose a deep neural network named Triplet MatchNet to learn metrics directly from raw audio signals of triplets of music excerpts with human-annotated relative similarity in a supervised fashion. It has the advantage of learning highly nonlinear feature representations and metrics in this end-to-end architecture. Experiments on a widely used music similarity measure dataset show that our method significantly outperforms three state-of-the-art music metric learning methods. Experiments also show that the learned features better preserve the partial orders of the relative similarity than handcrafted features.

关键词： Metric learning music similarity deep learning convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Where Does AlphaGo Go: From Church-Turing Thesis to AlphaGo Thesis and Beyond

引用

IEEE/CAA Journal of Automatica Sinica 2016年第2期3卷 113-120页

作者： Fei-Yue Wang Jun Jason Zhang Xinhu Zheng Xiao Wang Yong Yuan Xiaoxiao Dai Jie Zhang Liuqing Yang IEEE the State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences (SKL-MCCS CASIA) Research Center of Computational Experiments and Parallel Systems The National University of Defense Technology the Department of Electrical and Computer Engineering Ritchie School of Engineering and Computer Science University of Denver the Department of Computer Science and Engineering University of Minnesota the Qingdao Academy of Intelligent Industries (QAII) Qingdao Shandong China and SKL-MCCS CASIA the Department of Electrical and Computer Engineering Colorado State University

An investigation on the impact and significance of the AlphaGo vs. Lee Sedol Go match is conducted, and concludes with a conjecture of the AlphaGo Thesis and its extension in accordance with the Church-Turing Thesis in the history of computing. It is postulated that the architecture and method utilized by the AlphaGo program provide an engineering solution for tackling issues in complexity and intelligence. Specifically, the AlphaGo Thesis implies that any effective procedure for hard decision problems such as NP-hard can be implemented with AlphaGo-like approach. Deep rule-based networks are proposed in attempt to establish an understandable structure for deep neural networks in deep learning. The success of AlphaGo and corresponding thesis ensure the technical soundness of the parallel intelligence approach for intelligent control and management of complex systems and knowledge automation. © 2014 Chinese Association of Automation.

关键词： Religious buildings

来源：评论

学校读者我要写书评

暂无评论

Distributed computation of linear matrix equations: An optimization perspective

arXiv

引用

arXiv 2017年

作者： Zeng, Xianlin Liang, Shu Hong, Yiguang Chen, Jie Key Laboratory of Intelligent Control and Decision of Complex Systems School of Automation Beijing Institute of Technology Beijing100081 China Key Laboratory of Knowledge Automation for Industrial Processes of Ministry of Education School of Automation and Electrical Engineering University of Science and Technology Beijing Beijing100083 China Key Laboratory of Systems and Control Academy of Mathematics and Systems Science Chinese Academy of Sciences Beijing100190 China Ministry of Education Beijing100081 China

This paper investigates the distributed computation of the well-known linear matrix equation in the form of AXB = F, with the matrices A, B, X, and F of appropriate dimensions, over multiagent networks from an optimization perspective. In this paper, we consider the standard distributed matrix-information structures, where each agent of the considered multi-agent network has access to one of the sub-block matrices of A, B, and F. To be specific, we first propose different decomposition methods to reformulate the matrix equations in standard structures as distributed constrained optimization problems by introducing substitutional variables;we show that the solutions of the reformulated distributed optimization problems are equivalent to least squares solutions to original matrix equations;and we design distributed continuous-time algorithms for the constrained optimization problems, even by using augmented matrices and a derivative feedback technique. Moreover, we prove the exponential convergence of the algorithms to a least squares solution to the matrix equation for any initial condition. Copyright © 2017, The Authors. All rights reserved.

关键词： Continuous time systems

来源：评论

学校读者我要写书评

暂无评论

Motion trajectory design and tracking control for underactuated Furata pendulum system

Motion trajectory design and tracking control for underactua...

引用

IEEE International Conference on Automation Science and engineering (CASE)

作者： Ancai Zhang Jianlong Qiu Chaomin Luo Chengdong Yang Zhenxing Li School of Automation and Electrical Engineering Linyi University Linyi Shandong China Key Laboratory of Complex Systems and Intelligent Computing in Universities of Shandong (Linyi University) Linyi Shandong China Department of Electrical and Computer Engineering University of Detroit Mercy MI USA School of Information Science and Engineering Linyi University Linyi Shandong China

This paper discusses the motion trajectory design and tracking control problem for an underactuated mechanical system called Furuta pendulum. Firstly, the dynamic equations of a Furuta pendulum system are given. And the dynamic properties of this mechanical system are analyzed. Secondly, we construct a trajectory for the Furuta pendulum in its motion space based on the analysis properties. Afterwards, a tracking controller is designed to track the constructed motion trajectory. This guarantees the stabilization of the Furuta pendulum from an initial point to an objective point to be achieved. To demonstrate the validity of our proposed theoretical analysis results, a numerical example is presented finally.

关键词： Trajectory Tracking Mathematical model Mechanical systems Aerospace electronics Dynamics

来源：评论

学校读者我要写书评

暂无评论

A game-theoretic taxonomy and survey of defensive deception for cybersecurity and privacy

arXiv

引用

arXiv 2017年

作者： Pawlick, Jeffrey Colbert, Edward Zhu, Quanyan Department of Electrical and Computer Engineering New York University Tandon School of Engineering 5 MetroTech Center BrooklynNY United States Us Army Research Laboratory 2800 Powder Mill Road AdelphiMD United States Us Army Research Laboratory Virgina Tech Intelligent Systems Laboratory Hume Center for National Security and Technology 900 N. Glebe Road ArlingtonVA United States Department of Electrical and Computer Engineering New York University Tandon School of Engineering

Cyberattacks on both databases and critical infrastructure have threatened public and private sectors. Ubiquitous tracking and wearable computing have infringed upon privacy. Advocates and engineers have recently proposed using defensive deception as a means to leverage the information asymmetry typically enjoyed by attackers as a tool for defenders. The term deception, however, has been employed broadly and with a variety of meanings. In this paper, we survey 24 articles from 2008-2018 that use game theory to model defensive deception for cybersecurity and privacy. Then we propose a taxonomy that defines six types of deception: perturbation, moving target defense, obfuscation, mixing, honey-x, and attacker engagement. These types are delineated by their information structures, agents, actions, and duration: precisely concepts captured by game theory. Our aims are to rigorously define types of defensive deception, to capture a snapshot of the state of the literature, to provide a menu of models which can be used for applied research, and to identify promising areas for future work. Our taxonomy provides a systematic foundation for understanding different types of defensive deception commonly encountered in cybersecurity and privacy. Copyright © 2017, The Authors. All rights reserved.

关键词： Surveys

来源：评论

学校读者我要写书评

暂无评论

An information infrastructure framework for smart grids leveraging SDN and cloud

An information infrastructure framework for smart grids leve...

引用

Clemson University Power systems Conference, PSC 2016

作者： Narayanan, Rajesh Xu, Ke Wang, Kuang-Ching Kumar Venayagamoorthy, G. Dell Research Santa ClaraCA United States Real-Time Power and Intelligent Systems Laboratory Department of Electrical and Computer Engineering Clemson University SC United States

ISBN: (纸本)9781509006878

Smart grids are recognized as the next-generation power grid that uses digital information and communications technology to create an advanced, automated, and efficient energy network among a wealth of electronic appliances, meters, and energy producing and distributing devices. As more complex and distributed interactions among these different components are envisioned, an open, scalable, and manageable framework is needed to support the communication and computing needs. This paper proposes an innovative method to derive scalable information infrastructure for smart grids. The framework well aligns with the emerging micro-grid operational model of the smart grid. A prototype framework is being developed consisting of CloudLab [1], GENI [2] wired and wireless networks, and real-time power system platform at the RTPIS Lab [3]. © 2016 IEEE.

关键词： Smart power grids

来源：评论

学校读者我要写书评

暂无评论

State Estimation for BAM Neural Networks with Mixed Time Delays

State Estimation for BAM Neural Networks with Mixed Time Del...

引用

IEEE International Conference on Automation Science and engineering

作者： Guoquan Liu Chaomin Luo Jianlong Qiu Xianxi Luo Jiakai Ding Jiangxi Province Engineering University of Technology Nanchang China Department of Electrical and Computer Engineering University of Detroit Mercy Michigan USA School of Automation and Electrical Engineering Key Laboratory of Complex systems and Intelligent Computing in Universities of Shandong (Linyi University) Linyi Shandong Province China Jiangxi Province Engineering East China University of Technology Nanchang China School of mechanical and electronic engineering East China University of Technology Nanchang China

This paper is concerned with the state estimation problem of BAM neural networks with mixed time delays. By constructing a suitable Lyapunov-Krasovskii functional (LKF), a new criterion is obtained so that the BAM neural networks error system is asymptotically stable. A simulation example is given to demonstrate the effectiveness of the proposed method.

关键词： LKF concerned estimation

来源：评论

学校读者我要写书评

暂无评论

ANN-based modelling and prediction of daily global solar irradiation using commonly measured meteorological parameters

引用

IOP Conference Series: Earth and Environmental Science 2018年第1期161卷

作者： M Marzouq Z Bounoua A Mechaqrane H E Fadili Z Lakhliai K Zenkouar Laboratory of Computer Sciences and Interdisciplinary Physics National School of Applied Sciences USMBA Fez PO. Box 72 Fez Morocco Laboratory of Renewable Energies and Intelligent Systems Electrical Engineering department Faculty of Sciences and Technologies USMBA Fez PO. Box 2202 Fez Morocco Intelligent System and Application Laboratory Faculty of Sciences and Technologies USMBA Fez PO. Box 2202 Fez Morocco

The aim of this work is to develop an artificial neural network (ANN) based model for accurately predicting the daily global solar irradiation in the city of Fez. The potential of the developed model is verified and appraised through the local collected database for the period 2009-2015 from the radiometric station of the Faculty of Sciences and Technology of Fez. The obtained model is MLP with feed forward back-propagation algorithm containing three input parameters and a single hidden layer with nine neurons. Coefficient of determination R 2, the mean absolute percentage error MAPE and the relative root mean square error RRMSE are respectively equal to 97.16%, 21.77% and 18.79%.

关键词：

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：