检索结果-内蒙古大学图书馆

arXiv 2020年

作者： Huang, Zhiyong Sheng, Kekai Dong, Weiming Mei, Xing Ma, Chongyang Huang, Feiyue Zhou, Dengwen Xu, Changsheng School of Control and Computer Engineering North China Electric Power University Changping District Beijing China NLPR Institute of Automation Chinese Academy of Sciences and School of Artificial Intelligence University of Chinese Academy of Sciences Beijing China Youtu lab Tencent Shanghai China Bytedance Inc Beijing China Kuaishou Technology Beijing China

Semi-supervised domain adaptation (SSDA) methods have demonstrated great potential in large-scale image classification tasks when massive labeled data are available in the source domain but very few labeled samples are provided in the target domain. Existing solutions usually focus on feature alignment between the two domains while paying little attention to the discrimination capability of learned representations in the target domain. In this paper, we present a novel and effective method, namely Effective Label Propagation (ELP), to tackle this problem by using effective inter-domain and intra-domain semantic information propagation. For inter-domain propagation, we propose a new cycle discrepancy loss to encourage consistency of semantic information between the two domains. For intra-domain propagation, we propose an effective self-training strategy to mitigate the noises in pseudo-labeled target domain data and improve the feature discriminability in the target domain. As a general method, our ELP can be easily applied to various domain adaptation approaches and can facilitate their feature discrimination in the target domain. Experiments on Office-Home and DomainNet benchmarks show that ELP consistently improves the classification accuracy of mainstream SSDA methods by 2% ∼ 3%. Additionally, ELP also improves the performance of UDA methods as well (81.5% vs 86.1%), based on UDA experiments on the VisDA-2017 benchmark. Our source code and pre-trained models will be released soon. Copyright © 2020, The Authors. All rights reserved.

关键词： Information dissemination

来源：评论

学校读者我要写书评

暂无评论

Mobile Energy Transfer in Internet of Things

arXiv

引用

arXiv 2020年

作者： Zhang, Qingqing Wang, Gang Giannakis, Georgios B. Liu, Qingwen Chen, Jie College of Electronic and Information Engineering Tongji University Shanghai201800 China Department of Electrical and Computer Engineering University of Minnesota MinneapolisMN 55455 United States State Key Lab of Intelligent Control and Decision of Complex Systems School of Automation Beijing Institute of Technology Beijing100081 China Tongji University Shanghai200092 China

—Internet of things (IoT) is powering up smart cities by connecting all kinds of electronic devices. The power supply problem of IoT devices constitutes a major challenge in current IoT development, due to the poor battery endurance as well as the troublesome cable deployment. The wireless power transfer (WPT) technology has recently emerged as a promising solution. Yet, existing WPT advances cannot support free and mobile charging like Wi-Fi communications. To this end, the concept of mobile energy transfer (MET) is proposed, which relies critically on an resonant beam charging (RBC) technology. The adaptive (A) RBC technology builds on RBC, but aims at improving the charging efficiency by charging devices at device preferred current and voltage levels adaptively. A mobile ARBC scheme is developed relying on an adaptive source power control. Extensive numerical simulations using a 1,000mAh Li-ion battery show that the mobile ARBC outperforms simple charging schemes such as the constant power charging, the profile-adaptive charging, and the distance-adaptive charging in saving energy. Copyright © 2020, The Authors. All rights reserved.

关键词： Energy transfer

来源：评论

学校读者我要写书评

暂无评论

Distributed delay model of the McKeithan’s network

引用

IFAC-PapersOnLine 2019年第7期52卷 33-38页

作者： György Lipták Katalin M. Hangos Process Control Research Group Systems and Control Laboratory Computer and Automation Research Institute Hungarian Academy of Sciences P.O. Box 63 H-1518 Budapest Hungary Department of Electrical Engineering and Information Systems University of Pannonia Veszprém Hungary

In this paper CRNs containing linear reaction chains with multiple joint complexes were considered in order to obtain an equivalent reduced order delayed CRN model with distributed time delays. For this purpose, our earlier method (Lipták and Hangos (2018)) for decomposing the chains of linear reactions with multiple joint complexes was used together with the "linear chain trick". An analytical expression for the kernel function of the distributed delay was also derived from the reaction rate coefficients of the linear reaction chains. Our approach was demonstrated using the example of the well known McKeithan’s network model of kinetic proofreading.

关键词： Process control Delay Chemical Reaction Networks

来源：评论

学校读者我要写书评

暂无评论

A Primal-Dual SGD Algorithm for Distributed Nonconvex Optimization

arXiv

引用

arXiv 2020年

作者： Yi, Xinlei Zhang, Shengjun Yang, Tao Chai, Tianyou Johansson, Karl H. The Division of Decision and Control Systems School of Electrical Engineering and Computer Science KTH Royal Institute of Technology Stockholm100 44 Sweden The Department of Electrical Engineering University of North Texas DentonTX76203 United States The State Key Laboratory of Synthetical Automation for Process Industries Northeastern University Shenyang110819 China

The distributed nonconvex optimization problem of minimizing a global cost function formed by a sum of n local cost functions by using local information exchange is considered. This problem is an important component of many machine learning techniques with data parallelism, such as deep learning and federated learning. We propose a distributed primal–dual stochastic gradient descent (SGD) algorithm, suitable for arbitrarily connected communication networks and any smooth (possibly nonconvex) cost functions. We show that the proposed algorithm achieves the linear speedup convergence rate O(1/√nT) for general nonconvex cost functions and the linear speedup convergence rate O(1/(nT)) when the global cost function satisfies the Polyak–Lojasiewicz (P–L) condition, where T is the total number of iterations. We also show that the output of the proposed algorithm with constant parameters linearly converges to a neighborhood of a global optimum. We demonstrate through numerical experiments the efficiency of our algorithm in comparison with the baseline centralized SGD and recently proposed distributed SGD algorithms. Copyright © 2020, The Authors. All rights reserved.

关键词： Cost functions

来源：评论

学校读者我要写书评

暂无评论

Anchor-based spatio-temporal attention 3D convolutional networks for dynamic 3D point cloud sequences

arXiv

引用

arXiv 2020年

作者： Wang, Guangming Chen, Muyao Liu, Hanwen Yang, Yehui Liu, Zhe Wang, Hesheng The Department of Automation Institute of Medical Robotics Key Laboratory of System Control and Information Processing Ministry of Education Key Laboratory of Marine Intelligent Equipment System of Ministry of Education Shanghai Jiao Tong University Shanghai200240 China Beijing Advanced Innovation Center for Intelligent Robots and Systems Beijing Institute of Technology China The Department of Computer Science and Engineering Shanghai Jiao Tong University Shanghai200240 China The Department of Computer Science and Technology University of Cambridge

With the rapid development of measurwement technology, LiDAR and depth cameras are widely used in the perception of the 3D environment. Recent learning based methods for robot perception most focus on the image or video, but deep learning methods for dynamic 3D point cloud sequences are underexplored. Therefore, developing efficient and accurate perception method compatible with these advanced instruments is pivotal to autonomous driving and service robots. An Anchor-based Spatio-Temporal Attention 3D Convolution operation (ASTA3DConv) is proposed in this paper to process dynamic 3D point cloud sequences. The proposed convolution operation builds a regular receptive field around each point by setting several virtual anchors around each point. The features of neighborhood points are firstly aggregated to each anchor based on the spatio-temporal attention mechanism. Then, anchor-based 3D convolution is adopted to aggregate these anchors' features to the core points. The proposed method makes better use of the structured information within the local region and learns spatio-temporal embedding features from dynamic 3D point cloud sequences. Anchor-based Spatio-Temporal Attention 3D Convolutional Neural Networks (ASTA3DCNNs) are built for classification and segmentation tasks based on the proposed ASTA3DConv and evaluated on action recognition and semantic segmentation tasks. The experiments and ablation studies on MSRAction3D and Synthia datasets demonstrate the superior performance and effectiveness of our method for dynamic 3D point cloud sequences. Our method achieves the state-of-the-art performance among the methods with dynamic 3D point cloud sequences as input on MSRAction3D and Synthia datasets. Copyright © 2020, The Authors. All rights reserved.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

Corrigendum to “Realistic acceleration of neural networks with fine-grained tensor decomposition” [Neurocomputing 512 (2022) 52–68]

引用

Neurocomputing 2023年 527卷 47-47页

作者： Rui Lv Dingheng Wang Jiangbin Zheng Yefan Xie Zhao-Xu Yang School of Computer Science Northwestern Polytechnical University Xi’an Shaanxi China Northwest Institute of Mechanical & Electrical Engineering Xianyang Shaanxi China School of Automation Science and Engineering Faculty of Electronic and Information Engineering Xi’an Jiaotong University Xi’an Shaanxi China State Key Laboratory for Strength and Vibration of Mechanical Structures Shaanxi Key Laboratory of Environment and Control for Flight Vehicle and School of Aerospace Engineering Xi’an Jiaotong University Xi’an Shaanxi China

来源：评论

学校读者我要写书评

暂无评论

Affinely Parametrized State-space Models: Ways to Maximize the Likelihood Function

引用

IFAC-PapersOnLine 2018年第15期51卷 718-723页

作者： Wills, Adrian Yu, Chengpu Ljung, Lennart Verhaegen, Michel School of Electrical Engineering and Computer Science University of Newcastle Australia School iof Automation Beijing Institute of Technology China Division of Automatic Control Department of Electrical Engineering Linkoping University Sweden Delft Center for Systems and Control Delft University Delft2628CD Netherlands

Using Maximum Likelihood (or Prediction Error) methods to identify linear state space model is a prime technique. The likelihood function is a nonconvex function and care must be exercised in the numerical maximization. Here the focus will be on affine parameterizations which allow some special techniques and algorithms. Three approaches to formulate and perform the maximization are described in this contribution: (1) The standard and well known Gauss-Newton iterative search, (2) a scheme based on the EM (expectation-maximization) technique, which becomes especially simple in the affine parameterization case, and (3) a new approach based on lifting the problem to a higher dimension in the parameter space and introducing rank constraints. © 2018

关键词： Maximum likelihood estimation

来源：评论

学校读者我要写书评

暂无评论

Towards better surgical instrument segmentation in endoscopic vision: multi-angle feature aggregation and contour supervision

arXiv

引用

arXiv 2020年

作者： Qin, Fangbo Lin, Shan Li, Yangming Bly, Randall A. Moe, Kris S. Hannaford, Blake Research Center of Precision Sensing and Control Institute of Automation Chinese Academy of Sciences Beijing100190 China School of Artificial Intelligence University of Chinese Academy of Sciences Beijing101408 China SeattleWA98195-2500 United States Department of Otolaryngology-Head & Neck Surgery UW Seattle United States Department of Electrical Computer and Telecommunications Engineering Technology Rochester Institute of Technology United States

—Accurate and real-time surgical instrument segmentation is important in the endoscopic vision of robot-assisted surgery, and significant challenges are posed by frequent instrument-tissue contacts and continuous change of observation perspective. For these challenging tasks more and more deep neural networks (DNN) models are designed in recent years. We are motivated to propose a general embeddable approach to improve these current DNN segmentation models without increasing the model parameter number. Firstly, observing the limited rotation-invariance performance of DNN, we proposed the Multi-Angle Feature Aggregation (MAFA) method, leveraging active image rotation to gain richer visual cues and make the prediction more robust to instrument orientation changes. Secondly, in the end-to-end training stage, the auxiliary contour supervision is utilized to guide the model to learn the boundary awareness, so that the contour shape of segmentation mask is more precise. The effectiveness of the proposed methods is validated with ablation experiments conducted on novel Sinus-Surgery datasets. Copyright © 2020, 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

Silicone Oil Damping for Quasi-static Micro Scanners with Electrostatic Staggered Vertical Comb Drives

引用

IFAC-PapersOnLine 2019年第15期52卷 37-42页

作者： Richard Schroedter Jan Grahmann Klaus Janschek Fraunhofer Institute for Photonic Microsystems Active Microscanner Systems Maria-Reiche-Str.2 01109 Dresden Germany Automation and Control Institute (ACIN) Faculty of Electrical Engineering and Information Technology TU Wien Gußhausstraße 27-29 1040 Wien Austria Institute of Automation Faculty of Electrical and Computer Engineering Technische Universität Dresden 01062 Dresden Germany

Many applications like image projection, distance sensors or spectroscopy require high speed quasi-static operating scanners with the size of several millimeters for the laser beam guidance. Quasi-static micro scanners with electrostatic staggered vertical comb drives of sizes up to 5 mm achieve remarkable mechanical deflections of ±8 degree and eigenfrequencies of several hundred Hertz. Closed-loop control of the scanner position highly reduces parasitic eigenfrequency oscillation when driving an arbitrary trajectory like triangle or saw tooth, but requires position feedback and high performant drive electronics for real-time control. In this contribution we investigate silicone oil to attenuate undesired oscillations by passive mechanic damping. We present experimental results with different viscosity and determine the resulting system parameters such as damping coefficient, eigenfrequency and permittivity, supported by transient simulations. While the permittivity, refractive index and damping increase significantly, the deceasing eigenfrequency results in slower admissible trajectories. The overall performance is assessed and compared to the active damping approach using closed-loop control of the micro scanner operating in air. Finally, a potential packaging technology is presented.

关键词： laser beam guidance quasi-static micro scanner electrostatic staggered vertical comb drive silicone oil viscous passive damping permittivity close-loop trajectory control

来源：评论

学校读者我要写书评

暂无评论

Synaptic learning with augmented spikes

arXiv

引用

arXiv 2020年

作者： Yu, Qiang Song, Shiming Ma, Chenxiang Pan, Linqiang Tan, Kay Chen Tianjin Key Laboratory of Cognitive Computing and Application College of Intelligence and Computing Tianjin University Tianjin China Key Laboratory of Image Information Processing and Intelligent Control Institute of Artificial Intelligence School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan China The Department of Computer Science City University of Hong Kong Hong Kong

Traditional neuron models use analog values for information representation and computation, while all-or-nothing spikes are employed in the spiking ones. With a more brain-like processing paradigm, spiking neurons are more promising for improvements on efficiency and computational capability. They extend the computation of traditional neurons with an additional dimension of time carried by all-or-nothing spikes. Could one benefit from both the accuracy of analog values and the time-processing capability of spikes? In this paper, we introduce a concept of augmented spikes to carry complementary information with spike coefficients in addition to spike latencies. New augmented spiking neuron model and synaptic learning rules are proposed to process and learn patterns of augmented spikes. We provide systematic insight into the properties and characteristics of our methods, including classification of augmented spike patterns, learning capacity, construction of causality, feature detection, robustness and applicability to practical tasks such as acoustic and visual pattern recognition. The remarkable results highlight the effectiveness and potential merits of our methods. Importantly, our augmented approaches are versatile and can be easily generalized to other spike-based systems, contributing to a potential development for them including neuromorphic computing. Copyright © 2020, The Authors. All rights reserved.

关键词： Neurons

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：