检索结果-内蒙古大学图书馆

arXiv 2019年

作者： Ma, Lizheng Cui, Jiaxu Yang, Bo College of Computer Science and Technology Jilin University Changchun China Key Laboratory of Symbolic Computation Knowledge Engineering of Ministry of Education

Bayesian optimization (BO) is an effective method of finding the global optima of black-box functions. Recently BO has been applied to neural architecture search and shows better performance than pure evolutionary strategies. All these methods adopt Gaussian processes (GPs) as surrogate function, with the handcraft similarity metrics as input. In this work, we propose a Bayesian graph neural network as a new surrogate, which can automatically extract features from deep neural architectures, and use such learned features to fit and characterize black-box objectives and their uncertainty. Based on the new surrogate, we then develop a graph Bayesian optimization framework to address the challenging task of deep neural architecture search. Experiment results show our method significantly outperforms the comparative methods on benchmark tasks. Copyright © 2019, The Authors. All rights reserved.

关键词： Evolutionary algorithms

来源：评论

学校读者我要写书评

暂无评论

Optimal control approach to stability criteria on Hill's equations

引用

Applied Mathematics(A Journal of Chinese Universities) 2018年第3期33卷 253-273页

作者： ZU Jian LI Yong School of Mathematics and Statistics & Center for Mathematics and Interdisciplinary Sciences North-east Normal University Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Jilin University College of Mathematics Jilin University

This paper gives a tutorial on how to prove Lyapunov type criteria by optimal control methods. Firstly, we consider stability criteria on Hill’s equations with nonnegative potential. By optimal control methods developed in 1990s, we obtain several stability criteria including Lyapunov’s criterion, Neǐgauz and Lidskiǐ’s criterion. Secondly, we present stability criteria on Hill’s equations with sign-changing potential in which Brog’s criterion and Krein’s criterion are included.

关键词： stability criteria optimal control method Hill's equation Lyapunov inequality

来源：评论

学校读者我要写书评

暂无评论

Curvature regularization to prevent distortion in graph embedding 20

Curvature regularization to prevent distortion in graph embe...

引用

Proceedings of the 34th International Conference on Neural Information Processing Systems

作者： Hongbin Pei Bingzhe Wei Kevin Chen-Chuan Chang Chunxu Zhang Bo Yang College of Computer Science and Technology Jilin University China and Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education China Department of Electrical and Computer Engineering University of Illinois at Urbana-Champaign Department of Electrical and Computer Engineering University of Illinois at Urbana-Champaign and Department of Computer Science University of Illinois at Urbana-Champaign

ISBN: (纸本)9781713829546

Recent research on graph embedding has achieved success in various applications. Most graph embedding methods preserve the proximity in a graph into a manifold in an embedding space. We argue an important but neglected problem about this proximity-preserving strategy: Graph topology patterns, while preserved well into an embedding manifold by preserving proximity, may distort in the ambient embedding Euclidean space, and hence to detect them becomes difficult for machine learning models. To address the problem, we propose curvature regularization, to enforce flatness for embedding manifolds, thereby preventing the distortion. We present a novel angle-based sectional curvature, termed ABS curvature, and accordingly three kinds of curvature regularization to induce flat embedding manifolds during graph embedding. We integrate curvature regularization into five popular proximity-preserving embedding methods, and empirical results in two applications show significant improvements on a wide range of open graph datasets.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Application of Monocular Direct Vision Odometry in Augmented Reality

引用

Journal of Physics: Conference Series 2021年第4期1748卷

作者： Zuoming Zhang Zixuan Wang Hanwen Wang Xin Wang College of Software Engineering Jilin University Changchun Jilin 130000 China Key Laboratory of Symbolic Computation and Knowledge Engineer of Ministry of Education Jilin University Changchun Jilin 130000 China

In recent years, the unlabeled augmented reality system has been gradually applied to various mobile devices, among which stable, accurate, and fast registration is the key to realizing this function. For this technique, this paper introduces camera exposure parameters and puts the data association and pose estimation into a unified nonlinear optimization problem. Moreover, the direct monocular vision odometer is transplanted into the augmented reality system through the position adjustment module. We compare it with the traditional visual odometry method that matches the feature points. The results show that this improved method can be used to track more quickly and build a more visual semi-dense point cloud map, which can be used to support the registration and tracking of virtual objects in augmented reality.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Stochastic Variational Inference-Based Parallel and Online Supervised Topic Model for Large-Scale Text Processing

引用

Journal of Computer Science & Technology 2018年第5期33卷 1007-1022页

作者： Yang Li Wen-Zhuo Song Bo Yang College of Computer Science and Technology Jilin University Changchun 130012 China Key Laboratory of Symbolic Computation and Knowledge Engineering Ministry of Education Jilin University Changchun 130012 China Aviation University of Air Force Changchun 130062 China

Topic modeling is a mainstream and effective technology to deal with text data, with wide applications in text analysis, natural language, personalized recommendation, computer vision, etc. Among all the known topic models, supervised Latent Dirichlet Allocation （sLDA） is acknowledged as a popular and competitive supervised topic model. How- ever, the gradual increase of the scale of datasets makes sLDA more and more inefficient and time-consuming, and limits its applications in a very narrow range. To solve it, a parallel online sLDA, named PO-sLDA （Parallel and Online sLDA）, is proposed in this study. It uses the stochastic variational inference as the learning method to make the training procedure more rapid and efficient, and a parallel computing mechanism implemented via the MapReduce framework is proposed to promote the capacity of cloud computing and big data processing. The online training capacity supported by PO-sLDA expands the application scope of this approach, making it instrumental for real-life applications with high real-time demand. The validation using two datasets with different sizes shows that the proposed approach has the comparative accuracy as the sLDA and can efficiently accelerate the training procedure. Moreover, its good convergence and online training capacity make it lucrative for the large-scale text data analyzing and processing.

关键词： topic modeling, large-scale text classification, stochastic variational inference, cloud computing online learning

来源：评论

学校读者我要写书评

暂无评论

Application of Hybrid Monocular SLAM Method in Augmented Reality

引用

Journal of Physics: Conference Series 2021年第4期1748卷

作者： Zuoming Zhang Hanwen Wang Man Shu Xin Wang College of Software Engineering Jilin University Changchun Jilin 130000 China Key Laboratory of Symbolic Computation and Knowledge Engineer of Ministry of Education Jilin University Changchun Jilin 130000 China

In this paper, we design a hybrid (semi-direct) approach to simultaneous localization and mapping (SLAM) for monocular cameras and apply it to augmented reality (AR) for monocular cameras. We combine the advantagesof the direct method and the feature point method. We use both photometric bundle adjustment which is robust to camera exposure time and motion bundle adjustment which is geometrically robust based on feature points to do tracking process. This approach can maintain an intuitive direct local map as well as a reusable global sparse feature point map. Through the processing of point clouds, such as PCA plane detection and grid reconstruction, we greatly improve the effect of the augmented reality system.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Pyramid Pooling Dense Convolutional Neural Network for Multi-focus Image Fusion

Pyramid Pooling Dense Convolutional Neural Network for Multi...

引用

IEEE International Conference on Cloud Computing and Intelligence Systems (CCIS)

作者： Yi Li Xuanjing Shen Haipeng Chen College of Software Jilin University Changchun China Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Jilin University Changchun China

ISBN: (数字)9781728138633

ISBN: (纸本)9781728138640

In recent years, image fusion becomes one of the important technique in information fusion fields. In this paper, we proposed a Deep Learning-based pyramid pooling dense convolutional neural network for multi-focus image fusion problem. The PDenseCNN we proposed can accurately detect the clear regions and generate a fused decision feature map, afterward, morphological operation and guided filter are used to optimize the initial map. Finally, it can obtain a clear fusion image based on weighted-sum strategy. The experimental results proved that the proposed method can obtain accurate decision maps and state-of-art fusion results on both visual effect and objective evaluation assessment.

关键词： Economic indicators

来源：评论

学校读者我要写书评

暂无评论

An Unmanned Aerial Vehicle Pose Estimation System Guided by Desired Shot

An Unmanned Aerial Vehicle Pose Estimation System Guided by ...

引用

IEEE International Conference on Automation, Electronics and Electrical engineering (AUTEEE)

作者： Xinglei Dou Qijian Ding Qiao Du Min Yang Yuzhou Huo Xin Wang College of Software Engineering Jilin University Changchun China Key Laboratory of Symbolic Computation and Knowledge Engineer of Ministry of Education Jilin University Changchun China

ISBN: (数字)9781728150307

ISBN: (纸本)9781728150314

Unmanned aerial vehicles (UAVs) are widely used in aerial photography nowadays for their strong maneuverability, good image quality and high cost performance, while they have limited battery capacity and difficulty in operation. It is difficult to reach the ideal pose and get the desired shot by manual manipulation in a short time. To solve these problems, an UAV pose estimation system guided by desired shot is constructed. Either a sequence of images or a video is taken as input. The user interacts with the system to express the desired shot. The 3D-reconstruction is done by Structure from Motion (SfM). Then the Perspective-n-Point (PnP) problem is solved to estimate the ideal pose of the UAV. The experimental results proves that the system is effective and valid.

关键词： Three-dimensional displays Feature extraction Unmanned aerial vehicles Cameras Pose estimation Software engineering Data mining

来源：评论

学校读者我要写书评

暂无评论

A pseudo label based dataless naive bayes algorithm for text classification with seed words 27

A pseudo label based dataless naive bayes algorithm for text...

引用

27th International Conference on computational Linguistics, COLING 2018

作者： Li, Ximing Yang, Bo College of Computer Science and Technology Jilin University China Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education China

ISBN: (纸本)9781948087506

Traditional supervised text classifiers require a large number of manually labeled documents, which are often expensive to obtain. Recently, dataless text classification has attracted more attention, since it only requires very few seed words of categories that are much cheaper. In this paper, we develop a pseudo-label based dataless Naive Bayes (PL-DNB) classifier with seed words. We initialize pseudo-labels for each document using seed word occurrences, and employ the expectation maximization algorithm to train PL-DNB in a semi-supervised manner. The pseudo-labels are iteratively updated using a mixture of seed word occurrences and estimations of label posteriors. To avoid noisy pseudo-labels, we also consider the information of nearest neighboring documents in the pseudo-label update step, i.e., preserving local neighborhood structure of documents. We empirically show that PL-DNB outperforms traditional dataless text classification algorithms with seed words. Especially, PL-DNB performs well on the imbalanced dataset. © 2018 COLING 2018 - 27th International Conference on computational Linguistics, Proceedings. 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

Applications of Game Theory in Vehicular Networks: A Survey

arXiv

引用

arXiv 2021年

作者： Sun, Zemin Liu, Yanheng Wang, Jian Li, Guofa Anil, Carie Li, Keqiang Guo, Xinyu Sun, Geng Tian, Daxin Cao, Dongpu College of Computer Science and Technology Jilin University Changchun130012 China Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Jilin University Changchun130012 China Institute of Human Factors and Ergonomics College of Mechatronics and Control Engineering Shenzhen University Guangdong Shenzhen518060 China School of Computer Science and Engineering VIT-AP Andhra Pradesh Amaravati522237 India College of Engineering Nanjing Agricultural University Nanjing210031 China State Key Laboratory of Automotive Safety and Energy Department of Automotive Engineering Tsinghua University Beijing100084 China Beijing Advanced Innovation Center for Big Data and Brain Computing Beijing Key Laboratory for Cooperative Vehicle Infrastructure Systems and Safety Control School of Transportation Science and Engineering Beihang University Beijing100191 China Waterloo Cognitive Autonomous Driving Lab University of Waterloo N2L 3G1 Canada

In the Internet of things (IoT) era, vehicles and other intelligent components in an intelligent transportation system (ITS) are connected, forming vehicular networks (VNs) that provide efficient and safe traffic and ubiquitous access to various applications. However, as the number of nodes in an ITS increases, it is challenging to satisfy a varied and large number of service requests with different quality of service (QoS) and security requirements in highly dynamic VNs. Intelligent nodes in VNs can compete or cooperate for limited network resources to achieve the objective for either an individual or a group. Game theory (GT), a theoretical framework designed for strategic interactions among rational decision makers sharing scarce resources, can be used to model and analyze individual or group behaviors of communicating entities in VNs. This paper primarily surveys the recent developments of GT in solving various challenges of VNs. This survey starts with an introduction to the background of VNs. A review of GT models studied in the VNs is then introduced, including the basic concepts, classifications, and applicable vehicular issues. After discussing the requirements of VNs and the motivation of using GT, a comprehensive literature review on GT applications in dealing with the challenges of current VNs is provided. Furthermore, recent contributions of GT to VNs that are integrated with diverse emerging 5G technologies are surveyed. Finally, the lessons learned are given, and several key research challenges and possible solutions of applying GT in VNs are outlined. Copyright © 2021, The Authors. All rights reserved.

关键词： Quality of service

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：