检索结果-内蒙古大学图书馆

33rd Conference on Neural Information Processing Systems (NeurIPS)

作者： Yang, Zhiyong Xu, Qianqian Jiang, Yangbangyan Cao, Xiaochun Huang, Qingming Chinese Acad Sci Inst Informat Engn State Key Lab Informat Secur Beijing Peoples R China Univ Chinese Acad Sci Sch Cyber Secur Beijing Peoples R China Chinese Acad Sci Inst Comp Technol Key Lab Intelligent Informat Proc Beijing Peoples R China Univ Chinese Acad Sci Sch Comp Sci & Tech Beijing Peoples R China Chinese Acad Sci Key Lab Big Data Min & Knowledge Management Beijing Peoples R China Peng Cheng Lab Shenzhen Peoples R China

In multi-task learning, a major challenge springs from a notorious issue known as negative transfer, which refers to the phenomenon that sharing the knowledge with dissimilar and hard tasks often results in a worsened performance. To circumvent this issue, we propose a novel multi-task learning method, which simultaneously learns latent task representations and a block-diagonal Latent Task Assignment Matrix (LTAM). Different from most of the previous work, pursuing the Block-Diagonal structure of LTAM (assigning latent tasks to output tasks) alleviates negative transfer via punishing inter-group knowledge transfer and sharing. This goal is challenging since our notion of Block-Diagonal Property extends the traditional notion for homogeneous and square matrices. In this paper, we propose a spectral regularizer which is proven to leverage the expected structure. Practically, we provide a relaxation scheme which improves the flexibility of the model. With the objective function given, we then propose an alternating optimization method, which reveals an interesting connection between our method and the optimal transport problem. Finally, the method is demonstrated on a simulation dataset, three real-world benchmark datasets and further applied to two personalized attribute learning datasets.

关键词： Learning systems

来源：评论

学校读者我要写书评

暂无评论

Improved least squares support vector machine based on metric learning

引用

NEURAL COMPUTING & APPLICATIONS 2018年第7期30卷 2205-2215页

作者： Li, Dewei Tian, Yingjie Univ Chinese Acad Sci Sch Math Sci Beijing 100049 Peoples R China Chinese Acad Sci Res Ctr Fictitious Econ & Data Sci Beijing 100190 Peoples R China Chinese Acad Sci Key Lab Big Data Min & Knowledge Management Beijing 100190 Peoples R China

As two kinds of popular data mining methods, metric learning and SVM have a interesting and valuable internal relationship. The basic idea of metric learning is to learn a data-dependent metric, instead of Euclidean metric, to shrink the distances between similar points and extend the distances between dissimilar points. From a different view, LSSVM can reach a similar goal as metric learning. It finds two parallel hyperplanes to make the distances between points and corresponding hyperplane as small as possible and the distance between two hyperplanes as large as possible. LSSVM can be looked as a slack version of metric learning. Then, it can be improved by modifying the way in measuring between-class distance, lead to the raise of our novel approach ML-LSSVM, which adds constraints of inter-class distance into LSSVM. Alternating direction method of multipliers algorithm was implemented to solve ML-LSSVM effectively, much faster than handling the original quadratic convex programming problem. Experiments were made to validate the efficacy of ML-LSSVM and prove that different measurements of intra-class distance and inter-class distance have significant impact on classification. At last, the relation between LMNN and ML-LSSVM was discussed to illustrate that the local formulation of LMNN is equivalent to ML-LSSVM.

关键词： Metric learning Least square-SVM LMNN Classification Distance

来源：评论

学校读者我要写书评

暂无评论

CA-RPT: Context-Aware Road Passage Time Estimation for Urban Traffic 19th

CA-RPT: Context-Aware Road Passage Time Estimation for Urban...

引用

19th Annual International Conference on Computational Science (ICCS)

作者： Liu, Ying Cui, Zhenyu Zhang, Tianlin Leng, Jiaxu Xie, Weihong Zhang, Liang Univ Chinese Acad Sci Sch Comp Sci & Technol Beijing 100190 Peoples R China Chinese Acad Sci Key Lab Big Data Min & Knowledge Management Beijing 100190 Peoples R China Guangdong Univ Technol Sch Econ & Commerce Guangzhou 510006 Peoples R China Guangdong Univ Technol Sch Appl Math Guangzhou 510006 Peoples R China

ISBN: (纸本)9783030227500;9783030227494

Road passage time is an important measure of urban traffic. Accurate estimation of road passage time contributes to the route programming and the urban traffic planning. Currently, the estimation of road passage time for a particular road is usually based on its historical data which is simple to express the general law of road traffic. However, with the increase of the number of roads in the urban area, the connection between roads becomes more complex. The existing methods fail to make use of the connection between different roads and the road passage time, merely based on its own historical data. In this paper, we propose a road passage time estimating model, called "CA-RPT", which utilizes the contextual information between road connections as well as the date and time period. We evaluate our method based on a real geolocation information data set collected by mobile APP anonymously. The results demonstrate that our method is more accurate than the state-of-the-art methods.

关键词： Road passage time Contextual information Road connection

来源：评论

学校读者我要写书评

暂无评论

Short-Term Traffic Congestion Forecasting Using Attention-Based Long Short-Term Memory Recurrent Neural Network 19th

Short-Term Traffic Congestion Forecasting Using Attention-Ba...

引用

19th Annual International Conference on Computational Science (ICCS)

作者： Zhang, Tianlin Liu, Ying Cui, Zhenyu Leng, Jiaxu Xie, Weihong Zhang, Liang Univ Chinese Acad Sci Sch Comp Sci & Technol Beijing 100190 Peoples R China Chinese Acad Sci Key Lab Big Data Min & Knowledge Management Beijing 100190 Peoples R China Guangdong Univ Technol Sch Econ & Commerce Guangzhou 510006 Peoples R China Guangdong Univ Technol Sch Appl Math Guangzhou 510006 Peoples R China

ISBN: (纸本)9783030227449;9783030227432

Traffic congestion seriously affect citizens' life quality. Many researchers have paid much attention to the task of short-term traffic congestion forecasting. However, the performance of the traditional traffic congestion forecasting approaches is not satisfactory. Moreover, most neural network models cannot capture the features at different moments effectively. In this paper, we propose an Attention-based long short-term memory (LSTM) recurrent neural network. We evaluate the prediction architecture on a real-time traffic data from Gray-Chicago-Milwaukee (GCM) Transportation Corridor in Chicagoland. The experimental results demonstrate that our method outperforms the baselines for the task of congestion prediction.

关键词： Traffic congestion prediction LSTM Attention mechanism

来源：评论

学校读者我要写书评

暂无评论

Deep Convolutional Neural Network Based Object Detector for X-Ray Baggage Security Imagery

Deep Convolutional Neural Network Based Object Detector for ...

引用

International Conference on Tools for Artificial Intelligence (ICTAI)

作者： Jinyi Liu Xiaxu Leng Ying Liu School of Computer Science and Technology University of Chinese Academy of Sciences Beijing China University of Chinese Academy of Sciences China School of Computer Science and Technology University of Chinese Academy of Sciences Key Lab of Big Data Mining and Knowledge Management Beijing China

Detection and classification of X-ray baggage security imagery are of great significance not only in daily life. However, up to now, it is still difficult for the traditional image processing methods to detect and distinguish objects which we want to detect in X-Ray baggage security imagery. Moreover, it is even more challenging to classify different types of objects. Although the current state-of-the-art detectors have achieved impressive performance on various public datasets with visible images, these detectors fail to deal with objects in X-ray images. This paper proposes an object detection algorithm for X-Ray baggage security screening images. Firstly, to outline the detected object from X-Ray baggage security imagery, we propose a fore-ground-background segmentation method which based on color information. Then, to classify and outline different type of object in X-Ray im-age, a deep convolutional neural networks (DCNNs) based object detection framework Faster R-CNN are proposed. In this stage we also use transfer learning method to speed up Faster R-CNN. The proposed method is proved to achieve 77% mAP by in a real-word dataset which contains 32,253 sub-way X-Ray baggage security screening images.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Survey and experimental study on metric learning methods

引用

NEURAL NETWORKS 2018年 105卷 447-462页

作者： Li, Dewei Tian, Yingjie Univ Chinese Acad Sci Sch Math Sci Beijing 100049 Peoples R China Chinese Acad Sci Res Ctr Fictitious Econ & Data Sci Beijing Peoples R China Chinese Acad Sci Key Lab Big Data Min & Knowledge Management Beijing 100190 Peoples R China

Distance metric learning has been a hot research spot recently due to its high effectiveness and efficiency in improving the performance of distance related methods, such as k nearest neighbors (kNN). Metric learning aims to learn a data-dependent metric to make intra-class distance smaller and inter-class larger. A large number of methods have been proposed for various applications and a survey to evaluate and compare these methods is imperative. The existing surveys just analyze the algorithms theoretically or compare them experimentally with a narrow time scope. Therefore, the paper reviews classical and influential methods that were proposed between 2003 and 2017 and presents a taxonomy based on the most distinct character of each method. All the methods are categorized into five classes, including pairwise cost, probabilistic framework, boost-like approaches, advantageous variants and specific applications. A comprehensive experimental study is made to compare all the selected methods, exploring the ability in improving accuracy, the relation between distance change and accuracy, the relation between accuracy and kNN neighbor size. (c) 2018 Elsevier Ltd. All rights reserved.

关键词： Metric learning Distance Classification Similarity Nearest neighbor

来源：评论

学校读者我要写书评

暂无评论

China’s NTB Market: A Liquidity Dilemma

引用

Journal of Systems Science & Complexity 2018年第2期31卷 493-507页

作者： LI Yumeng MENG Xiangying ZHANG Yueyan WEI Xianhua School of Economics and Management University of Chinese Academy of Sciences Beijing 100190 China Key Laborutory of Big Data Mining and Knowledge Management Chinese Academy of Sciences Beijing 100190 China Sino-Danish Center for Education and Research University of Chinese Academy of Sciences Beijing 100190 China The State Key Laboratory of Automotive Safety and Energy Tsinghua University Beijing 100084 China Department of Automotive Engineering Tsinghua University Beijing 100084 China

This paper introduces China＇s New Third Board Market（the NTB market） and tests the market-making system in the role of improving market liquidity. The NTB Market is the main part of China＇s OTC market, established in 2006. In comparing with China＇s Main Board Market and the Second Board Market, it attracts a lot of start-up companies that need financing with less strict listing requirements. Meanwhile, it is full of opportunities and challenges that appeal to numerous securities traders and investors with the rapid development momentum. Since its establishment, the NTB Market has been stuck in the lack of liquidity. The authority of the NTB Market introduced market maker system, so as to solve the problem of liquidity. Using the difference-in-difference method（DID method）, the market maker system has been proved to make little contribution to improving the stock liquidity. Although the problem of liquidity is difficult to solve in short term, the NTB Market is full of opportunities for all kinds of participants definitely.

关键词： China＇s stock market DID method liquidity market makers.

来源：评论

学校读者我要写书评

暂无评论

SkeletonNet: A Hybrid Network With a Skeleton-Embedding Process for Multi-View Image Representation Learning

引用

IEEE TRANSACTIONS ON MULTIMEDIA 2019年第11期21卷 2916-2929页

作者： Yang, Shijie Li, Liang Wang, Shuhui Zhang, Weigang Huang, Qingming Tian, Qi Univ Chinese Acad Sci Sch Comp Sci & Technol Beijing 101408 Peoples R China Univ Chinese Acad Sci Key Lab Big Data Min & Knowledge Management Beijing 101408 Peoples R China Chinese Acad Sci Inst Comp Technol Key Lab Intelligent Informat Proc Beijing 100190 Peoples R China Harbin Inst Technol Sch Comp Sci & Technol Weihai 264209 Peoples R China Chinese Acad Sci Univ Chinese Acad Sci Beijing 100049 Peoples R China Univ Texas San Antonio Dept Comp Sci San Antonio TX 78249 USA Huawei Noahs Ark Lab Comp Vis Shenzhen 518129 Peoples R China

Multi-view representation learning plays a fundamental role in multimedia data analysis. Some specific inter-view alignment principles are adopted in conventional models, where there is an assumption that different views share a common latent subspace. However, when dealing views on diverse semantic levels, the view-specific characteristics are neglected, and the divergent inconsistency of similarity measurements hinders sufficient information sharing. This paper proposes a hybrid deep network by introducing tensor factorization into the multi-view deep auto-encoder. The network adopts skeleton-embedding process for unsupervised multi-view subspace learning. It takes full consideration of view-specific characteristics, and leverages the strength of both shallow and deep architectures for modeling low- and high-level views, respectively. We first formulate the high-level-view semantic distribution as the underlying skeleton structure of the learned subspace, and then infer the local tangent structures according to the affinity propagation of low-level-view geometric correlations. As a consequence, more discriminative subspace representation can be learned from global semantic pivots to local geometric details. Experimental comparisons on three benchmark image datasets show the promising performance and flexibility of our model.

关键词： Semantics Correlation Visualization Skeleton Matrix decomposition Kernel Laplace equations Unsupervised multi-view subspace learning semantic inconsistency tensor factorization deep auto-encoders

来源：评论

学校读者我要写书评

暂无评论

Application of interpretable machine learning models for the intelligent decision

引用

NEUROCOMPUTING 2019年 333卷 273-283页

作者： Li, Yawen Yang, Liu Yang, Bohan Wang, Ning Wu, Tian Beijing Univ Posts & Telecommun Sch Econ & Management Beijing Peoples R China Hong Kong Univ Sci & Technol Dept Comp Sci & Engn Hong Kong Peoples R China Chinese Acad Social Sci Grad Sch Dept World Econ & Polit Beijing Peoples R China China Agr Univ Int Coll Beijing Beijing Peoples R China Chinese Acad Sci Acad Math & Syst Sci NCMIS Beijing Peoples R China Univ Chinese Acad Sci Sch Econ & Management Beijing Peoples R China Chinese Acad Sci Key Lab Big Data Min & Knowledge Management Beijing Peoples R China

In this study, an interpretable machine learning algorithm is proposed for the issues of intelligent decision through predicting the firms' efficiency of innovation. Based on the unbalanced panel data collected in Zhongguancun Science Parks from year 2005 to 2015, the efficiency of over 10,000 firms have been analysed in this study, and the change and growth of these firms have been captured over time. The linear regression, decision tree, random forests, neural network and XGBoost models are applied to figure out the impact factors of innovation. After comparing the results of different models, it has been found that the accuracy of XGBoost for R&D efficiency labelled, commercial efficiency labelled and overall efficiency labelled classification problems are 73.65%, 70.02% and 70.09%, which outperform the other four models. Moreover, the interpretability of XGBoost is also better than other models. Thus, the XGBoost model makes it possible for managers to predict the firm's future innovation performance derived from their innovation strategies in the current stage. Furthermore, it helps firms to build an intelligent decision support system, which is of great importance for them to deal with complex decision environments, and to increase their efficiency of innovation in the long-term dynamic competition with other firms. (C) 2018 Elsevier B.V. All rights reserved.

关键词： Machine learning XGBoost R&D investments Firm size Innovation performance

来源：评论

学校读者我要写书评

暂无评论

High Performance Geological Disaster Recognition using Deep Learning 6th

High Performance Geological Disaster Recognition using Deep ...

引用

6th International Conference on Information Technology and Quantitative management (ITQM)

作者： Liu, Ying Wu, Linzhi Univ Chinese Acad Sci Beijing 100190 Peoples R China Chinese Acad Sci Key Lab Big Data Min & Knowledge Management Beijing 100190 Peoples R China

Geological disaster recognition on optical image is one of the key techniques in disaster control and disaster relief. Comparing with optical images, remote sensing images contain much higher resolution and more visualized contents. In this paper, we propose a landslide recognition framework which trains a deep auto-encoder network on the compressed domain. ANN or SVM is used as the classifier for decision making. In addition, in order to meet the requirement of some real-time applications, a high performance training network on CUDA-enabled GPUs is designed and implemented. Experiments are conducted on optical images from Google Earth. (C) 2018 The Authors. Published by Elsevier B.V.

关键词： deep learning geological disaster recognition parallel computing CUDA

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：