检索结果-内蒙古大学图书馆

Is Local Window Essential for Neural Network based Chinese Word Segmentation?

Is Local Window Essential for Neural Network based Chinese W...

第十五届全国计算语言学学术会议(CCL2016)暨第四届基于自然标注大数据的自然语言处理国际学术研讨会(NLP-NABD-2016)

作者： Jinchao Zhang Fandong Meng Mingxuan Wang Daqi Zheng Wenbin Jiang Qun Liu Key Laboratory of Intelligent Information Processing Institute of Computing TechnologyChinese Academy of Sciences

Neural network based Chinese Word Segmentation(CWS)approaches can bypass the burdensome feature engineering comparing with the conventional *** previous neural network based approaches rely on a local window in character sequence lab.lling *** can hardly exploit the outer context and may preserve indifferent inner ***,the size of local window is a toilsome manual-tuned hyper-parameter that has significant influence on model *** are wondering if the local window can be discarded in neural network based *** this paper,we present a window-free Bi-directional Long Short-term Memory(Bi-LSTM)neural network based Chinese word segmentation *** model takes the whole sentence under consideration to generate reasonable word *** experiments show that the Bi-LSTM can learn sufficient context for CWS without the local window.

关键词： Chinese Word Segmentation Neural Network Window

来源：评论

学校读者我要写书评

暂无评论

Online Bayesian multiple kernel bipartite ranking 32

Online Bayesian multiple kernel bipartite ranking

引用

32nd Conference on Uncertainty in Artificial Intelligence 2016, UAI 2016

作者： Du, Changying Du, Changde Long, Guoping He, Qing Li, Yucheng Beijing100190 China Key Lab of Intelligent Information Processing of CAS Institute of Computing Technology CAS Beijing100190 China Key Laboratory of Optical Astronomy National Astronomical Observatories CAS Beijing100012 China University of Chinese Academy of Sciences Beijing100049 China

ISBN: (纸本)9781510827806

Bipartite ranking aims to maximize the area under the ROC curve (AUC) of a decision function. To tackle this problem when the data appears sequentially, existing online AUC maximization methods focus on seeking a point estimate of the decision function in a linear or predefined single kernel space, and cannot learn effective kernels automatically from the streaming data. In this paper, we first develop a Bayesian multiple kernel bipartite ranking model, which circumvents the kernel selection problem by estimating a posterior distribution over the model weights. To make our model applicable to streaming data, we then present a kernelized online Bayesian passive-aggressive learning framework by maintaining a variational approximation to the posterior based on data augmentation. Furthermore, to efficiently deal with large-scale data, we design a fixed budget strategy which can effectively control online model complexity. Extensive experimental studies confirm the superiority of our Bayesian multi-kernel approach.

关键词： Budget control

来源：评论

学校读者我要写书评

暂无评论

GLAD: Global-local-alignment descriptor for pedestrian retrieval

arXiv

引用

arXiv 2017年

作者： Wei, Longhui Zhang, Shiliang Yao, Hantao Gao, Wen Tian, Qi School of Electronic Engineering and Computer Science Peking University Beijing100871 China Key Lab of Intelligent Information Processing of CAS Institute of Computing Technology CAS Beijing100190 China University of Chinese Academy of Sciences Beijing100049 China Department of Computer Science University of Texas at San Antonio San AntonioTX78249-1604 United States

The huge variance of human pose and the misalignment of detected human images significantly increase the difficulty of person Re-Identification (Re-ID). Moreover, efficient Re-ID systems are required to cope with the massive visual data being produced by video surveillance systems. Targeting to solve these problems, this work proposes a Global-Local-Alignment Descriptor (GLAD) and an efficient indexing and retrieval framework, respectively. GLAD explicitly leverages the local and global cues in human body to generate a discriminative and robust representation. It consists of part extraction and descriptor learning modules, where several part regions are first detected and then deep neural networks are designed for representation learning on both the local and global regions. A hierarchical indexing and retrieval framework is designed to eliminate the huge redundancy in the gallery set, and accelerate the online Re-ID procedure. Extensive experimental results show GLAD achieves competitive accuracy compared to the state-of-the-art methods. Our retrieval framework significantly accelerates the online Re-ID procedure without loss of accuracy. Therefore, this work has potential to work better on person Re-ID tasks in real scenarios. Copyright © 2017, 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

Identification of pre-microRNAs by characterizing their sequence order evolution information and secondary structure graphs

引用

BMC bioinformatics 2018年第SUPPL 19期19卷 521页

作者： Yuanlin Ma Zuguo Yu Guosheng Han Jinyan Li Vo Anh Key Laboratory of Intelligent Computing and Information Processing of Ministry of Education and Hunan Key Laboratory for Computation and Simulation in Science and Engineering Xiangtan University Hunan 411105 China. Key Laboratory of Intelligent Computing and Information Processing of Ministry of Education and Hunan Key Laboratory for Computation and Simulation in Science and Engineering Xiangtan University Hunan 411105 China. yuzuguo@***. School of Electrical Engineering and Computer Science Queensland University of Technology GPO Box 2434 Brisbane Q4001 Australia. yuzuguo@***. Advanced Analytics Institute Faculty of Engineering & IT University of Technology Sydney P.O Box 123 Broadway NSW 2007 Australia. School of Mathematical Sciences Queensland University of Technology GPO Box 2434 Brisbane Q4001 Australia.

BACKGROUND:Distinction between pre-microRNAs (precursor microRNAs) and length-similar pseudo pre-microRNAs can reveal more about the regulatory mechanism of RNA biological processes. Machine learning techniques have been widely applied to deal with this challenging problem. However, most of them mainly focus on secondary structure information of pre-microRNAs, while ignoring sequence-order information and sequence evolution information. RESULTS:We use new features for the machine learning algorithms to improve the classification performance by characterizing both sequence order evolution information and secondary structure graphs. We developed three steps to extract these features of pre-microRNAs. We first extract features from PSI-BLAST profiles and Hilbert-Huang transforms, which contain rich sequence evolution information and sequence-order information respectively. We then obtain properties of small molecular networks of pre-microRNAs, which contain refined secondary structure information. These structural features are carefully generated so that they can depict both global and local characteristics of pre-microRNAs. In total, our feature space covers 591 features. The maximum relevance and minimum redundancy (mRMR) feature selection method is adopted before support vector machine (SVM) is applied as our classifier. The constructed classification model is named MicroRNA -NHPred. The performance of MicroRNA -NHPred is high and stable, which is better than that of those state-of-the-art methods, achieving an accuracy of up to 94.83% on same benchmark datasets. CONCLUSIONS:The high prediction accuracy achieved by our proposed method is attributed to the design of a comprehensive feature set on the sequences and secondary structures, which are capable of characterizing the sequence evolution information and sequence-order information, and global and local information of pre-microRNAs secondary structures. MicroRNA -NHPred is a valuable method for pre-microRNAs iden

关键词： Hibert-Huang transform Network PSI-BLAST profiles Pre-microRNA SVM mRMR

来源：评论

学校读者我要写书评

暂无评论

Real-Time Task Scheduling for Joint Energy Efficiency Optimization in Data Centers

Real-Time Task Scheduling for Joint Energy Efficiency Optimi...

引用

IEEE Symposium on Computers and Communications

作者： Youshi Wang Fa Zhang Rui Wang Yangguang Shi Hua Guo Zhiyong Liu Chinese Academy of Sciences (CAS) Institute of Computing Technology (ICT) Beijing China University of Chinese Academy of Sciences Beijing China ICT Key Laboratory of Intelligent Information Processing Beijing China Hong Kong University of Science and Technology Hong Kong China Technion - Israel Institute of Technology Haifa Israel State Grid Jingzhou Electric Power Company Jingzhou Hubei China ICT State Key Laboratory for Computer Architecture Beijing China

The high energy consumption has become one bottleneck in the development of the data centers (DCs), where the main energy consumers are the cooling system and the servers. Therefore, the joint optimization for the energy efficiency of the cooling system and the servers is a crucial problem, while most of previous works on energy saving only studies one of these two components in an isolated manner. In this paper, we propose a real-time strategy, rTCS (real-time Task Classification and Scheduling strategy), to jointly optimize the energy efficiency of these two components in the scenario where the tasks arrive dynamically. Strategy rTCS first lab.ls the tasks to classify them according to their run time and end time with a time complexity of O(1) and a bounded space complexity. Then, rTCS schedules the tasks in real time based on their lab.ls and the energy consumption model of the DC. Simulation results show that rTCS can effectively improve the energy efficiency of DCs.

关键词： Energy efficiency Data center Cooling system Task classification Real-time scheduling algorithm

来源：评论

学校读者我要写书评

暂无评论

Browsing regularities in hedonic content systems 25

Browsing regularities in hedonic content systems

引用

25th International Joint Conference on Artificial Intelligence, IJCAI 2016

作者： Luo, Ping Zhou, Ganbin Tang, Jiaxi Chen, Rui Yu, Zhongjie He, Qing Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing China University of Chinese Academy of Sciences Beijing China School of Computing Science Simon Fraser University Canada School of Information University of Michigan United States Deparment of Statistics and Finance University of Science and Technology of China China

Various hedonic content systems (e.g. mobile apps for video, music, news, jokes, pictures, social networks etc.) increasingly dominates people's daily spare life. This paper studies common regularities of browsing behaviors in these systems, based on a large data set of user logs. We found that despite differences in visit time and user types, the distribution over browsing length for a visit can be described by the inverse Gaussian form with a very high precision. It indicates that the choice threshold model of decision making on continuing browsing or leave does exist. Also, We found that the stimulus intensity, in terms of the amount of recent enjoyed items, affects the probability of continuing browsing in a curve of inverted-U shape. We discuss the possible origin of this curve based on a proposed Award-Aversion Contest model. This hypothesis is supported by the empirical study, which shows that the proposed model can successfully recover the original inverse Gaussian distribution for the browsing length. These browsing regularities can be used to develop better organization of hedonic content, which helps to attract more user dwell time in these systems.

关键词： Decision making

来源：评论

学校读者我要写书评

暂无评论

A local-optimization refinement algorithm in single particle analysis for macromolecular complex with multiple rigid modules

引用

Protein & Cell 2016年第1期7卷 46-62页

作者： Hong Shan Zihao wang Fa Zhang Yong Xiong Chang-Cheng Yin Fei Sun Department of Biophysics College of Basic Medical Sciences Peking University Health Science Center Beijing 100191China National Laboratory of Biomacromolecules Institute of Biophysics Chinese Academy of Sciences Beijing 100101 China Key Lab of Intelligent Information Processing and Advanced Computing Research Lab Institute of Computing TechnologyChinese Academy of Sciences Beijing 100190 China University of Chinese Academy of Sciences Beijing 100049 China Department of Molecular Biophysics and Biochemistry Yale University New Haven CT 06511 USA Center for Biological Imaging Institute of Biophysics Chinese Academy of Sciences Beijing 100101 China

Single particle analysis, which can be regarded as an average of signals from thousands or even millions of particle projections, is an efficient method to study the three-dimensional structures of biological macro- molecules. An intrinsic assumption in single particle analysis is that all the analyzed particles must have identical composition and conformation. Thus specimen heterogeneity in either composition or conformation has raised great challenges for high-resolution analysis. For particles with multiple conformations, inaccurate align- ments and orientation parameters will yield an averaged map with diminished resolution and smeared density. Besides extensive classification approaches, here based on the assumption that the macromolecular complex is made up of multiple rigid modules whose relative orien- tations and positions are in slight fluctuation around equilibriums, we propose a new method called as local optimization refinement to address this conformational heterogeneity for an improved resolution. The key idea is to optimize the orientation and shift parameters of each rigid module and then reconstruct their three-dimen- sional structures individually. Using simulated data of 80S/70S ribosomes with relative fluctuations between the large （60S/50S） and the small （40S/30S） subunits, we tested this algorithm and found that the resolutions of both subunits are significantly improved. Our method provides a proof-of-principle solution for high-resolutionsingle particle analysis of macromolecular complexes with dynamic conformations.

关键词： cryo-electron microscopy single particleanalysis conformational heterogeneity rigid module Iocaoptimization refinement

来源：评论

学校读者我要写书评

暂无评论

Deep Supervised Hashing for Fast Image Retrieval

Deep Supervised Hashing for Fast Image Retrieval

引用

IEEE Conference on Computer Vision and Pattern Recognition

作者： Haomiao Liu Ruiping Wang Shiguang Shan Xilin Chen Key Laboratory of Intelligent Information Processing of Chinese Academy of Sciences (CAS) Institute of Computing Technology CAS

ISBN: (纸本)9781467388528

In this paper, we present a new hashing method to learn compact binary codes for highly efficient image retrieval on large-scale datasets. While the complex image appearance variations still pose a great challenge to reliable retrieval, in light of the recent progress of Convolutional Neural Networks (CNNs) in learning robust image representation on various vision tasks, this paper proposes a novel Deep Supervised Hashing (DSH) method to learn compact similarity-preserving binary code for the huge body of image data. Specifically, we devise a CNN architecture that takes pairs of images (similar/dissimilar) as training inputs and encourages the output of each image to approximate discrete values (e.g. +1/-1). To this end, a loss function is elab.rately designed to maximize the discriminability of the output space by encoding the supervised information from the input image pairs, and simultaneously imposing regularization on the real-valued outputs to approximate the desired discrete values. For image retrieval, new-coming query images can be easily encoded by propagating through the network and then quantizing the network outputs to binary codes representation. Extensive experiments on two large scale datasets CIFAR-10 and NUS-WIDE show the promising performance of our method compared with the state-of-the-arts.

关键词： image retrieval binary code hashing hashing method images discrete value image representation LOSS FUNCTION image data Propagating Imagery (Psychotherapy)

来源：评论

学校读者我要写书评

暂无评论

Analysis of the paragraph vector model for information retrieval 16

Analysis of the paragraph vector model for information retri...

引用

2016 ACM International Conference on the Theory of information Retrieval, ICTIR 2016

作者： Ai, Qingyao Yang, Liu 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 China

ISBN: (纸本)9781450344975

Previous studies have shown that semantically meaningful representations of words and text can be acquired through neural embedding models. In particular, paragraph vector (PV) models have shown impressive performance in some natural language processing tasks by estimating a document (topic) level language model. Integrating the PV models with traditional language model approaches to retrieval, however, produces unstable performance and limited improvements. In this paper, we formally discuss three intrinsic problems of the original PV model that restrict its performance in retrieval tasks. We also describe modifications to the model that make it more suitable for the IR task, and show their impact through experiments and case studies. The three issues we address are (1) the unregulated training process of PV is vulnerable to short document overfitting that produces length bias in the final retrieval model;(2) the corpus-based negative sampling of PV leads to a weighting scheme for words that overly suppresses the importance of frequent words;and (3) the lack of word-context information makes PV unable to capture word substitution relationships. © 2016 ACM.

关键词： Natural language processing systems

来源：评论

学校读者我要写书评

暂无评论

Category aggregation among region proposals for object detection 17th

Category aggregation among region proposals for object detec...

引用

17th Pacific-Rim Conference on Multimedia, PCM 2016

作者： Li, Linghui Tang, Sheng Zhou, Jianshe Wang, Bin Tian, Qi Key Lab of Intelligent Information Processing Institute of Computing Technology CAS Beijing100190 China Beijing Advanced Innovation Center for Imaging Technology Capital Normal University Beijing100048 China Department of Computer Science University of Texas at San Antonio San AntonioTX78249-1604 United States

ISBN: (纸本)9783319488950

Recently, an overwhelming majority of object detection methods have focused on how to reduce the number of region proposals while keeping high object recall without consideration of category information. It may lead to a lot of false positives due to the interferences between categories especially when the number of categories is very large. To eliminate such interferences, we propose a novel category aggregation approach based upon our observation that more frequently detected categories around an object have the higher probabilities to be present in an image. After further exploiting the co-occurrence relationship between categories, we can determine the most possible categories for an image in advance. Thus, many false positives can be greatly filtered out before subsequent classification process. Our extensive experiments on the well-known ILSVRC 2015 detection dataset show that our approach can achieve 49.0% of mAP in the validation dataset and 45.36% of mAP in the test dataset ranked 5th in the ILSVRC 2015 detection task. © Springer International Publishing AG 2016.

关键词： Object detection

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：