检索结果-内蒙古大学图书馆

European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases, ECML PKDD 2013

作者： Yu, Wenchao Zeng, Guangxiang Luo, Ping Zhuang, Fuzhen He, Qing Shi, Zhongzhi Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing 100190 China University of Chinese Academy of Sciences Beijing 100049 China University of Science and Technology of China China HP Labs. China China

ISBN: (纸本)9783642409936

The problem of embedding arises in many machine learning applications with the assumption that there may exist a small number of variabilities which can guarantee the "semantics" of the original high-dimensional data. Most of the existing embedding algorithms perform to maintain the locality-preserving property. In this study, inspired by the remarkable success of representation learning and deep learning, we propose a framework of embedding with autoencoder regularization (EAER for short), which incorporates embedding and autoencoding techniques naturally. In this framework, the original data are embedded into the lower dimension, represented by the output of the hidden layer of the autoencoder, thus the resulting data can not only maintain the locality-preserving property but also easily revert to their original forms. This is guaranteed by the joint minimization of the embedding loss and the autoencoder reconstruction error. It is worth mentioning that instead of operating in a batch mode as most of the previous embedding algorithms conduct, the proposed framework actually generates an inductive embedding model and thus supports incremental embedding efficiently. To show the effectiveness of EAER, we adapt this joint learning framework to three canonical embedding algorithms, and apply them to both synthetic and real-world data sets. The experimental results show that the adaption of EAER outperforms its original counterpart. Besides, compared with the existing incremental embedding algorithms, the results demonstrate that EAER performs incremental embedding with more competitive efficiency and effectiveness. © 2013 Springer-Verlag.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Modeling lexical cohesion for document-level machine translation

Modeling lexical cohesion for document-level machine transla...

引用

23rd International Joint Conference on Artificial Intelligence, IJCAI 2013

作者： Xiong, Deyi Ben, Guosheng Zhang, Min Lü, Yajuan Liu, Qun School of Computer Science and Technology Soochow University Suzhou 215006 China Institute for Infocomm Research 1 Fusionopolis Way 21-01 Connexis 138632 Singapore Key Laboratory of Intelligent Information Processing Institute of Computing Technology China Centre for Next Generation Localisation School of Computing Dublin City University Ireland

ISBN: (纸本)9781577356332

Lexical cohesion arises from a chain of lexical items that establish links between sentences in a text. In this paper we propose three different models to capture lexical cohesion for document-level machine translation: (a) a direct reward model where translation hypotheses are rewarded whenever lexical cohesion devices occur in them, (b) a conditional probability model where the appropriateness of using lexical cohesion devices is measured, and (c) a mutual information trigger model where a lexical cohesion relation is considered as a trigger pair and the strength of the association between the trigger and the triggered item is estimated by mutual information. We integrate the three models into hierarchical phrase-based machine translation and evaluate their effectiveness on the NIST Chinese-English translation tasks with large-scale training data. Experiment results show that all three models can achieve substantial improvements over the baseline and that the mutual information trigger model performs better than the others.

关键词： Machine translation

来源：评论

学校读者我要写书评

暂无评论

A model of three points for location estimation in wireless sensor networks

引用

2013 2nd International Symposium on Materials Science and Engineering technology, ISMSET 2013

作者： Xie, Shao Guo Hu, Yan Jun Wang, Yi Jiang, Fang Liu, Jing Jing Wang, Ying Guan Key Laboratory of Intelligent Computing and Signal Processing Ministry of Education AnHui University Hefei China Key Laboratory of Wireless Sensor Network and Communication Shanghai Institute of Microsystem and Information Technology Chinese Academy of Sciences 865 Changning Road Shanghai 200050 China

ISBN: (纸本)9783037858028

In this paper, we propose a novel model of three points named TP for location estimation in wireless sensor networks (WSNs) with random deployment of anchor nodes. In this model, we select three anchor nodes which have the strongest received signal strength (RSS) for location estimation, the centroid algorithm and the method of intersection of judgment are used to estimate the location of unknown nodes. To further exploit three nearest intersection points in TP, the enhanced TP (ETP) is proposed. The simulation results show that the proposed models outperform MMSE and BML in terms of the localization accuracy for WSNs. Moreover, the localization accuracy of the proposed models in scenario 2 with random deployment of anchor nodes are better than in scenario 1 with planned deployment of anchor nodes. Additionally, compared with MMSE and BML, ETP and TP can reduce the environmental impact on location estimation. © (2013) Trans Tech Publications, Switzerland.

关键词： Location

来源：评论

学校读者我要写书评

暂无评论

Distributed query processing in an ad-hoc semantic web data sharing system

Distributed query processing in an ad-hoc semantic web data ...

引用

2013 IEEE 37th Annual Computer Software and Applications Conference, COMPSAC 2013

作者： Zhou, Jing Bochmann, Gregor V. Shi, Zhongzhi School of Computer Science Communication University of China Beijing China School of Electrical Engineering and Computer Science University of Ottawa ON Canada Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing China

ISBN: (纸本)9780769549798

Sharing the Semantic Web data in proprietary datasets in which data is encoded in RDF triples in a decentralized environment calls for efficient support from distributed computing technologies. The highly dynamic ad-hoc settings that would be pervasive for Semantic Web data sharing among personal users in the future, however, pose even more demanding challenges for the enabling technologies. We extend previous work on a hybrid P2P architecture for an ad-hoc Semantic Web data sharing system which better models the data sharing scenario by allowing data to be maintained by its own providers and exhibits satisfactory scalab.lity owing to the adoption of a two-level distributed index and hashing techniques. Additionally, we propose efficient distributed processing of SPARQL queries in such a context and explore optimization techniques that build upon distributed query processing for database systems and relational algebra optimization. We anticipate that our work will become an indispensable, complementary approach to making the Semantic Web a reality by delivering efficient data sharing and reusing in an ad-hoc environment. © 2013 IEEE.

关键词： Query processing

来源：评论

学校读者我要写书评

暂无评论

Classification of big velocity data via cross-domain Canonical Correlation Analysis

Classification of big velocity data via cross-domain Canonic...

引用

IEEE International Conference on Big Data

作者： Bo Zhang Zhong-Zhi Shi The Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing China

Many classification techniques work well only under a common assumption that the training and test data are drawn from the same feature space and the same distribution. However, big velocity data usually show disobedience of this assumption. For example, in the field of web-document classification, new document is continuously emerging every day. Transfer learning aims at leveraging the knowledge in lab.led source domains to predict the unlab.led data in a target domain, where the distributions are different in domains. As one of the important research directions of transfer learning, one kind of approaches focus on the correspondence between pivot features and all the other specific features from different domains, to extract some relevant features that may reduce the difference between the domains, have attracted wide attention and study. However, the limitation caused by the vague meanings in different domains prevents these algorithms from further improvement. To tackle this problem, we propose a cross-domain canonical correlation analysis algorithm called CD-CCA by applying Canonical Correlation Analysis (CCA) to transfer learning. CD-CCA can learn a semantic space of multi-view correspondences from different domains respectively and transfer the knowledge by dimensionality reduction in a multi-view way. Experimental results on the 144×6 classification problems in 20Newsgroups, show that CD-CCA can significantly improve the prediction accuracy.

关键词： Correlation Algorithm design and analysis Classification algorithms Feature extraction Semantics Vectors Mutual information

来源：评论

学校读者我要写书评

暂无评论

TEMPORALLY MULTIPLE DYNAMIC TEXTURES SYNTHESIS USING PIECEWISE LINEAR DYNAMIC SYSTEMS

TEMPORALLY MULTIPLE DYNAMIC TEXTURES SYNTHESIS USING PIECEWI...

引用

IEEE International Conference on Image processing

作者： Xing Yan Hong Chang Xilin Chen Key Lab of Intelligent Information Processing of Chinese Academy of Sciences (CAS) Institute of Computing Technology CAS Beijing 100190 China

ISBN: (纸本)9781479923427

Real-world nonlinear dynamic textures (DTs) usually consist of temporally multiple linear DTs which cannot be correctly modeled by previous works. In this paper, we propose piecewise linear dynamic systems (PLDS) to model temporally multiple DTs. PLDS simultaneously decides the temporal segmentation, models each DT segment with an LDS and the whole DT by switching between the LDS'. Experimental results verify that PLDS can capture the stochastic and dynamic nature of temporally multiple DTs and it synthesizes nonlinear DTs without decay or divergence. An EM-like algorithm iterating between sequence division and LDS' fitting is adopted to learn the model parameters.

关键词： Temporally Multiple Dynamic Textures Piecewise Linear Dynamic Systems Temporal Segmentation Local Digital Switch model parameters Programmable logic devices textures Stochastic dynamic decay Decay biodeterioration synthesis

来源：评论

学校读者我要写书评

暂无评论

Multifractal analyses of daily rainfall time series in Pearl River basin of China

引用

Physica A: Statistical Mechanics and its Applications 2014年 405卷 193-202页

作者： Zu-Guo Yu Yee Leung Yongqin David Chen Qiang Zhang Vo Anh Yu Zhou Hunan Key Laboratory for Computation and Simulation in Science and Engineering Xiangtan University Xiangtan Hunan 411105 China Key Laboratory of Intelligent Computing and Information Processing of Ministry of Education Xiangtan University Xiangtan Hunan 411105 China School of Mathematical Sciences Queensland University of Technology GPO Box 2434 Brisbane Q4001 Australia Department of Geography and Resource Management The Chinese University of Hong Kong Hong Kong China Institute of Environment Energy and Sustainability The Chinese University of Hong Kong Hong Kong China Department of Water Resources and Environment Sun Yat-sen University Guangzhou 510275 China Key Laboratory of Water Cycle and Water Security in Southern China of Guangdong High Education Institute Sun Yat-sen University Guangzhou 510275 China

The multifractal properties of daily rainfall time series at the stations in Pearl River basin of China over periods of up to 45 years are examined using the universal multifractal approach based on the multiplicative cascade model and the multifractal detrended fluctuation analysis (MF-DFA). The results from these two kinds of multifractal analyses show that the daily rainfall time series in this basin have multifractal behavior in two different time scale ranges. It is found that the empirical multifractal moment function K ( q ) of the daily rainfall time series can be fitted very well by the universal multifractal model (UMM). The estimated values of the conservation parameter H from UMM for these daily rainfall data are close to zero indicating that they correspond to conserved fields. After removing the seasonal trend in the rainfall data, the estimated values of the exponent h ( 2 ) from MF-DFA indicate that the daily rainfall time series in Pearl River basin exhibit no long-term correlations. It is also found that K ( 2 ) and elevation series are negatively correlated. It shows a relationship between topography and rainfall variability.

关键词： Daily rainfall time series Multifractal property Universal multifractal model Multifractal detrended fluctuation analysis

来源：评论

学校读者我要写书评

暂无评论

Pivot probability induction for statistical machine translation with topic similarity

引用

Journal of Computational information Systems 2013年第20期9卷 8351-8359页

作者： Huang, Yanzhou Shi, Xiaodong Su, Jinsong Chen, Yidong Huang, Guimin Fujian Key Lab. of the Brain-Like Intelligent Systems Xiamen University Xiamen 361005 China Department of Cognitive Science School of Information Science and Technology Xiamen University Xiamen 361005 China School of Software Xiamen University Xiamen 361005 China Research Center on Data Science and Social Computing Guilin University of Electronic Technology Guilin 541004 China

Previous works employ the pivot language approach to conduct statistical machine translation when encountering with limited amount of bilingual corpus. Conventional solutions based upon phrase-table combination overlook the semantic discrepancy between the source-pivot corpus and pivot-target corpus and consequently lead to probability estimation inaccuracy for the induced translation rules. In this paper, the latent topic structure of the document-level training data is learned automatically and each phrase translation rule is assigned to a topic distribution. Furthermore, the phrase probability induction is carried out on the basis of the topic similarity, allowing the translation system to consider the semantic relatedness among different rules. Using BLEU as a metric of translation accuracy, we find out our system is capable of achieving a absolute improvement in in-domain test compared with the baseline system. © 2013 Binary information Press.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Bilingually-guided monolingual dependency grammar induction

Bilingually-guided monolingual dependency grammar induction

引用

51st Annual Meeting of the Association for Computational Linguistics, ACL 2013

作者： Liu, Kai Lü, Yajuan Jiang, Wenbin Liu, Qun Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences P.O. Box 2704 Beijing 100190 China Centre for Next Generation Localisation Faculty of Engineering and Computing Dublin City University Ireland University of Chinese Academy of Sciences China

ISBN: (纸本)9781937284503

This paper describes a novel strategy for automatic induction of a monolingual dependency grammar under the guidance of bilingually-projected dependency. By moderately leveraging the dependency information projected from the parsed counterpart language, and simultaneously mining the underlying syntactic structure of the language considered, it effectively integrates the advantages of bilingual projection and unsupervised induction, so as to induce a monolingual grammar much better than previous models only using bilingual projection or unsupervised induction. We induced dependency grammar for five different languages under the guidance of dependency information projected from the parsed English translation, experiments show that the bilinguallyguided method achieves a significant improvement of 28.5% over the unsupervised baseline and 3.0% over the best projection baseline on average. © 2013 Association for Computational Linguistics.

关键词： Syntactics

来源：评论

学校读者我要写书评

暂无评论

ROBUST MULTI-PATCH TRACKING

ROBUST MULTI-PATCH TRACKING

引用

IEEE International Conference on Image processing

作者： Shanxin Yuan Jun Miao Laiyun Qing Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing 100190 China

ISBN: (纸本)9781479923427

In this paper, we propose a robust and fast multi-patch visual tracking algorithm within the Bayesian inference framework. The target template is initialized by selecting the object in the first frame manually and dividing it into small patches. For one certain frame, target candidates are sampled with the state transition model. Each candidate is divided into patches in the same way as the target template. By comparing the candidate's patches with the corresponding template patches, we can get the candidate's likelihood. The tracking result is the candidate which Maximum a Posteriori estimation. After that, tracking is continued using the Bayesian state inference and template update. Our approach can handle appearance variation, occlusion, illumination change, scale variation, rotation and cluttered background. The tracker is fast and performs favorably against several state-of-the-art trackers on challenging sequences.

关键词： Visual tracking Bayesian inference multi-patch fast robust Bayesian inference visual tracking Fasting jigs(templates) tracking Maximum a posteriori estimation Robustness Patches State Change candidate species

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：