检索结果-内蒙古大学图书馆

International Joint Conference on Neural Networks

作者： Jinrong He Lixin Ding Lei Jiang Li Huang The School of Computer State Key Laboratory of Software Engineering Wuhan University Wuhan China State Key Laboratory of Software Engineering Wuhan University Wuhan China Key Laboratory of Knowledge Processing and Networked Manufacture Hunan University of Science and Technology Xiangtan China The School of Computer & Information Technology Shanxi University Shanxi China

Marginal Fisher analysis (MFA) is a well-known linear dimensionality reduction method. However, MFA does not utilize the local diversity information of the training data, which will degrade its performance. In order to enhance the discriminant power of MFA, this paper considers introducing local variation quantity to enlarge the distances between local neighborhood embeddings and proposes a flexible and efficient implementation of MFA (F-MFA) within the regularization framework. Therefore, the discriminant structure and diversity of data are preserved in low-dimensional subspace. Computationally, F-MFA is formulated as a trace differential optimization problem which can completely avoids the singularity problem as it exists in MFA. Further, an efficient algorithm is developed for implementing F-MFA via QR-decomposition. Experimental results on four face data sets demonstrate the effectiveness of our approach.

关键词： Algorithm design and analysis Symmetric matrices Linear programming Manifolds Eigenvalues and eigenfunctions Educational institutions TV

来源：评论

学校读者我要写书评

暂无评论

END-TO-END ENTITY DETECTION WITH PROPOSER AND REGRESSOR

arXiv

引用

arXiv 2022年

作者： Wen, Xueru Zhou, Changjiang Tang, Haotian Liang, Luguang Jiang, Yu Qi, Hong College of Computer Science and Technology Jilin University Changchun China Key Laboratory of Symbolic Computation and Knowledge Engineering Ministry of Education Jilin University China

Named entity recognition is a traditional task in natural language processing. In particular, nested entity recognition receives extensive attention for the widespread existence of the nesting scenario. The latest research migrates the well-established paradigm of set prediction in object detection to cope with entity nesting. However, the manual creation of query vectors, which fail to adapt to the rich semantic information in the context, limits these approaches. An end-to-end entity detection approach with proposer and regressor is presented in this paper to tackle the issues. First, the proposer utilizes the feature pyramid network to generate high-quality entity proposals. Then, the regressor refines the proposals for generating the final prediction. The model adopts encoder-only architecture and thus obtains the advantages of the richness of query semantics, high precision of entity localization, and easiness of model training. Moreover, we introduce the novel spatially modulated attention and progressive refinement for further improvement. Extensive experiments demonstrate that our model achieves advanced performance in flat and nested NER, achieving a new state-of-the-art F1 score of 80.74 on the GENIA dataset and 72.38 on the WeiboNER dataset. Copyright © 2022, The Authors. All rights reserved.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

MDPL-net: Multi-layer Dictionary Learning Network with Added Skip Dense Connections

MDPL-net: Multi-layer Dictionary Learning Network with Added...

引用

IEEE International Conference on data Mining (ICDM)

作者： Zhao Zhang Yulin Sun Zheng Zhang Yang Wang Lin Wu Meng Wang School of Computer Science and Technology Soochow University Suzhou China Ministry of Education Key Laboratory of Knowledge Engineering with Big Data School of Computer Science and Information Engineering Hefei University of Technology Hefei China Bio-Computing Research Center Harbin Institute of Technology (Shenzhen) Shenzhen China

ISBN: (数字)9781728183169

ISBN: (纸本)9781728183176

Dictionary learning (DL) is powerful for representation learning, while it fails to capture the deep hierarchical information hidden in data. In this paper, we propose a new generalized end-to-end mulita-layer representation learning architecture referred to as Multi-layer Dictionary Pair Learning Network (MDPL-net) for the deep sparse and hierarchical representation of images. To enable MDPL-net to conduct accurate classification, MDPL-net clearly integrates the skip connection end-to-end network and multi-layer deep sparse dictionary learning into a unified architecture. The representation learning module has several hidden DL blocks, where each hidden DL block has a dictionary pair learning (DPL) layer, a batch-norm layer and an activation function layer, and the DL blocks are connected in a feed-forward manner. To further improve the information flow and maintain the privileged features between different DL blocks, a novel skip dense connectivity pattern is deployed between hidden DL blocks, which can obtain more stable and discriminative features. The DPL layer jointly formulates the discriminative synthesis dictionary and analysis dictionary by minimizing reconstruction error within each batch over the feature maps from front layers. Extensive results on benchmark databases demonstrate the effectiveness of MDPL-net for discriminative representation and robust image classification.

关键词： Dictionaries databases Conferences Machine learning data mining Image reconstruction Image classification

来源：评论

学校读者我要写书评

暂无评论

Chinese word segmentation probability dictionary training and enrich solution

引用

International Journal of Applied Mathematics and Statistics 2013年第24期51卷 162-170页

作者： Qi, Wang Guangping, Zeng Yonghao, Wang Xunlong, Gui School of Computer and Communication Engineering University of Science and Technology Beijing Beijing 100083 China Beijing Key Laboratory of Knowledge Engineering for Materials Science Beijing 100083 China SDE of Product Ads Joyo Amazon Co. Beijing China

Word segmentation is one necessary component for Asian language search engine, and probability dictionary is core component for statistical language model based word segmentation application. Manually marking is the traditional way to build probability dictionary, slow and low efficient, usually can't cover recent new words. Society is progressing, there are always new words born in human language. How to include new words into probability dictionary to increase word segmentation application's recall and precision value is a big challenge for search engine of Asian language, for example Chinese. This article introduces one automatically probability dictionary learning and enriches approach. This unsupervised Machine Learning based solution extracts word appear probability and word transfer probability information from user search logs, learn new words which does not exist in our current lexicon to enrich our tokenization probability dictionary. © 2013 by CESER Publications.

关键词： Probability

来源：评论

学校读者我要写书评

暂无评论

Edge Intelligence Empowered Distribution Path Planning with Internet of Vehicles

Edge Intelligence Empowered Distribution Path Planning with ...

引用

IEEE International Conference on High Performance Computing and Communications (HPCC)

作者： Tiancai Li Yiping Wen Zheng Tan Hong Chen School of Computer Science and Engineering Hunan University of Science and Technology China Key Laboratory of Knowledge Processing & Networked Manufacturing Hunan University of Science and Technology

ISBN: (纸本)9781728176505

With rapid urbanization and increasing traffic, distribution path planning has become an important challenging issue. Traditional vehicle distribution route planning mostly relies on static road information or historical traffic data for route planning. However, route planning based on such information may be unreasonable, because many uncertainty factors involve in the vehicle distribution process. Edge intelligence can help to handle such uncertainty factors, as it can offer smart services in close proximity to the Internet of Vehicles (IoV) environment with low latency and less cost. Therefore, in this paper, a model for dynamic distribution path planning with IoV and edge intelligence is constructed, and a corresponding planning strategy is proposed. The result of simulation experiments shows its effectiveness.

关键词： Uncertainty Intelligent vehicles Computational modeling Roads High performance computing Path planning Planning

来源：评论

学校读者我要写书评

暂无评论

A ε-domination based multi-objective particle swarm optimization

A ε-domination based multi-objective particle swarm optimiz...

引用

2010 International Conference on Measuring Technology and Mechatronics Automation(ICMTMA 2010)(2010年检测技术与机电自动化国际会议)

作者： Junnian Wang Lanxia Liu Yiduo Yan Deshun Liu School of Information and Electrical Engineering Hunan University of Science and Technology Xiangtan Knowledge Processing and Networked Manufacturing Key Laboratory in Universities of Hunan Province Hu

A multi-objective particle swarm optimization algorithm based on ε- dominance is proposed. The ε-dominance is applied to update the external set in order to obtain the Pareto set with better distribution, and the dynamic adjustment strategy, which made the algorithm achieving the search and approximation to the Pareto set, is adopted in the iterative process of the ε-Pareto solution set. Three benchmark cases were tested and the results show that this algorithm is much more efficient than the DNPSO.

关键词： Multi-objective optimization particle swarm optimization ε-dominance Pareto set

来源：评论

学校读者我要写书评

暂无评论

Heterogeneous deep web data extraction using ontology evolution

引用

Journal of Convergence Information Technology 2010年第8期5卷 23-23页

作者： Chen, Kerui Zhao, Jinchao Zuo, Wanli He, Fengling Chen, Yongheng College of Computer Science and Technology Jilin University Changchun 130012 China Key Laboratory of Symbol Computation and Knowledge Engineering of the Ministry of Education Changchun China School of Computer and Communication Engineering Zhengzhou University of Light Industry Zhengzhou 450002 China

This paper proposed a complex ontology evolution based method of extracting data, and also completely designed an extraction system, which consists of four important components: Resolver, Extractor, Consolidator and the ontology construction components. The system gives priority to the construction of mini-ontology. When the user submits query keywords to the deep web query interface, the returned result will pass through the prior three components;after that, the final execution result will be returned to user in a unified form. This paper adopted an extraction method that is different from the general ontology extraction. More specifically, the ontology used in extraction here is dynamic evolution, which can adapt various data source better. Experimental results proved that this method could effectively extract the data in the query result pages.

关键词： Ontology

来源：评论

学校读者我要写书评

暂无评论

Automatic table integration by domain-specific ontology

International Journal of Digital Content Technology and its ...

引用

International Journal of Digital Content Technology and its Applications 2011年第1期5卷 218-225页

作者： Kerui, Chen Jinchao, Zhao Wanli, Zuo Fengling, He Yongheng, Chen College of Computer Science and Technology Jilin University Changchun 130012 China Key Laboratory of Symbol Computation and knowledge Engineering of the Ministry of Education Changchun China School of Computer and Communication Engineering Zhengzhou University of Light Industry Zhengzhou 450002 China

Deep web could automatically produce web pages according to the query criteria of users. The report found most query result page store data information using table form. knowledge management, information retrieval, Web mining, abstract extraction and so on were benefited from automatically understanding of table forms. The study web forms on the web information extraction and integration have important significance. This paper proposed a domain-specific ontology based strategy for integration tables, and this method could independent the structure of table. Experimental results confirm that this method could effectively improve the accuracy of integration.

关键词： Integration

来源：评论

学校读者我要写书评

暂无评论

H function based tamper-proofing software watermarking scheme

Journal of Software

引用

Journal of Software 2011年第1期6卷 149-155页

作者： Zhu, Jianqi Liu, Yanheng Wang, Aimin Yin, Kexin College of Computer Science and technology Ministry of Education Jilin University Changchun China Key Laboratory of Computation and Knowledge Engineering Ministry of Education Jilin University Changchun China College of computer and science and engineering ChangChun University of Technology Changchun China

A novel constant tamper-proofing software watermark technique based on H encryption function is presented. First we split the watermark into smaller pieces before encoding them using CLOC scheme. With the watermark pieces, a many-to-one function (H function) as the decoding function is constructed in order to avoid the pattern-matching or reverse engineering attack. The results of the function are encoded into constants as the parameters of opaque predicates or appended to the condition branches of the program to make the pieces relevant. The feature of interaction among the pieces improves the tamper-proofing ability because there being one piece destroyed, the program will not work correctly. The simulation shows that the performance of the proposed scheme is good and can resist many kinds of attacks. © 2011 ACADEMY PUBLISHER.

关键词： Pattern matching

来源：评论

学校读者我要写书评

暂无评论

Distance Ratio Fractal for Complex Mapping z\leftarrow z^a

Distance Ratio Fractal for Complex Mapping z\leftarrow z^a

引用

International Multi-Symposiums on Computer and Computational Sciences (IMSCCS)

作者： Xizhe Zhang Tianyang Lv Shaobin Huang Zhengxuan Wang College of Computer Science and Technology Key laboratory of symbolic computing and knowledge engineering of ministry of education Jilin University Changchun China College of Computer Science and Technology Harbin Engineering of Technology Harbin China

The complex mapping z larr z a is important in dynamical application, but it is not received as much attention in the literature as the mapping z larr z a +c, for there is not fractal structure by using escape time algorithm. This paper utilizes a new method named as distance ratio iteration method and discusses the iteration properties of the complex mapping z larr z a . The distance ratio iteration method can render the convergence region of the mapping, so the image has complex and self-similarity structure. This paper generates fractal image using distance ratio iteration method for various exponents of z larr z a and discusses their visual properties. There is rich detail fractal structure in the mapping z larr z a

关键词： Fractals Rendering (computer graphics) Image generation Convergence Educational institutions Computer science Educational technology knowledge engineering Image analysis Laboratories

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：