检索结果-内蒙古大学图书馆

arXiv 2018年

作者： Park, Dae Hoon Chang, Yi Huawei Research America California School of Artificial Intelligence Jilin University Key Laboratory of Symbolic Computation and Knowledge Engineering Ministry of Education China

Ad-hoc retrieval models with implicit feedback often have problems, e.g., the imbalanced classes in the data set. Too few clicked documents may hurt generalization ability of the models, whereas too many non-clicked documents may harm effectiveness of the models and efficiency of training. In addition, recent neural networkbased models are vulnerable to adversarial examples due to the linear nature in them. To solve the problems at the same time, we propose an adversarial sampling and training framework to learn ad-hoc retrieval models with implicit feedback. Our key idea is (i) to augment clicked examples by adversarial training for better generalization and (ii) to obtain very informational non-clicked examples by adversarial sampling and training. Experiments are performed on benchmark data sets for common ad-hoc retrieval tasks such as Web search, item recommendation, and question answering. Experimental results indicate that the proposed approaches significantly outperformstrong baselines especially for high-ranked documents, and they outperform IRGAN in NDCG@5 using only 5% of labeled data for the Web search task. Copyright © 2018, The Authors. All rights reserved.

关键词： Information retrieval

来源：评论

学校读者我要写书评

暂无评论

A Cascaded Co-evolutionary Model for Attribute Reduction and Classification Based on Coordinating Architecture with Bidirectional Elitist Optimization

引用

Chinese Journal of Electronics 2017年第1期26卷 13-21页

作者： DING Weiping WANG Jiandong LI Yuehua CHENG Xueyun School of Computer Science and Technology Nantong University Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Jilin University Provincial Key Laboratory for Computer Information Processing Technology Soochow University College of Computer Science and Technology Nanjing University of Aeronautics and Astronautics

A cascaded co-evolutionary model for Attribute reduction and classification based on Coordinating architecture with bidirectional elitist optimization(ARC-CABEO) is proposed for the more practical applications. The regrouping and merging coordinating strategy of ordinary-elitist-role-based population is introduced to represent a more holistic cooperative co-evolutionary framework of different populations for attribute reduction. The master-slave-elitist-based subpopulations are constructed to coordinate the behaviors of different elitists, and meanwhile the elitist optimization vector with the strongest balancing between exploration and exploitation is selected out to expedite the bidirectional attribute co-evolutionary reduction process. In addition, two coupled coordinating architectures and the elitist optimization vector are tightly cascaded to perform the co-evolutionary classification of reduction subsets. Hence the preferring classification optimization goal can be achieved better. Some experimental results verify that the proposed ARC-CABEO model has the better feasibility and more superior classification accuracy on different UCI datasets, compared with representative algorithms.

关键词： Attribute reduction for classification Bidirectional elitist optimization Coordinating architecture Cascaded co-evolutionary model

来源：评论

学校读者我要写书评

暂无评论

A Layered Co-evolution Based Rough Feature Selection Using Adaptive Neighborhood Radius Hierarchy and Its Application in 3D-MRI

引用

Chinese Journal of Electronics 2017年第6期26卷 1168-1176页

作者： DING Weiping GUAN Zhijin WANG Jiehua TIAN Di School of Computer Science and Technology Nantong University State Key Laboratory for Novel Software Technology Nanjing University Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Jilin University Key Laboratory of Intelligent Perception and Systems for High-Dimensional Information of Ministry of Education Nanjing University of Science and Technology

As the conventional feature selection algorithms are prone to the poor running efficiency in largescale datasets with interacting features, this paper aims at proposing a novel rough feature selection algorithm whose innovation centers on the layered co-evolutionary strategy with neighborhood radius hierarchy. This hierarchy can adapt the rough feature scales among different layers as well as produce the reasonable decompositions through exploiting any correlation and interdependency among feature subsets. Both neighborhood interaction within layer and neighborhood cascade between layers are adopted to implement the interactive optimization of neighborhood radius matrix, so that both the optimal rough feature selection subsets and their global optimal set are obtained efficiently. Our experimental results substantiate the proposed algorithm can achieve better effectiveness, accuracy and applicability than some traditional feature selection algorithms.

关键词： Layered co-evolution Rough feature se lection Adaptive neighborhood radius hierarchy Longitudinal cortical surface labeling

来源：评论

学校读者我要写书评

暂无评论

A cloud-based evaluation system for science-and-engineering students 4th

A cloud-based evaluation system for science-and-engineering ...

引用

4th International Conference of Pioneer Computer Scientists, Engineers and Educators, ICPCSEE 2018

作者： Huang, Qian Ye, Feng Chen, Yong Xu, Peiling College of Computer and Information Hohai University Nanjing211100 China Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Jilin University Changchun130012 China Postdoctoral Centre Nanjing Longyuan Micro-Electronic Company Nanjing211106 China Suzhou College of Information Technology Suzhou215200 China

ISBN: (纸本)9789811322051

With the burgeoning of IT industry, more and more companies and universities concentrate on the scientific evaluation of science-and-engineering students. Existing evaluation strategies typically lie on grades or scores of the courses taken by students, which have obvious drawbacks nowadays and cannot lead to a proper improvement of education management. This paper proposes an overall student evaluation system architecture that includes three levels, i.e. data collection infrastructure which comprises student data collection and student data transmission, data center which is composed of four sub-levels, and unified portal which defines unified applications and classes of visiting terminals. In the proposed architecture, the main contribution lie in the upper most sub-level of data center, i.e. evaluation services. Four categories of student evaluation services, i.e. moral trait, civic literacy, knowledge level and comprehensive ability, are defined. Furthermore, in order to have a satisfactory feedback in the practical teaching process, the most important comprehensive ability for science-and-engineering students is fractionized into four sub-categories and visualized from several different aspects for a good feedback in practical teaching process. © Springer Nature Singapore Pte Ltd. 2018.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

Approximate Model Counting by Partial knowledge Compilation

arXiv

引用

arXiv 2018年

作者： Lai, Yong College of Computer Science and Technology Jilin University Changchun130012 China Key Laboratory of Symbolic Computation Knowledge Engineering of Ministry of Education Changchun China

Model counting is the problem of computing the number of satisfying assignments of a given propositional formula. Although exact model counters can be naturally furnished by most of the knowledge compilation (KC) methods, in practice, they fail to generate the compiled results for the exact counting of models for certain formulas due to the explosion in sizes. Decision-DNNF is an important KC language that captures most of the practical compilers. We propose a generalized Decision-DNNF (referred to as partial Decision-DNNF) via introducing a class of new leaf vertices (called unknown vertices), and then propose an algorithm called PARTIALKC to generate randomly partial Decision-DNNF formulas from the given formulas. An unbiased estimate of the model number can be computed via a randomly partial Decision-DNNF formula. Each calling of PARTIALKC consists of multiple callings of MICROKC, while each of the latter callings is a process of importance sampling equipped with KC technologies. The experimental results show that PARTIALKC is more accurate than both SampleSearch and SearchTreeSampler, PARTIALKC scales better than SearchTreeSampler, and the KC technologies can obviously accelerate sampling. Copyright © 2018, The Authors. All rights reserved.

关键词： Importance sampling

来源：评论

学校读者我要写书评

暂无评论

Image clustering segmentation based on SLIC superpixel and transfer learning

引用

Pattern Recognition and Image Analysis 2017年第4期27卷 838-845页

作者： Li, X.X. Shen, X.J. Chen, H.P. Feng, Y.C. College of Computer Science and Technology Jilin University ChangchunJilin130012 China Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Jilin University ChangchunJilin130012 China

Traditional fuzzy C-means clustering algorithm has poor noise immunity and clustering results in image segmentation. To overcome this problem, a novel image clustering algorithm based on SLIC superpixel and transfer learning is proposed in this paper. In the proposed algorithm, SLIC superpixel method is used to improve the edge matching degree of image segmentation and enhances the robustness to noise. Transfer learning is adopted to correct the image segmentation result and further improve the accuracy of image segmentation. In addition, the proposed algorithm improves the original SLIC superpixel algorithm and makes the edge of the superpixel more accurate. Experimental results show that the proposed algorithm can obtain better segmentation results. © 2017, Pleiades Publishing, Ltd.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

A hybrid feature selection algorithm for microarray data

引用

Concurrency and computation: Practice and Experience 2018年

作者： Zheng, Yuefeng Li, Ying Wang, Gang Chen, Yupeng Xu, Qian Fan, Jiahao Cui, Xueting College of Computer Science and Technology Jilin University Changchun130012 China Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Jilin University Changchun China BODA College of Jilin Normal University SiPing China

For each microarray data set, only a small number of genes are beneficial. Due to the high-dimensional problem, gene selection research work remains a challenge. In order to solve the high-dimensional problem, we propose a dimensionality reduction algorithm named K Value Maximum Relevance Minimum Redundancy Improved Grey Wolf Optimizer (KMR2IGWO). First, in the processing of KMR2, the K genes are selected. Second, the K genes are initialized by two ways according to random selection feature and different proportions of selection feature. Finally, the IGWO algorithm selects the optimal classification accuracy and the optimal combination of gene by adjusting the parameters of fitness function. The algorithm has a significant dimensionality reduction effect and is suitable for high-dimensional data sets. Experimental results show that the proposing KMR2IGWO strategy significantly reduces the dimension of microarray data and removes the redundant features. On the 14 microarray datasets, compared with the four algorithms mRMR+PSO, mRMR + GA, mRMR + BA, mRMR + CS, the proposed algorithm has higher performance in classification accuracy and feature subset length. © 2018 John Wiley & Sons, Ltd.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Corrigendum to: Multi-Swarm Cuckoo Search Algorithm withQ-Learning Model

引用

The Computer Journal 2022年第7期65卷 1938-1938页

作者： Li, Juan Xiao, Dan-dan Zhang, Ting Liu, Chun Li, Yuan-xiang Wang, Gai-ge School of Artificial Intelligence Wuhan Technology and Business University Wuhan 430065 China School of Artificial Intelligence Wuchang University of Technology Wuhan 430223 China Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Jilin University No. 2699 Qianjin Street Gaoxin District Changchun Jilin China 130012 School of Computer Wuhan University No. 299 Bayi Street Wuchang District Wuhan Hubei China 430072 Department of Computer Science and Technology Ocean University of China No. 238 Songling Street Laoshan District Qingdao Shandong China 266100 Institute of Algorithm and Big Data Analysis Northeast Normal University No. 5268 Renmin Street Nanguan District Changchun Jilin China 130117

来源：评论

学校读者我要写书评

暂无评论

A Cloud-Based Evaluation System for Science-and-engineering Students

A Cloud-Based Evaluation System for Science-and-Engineering ...

引用

2018国际计算机前沿大会（原国际青年计算机大会）

作者： Qian Huang Feng Ye Yong Chen Peiling Xu College of Computer and Information Hohai University Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministryof Education Jilin University Postdoctoral Centre Nanjing Longyuan Micro-Electronic Company Suzhou College of Information Technology

With the burgeoning of IT industry, more and more companies and universities concentrate on the scientific evaluation of science-and-engineering students. Existing evaluation strategies typically lie on grades or scores of the courses taken by students, which have obvious drawbacks nowadays and cannot lead to a proper improvement of education management. This paper proposes an overall student evaluation system architecture that includes three levels, i.e. data collection infrastructure which comprises student data collection and student data transmission, data center which is composed of four sub-levels, and unified portal which defines unified applications and classes of visiting terminals. In the proposed architecture, the main contribution lie in the upper most sub-level of data center, i.e. evaluation services. Four categories of student evaluation services, i.e. moral trait, civic literacy, knowledge level and comprehensive ability,are defined. Furthermore, in order to have a satisfactory feedback in the practical teaching process, the most important comprehensive ability for science-andengineering students is fractionized into four sub-categories and visualized from several different aspects for a good feedback in practical teaching process.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Two-Dimensional Improvement for Farr-Gao Algorithm

引用

Journal of Systems Science & Complexity 2016年第5期29卷 1382-1399页

作者： DONG Tian School of Mathematics Key Laboratory of Symbolic Computation and Knowledge Engineering (Ministry of Education) Jilin University

Farr-Gao algorithm is a state-of-the-art algorithm for reduced Gr?bner bases of vanishing ideals of finite points, which has been implemented in Maple as a build-in command. This paper presents a two-dimensional improvement for it that employs a preprocessing strategy for computing reduced Gr?bner bases associated with tower subsets of given point sets. Experimental results show that the preprocessed Farr-Gao algorithm is more efficient than the classical one.

关键词： Grobner basis GrSbner escalier Newton interpolation basis tower set vanishing ideal.

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：