检索结果-内蒙古大学图书馆

arXiv 2017年

作者： Dong, Jianfeng Li, Xirong Snoek, Cees G.M. College of Computer Science and Technology Zhejiang University Hangzhou310027 China Key Lab of Data Engineering and Knowledge Engineering School of Information Renmin University of China Beijing100872 China Informatics Institute University of Amsterdam Amsterdam1098 XH Netherlands

This paper strives to find amidst a set of sentences the one best describing the content of a given image or video. Different from existing works, which rely on a joint subspace for their image and video caption retrieval, we propose to do so in a visual space exclusively. Apart from this conceptual novelty, we contribute Word2VisualVec, a deep neural network architecture that learns to predict a visual feature representation from textual input. Example captions are encoded into a textual embedding based on multi-scale sentence vectorization and further transferred into a deep visual feature of choice via a simple multi-layer perceptron. We further generalize Word2VisualVec for video caption retrieval, by predicting from text both 3-D convolutional neural network features as well as a visual-audio representation. Experiments on Flickr8k, Flickr30k, the Microsoft Video Description dataset and the very recent NIST TrecVid challenge for video caption retrieval detail Word2VisualVec's properties, its benefit over textual embeddings, the potential for multimodal query composition and its state-of-the-art results. Copyright © 2017, 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

Semantics and computation of the evolution of hybrid systems with ariadne 14

Semantics and computation of the evolution of hybrid systems...

引用

14th International Conference on Computability and Complexity in Analysis, CCA 2017

作者： Collins, Pieter Bresolin, Davide Gonzalez, Sanja Živanovic Geretti, Luca Villa, Tiziano Department of Data Science and Knowledge Engineering Maastricht University Bouillonstraat 8-10 Postbus 616 6200MD Netherlands Dipartimento di Informatica Università di Bologna Mura Anteo Zamboni 7 Bologna40126 Italy Department of Mathematics and Computer Science Barry University 11300 NE 2nd Avenue Miami ShoresFL33161-6695 United States Dipartimento di Informatica Università Degli Studi di Verona Strada le Grazie 15 Verona37134 Italy

In this talk we will present material on the semantics, computability, and algorithms for the evolution of hybrid dynamical systems, and an overview of the tool Ariadne for verification of hybrid systems [1]. Hybrid systems are characterised by undergoing continuous evolution interspersed by discrete jumps. They exhibit all the complexities of finite automata, nonlinear dynamic systems and differential equations, and are extremely difficult to analyze. We will consider hybrid systems in which the continuous dynamics is given by a differential equation x = f(x), with discrete jumps x' = ri(x) which occur as soon as a guard condition gi(x) ≥ 0 is activated. It is clear that the evolution of a hybrid system undergoes discontinuities, but since only continuous functions are computable, it is not clear to what extent, if any, it is possible to perform a rigorous analysis of a hybrid system. We will first show that we can define lower and upper semantics of evolution under which it is possible to compute reachable sets, and that away from discontinuity points (such as grazing or corner collision points), these semantics agree [2]. In order to perform reachability analysis, it is necessary to define the evolution over bounded initial sets of states. We show that this can be done using the operations of range, compose, flow and solve operations on functions. We will see that constrained image sets of the form {f(x) | x ∈ D | g(x) ∈ C}, are sufficient to express the evolution exactly, except for the case of degenerate (non-transverse) cross- ings [3]. The flow operation is the most computationally demanding, and we will give some details of the implementation and efficiency considerations [4]. We will give examples of reachability analysis in Ariadne, including electrical power converters and heating systems. Finally, we will outline some areas of active research, including differential inclusions [5] and modular reasoning. © 2017 14th International Conference on Computabili

关键词： Hybrid systems

来源：评论

学校读者我要写书评

暂无评论

Random analysis of statistical rough set

Random analysis of statistical rough set

引用

2016 International Conference on Machine Learning and Cybernetics, ICMLC 2016

作者： Tsang, Eric C.C. Zhao, Su-Yun Faculty of Information Technology Macau University of Science and Technology C-Macau China Key Laboratory of Data Engineering and Knowledge Engineering MOE Renmin University of China Beijing China

ISBN: (纸本)9781509003891

Attribute reduction is an inevitable problem in machine learning and statistical learning. To improve the traditional rough set reduction, statistical rough sets is then proposed by introducing random sampling into the rough approximation. Random sampling is the main contribution of statistical rough sets. As a result, it is necessary to analyze the randomness of statistical rough sets. In this paper, we analyze and demonstrate the influence of the randomness in the process of attribute reduction by a large number of experiments to test the effectiveness and stability of the random sampling. © 2016 IEEE.

关键词： Sampling

来源：评论

学校读者我要写书评

暂无评论

Towards multi-target search of semantic association 6th

Towards multi-target search of semantic association

引用

6th Joint International Conference on Semantic Technology, JIST 2016

作者： Zhang, Xiang Lv, Yulian School of Computer Science and Engineering Southeast University Nanjing China Key Laboratory of Data Engineering and Knowledge Services Nanjing University Nanjing China Southeast University Suzhou China

ISBN: (纸本)9783319501116

Semantic association represents group relationship among objects in linked data. Searching semantic associations is complicated, which involves the search of multiple objects and the search of their group relationships simultaneously. In this paper, we propose this kind of search as a multi-target search, and we compare it to traditional search tasks, which we classify as single-target search. A novel search model is introduced, and the notion of virtual document is used to extract linguistic information of semantic associations. Multi-target search is finally fulfilled by a PageRank-like ranking scheme and a top-K selection policy considering object affinity. Experiments show that our approach is effective in improving retrieval precision on semantic associations. © Springer International Publishing AG 2016.

关键词： Linked data

来源：评论

学校读者我要写书评

暂无评论

Hierarchical Task Network Plan Reuse for video games

Hierarchical Task Network Plan Reuse for video games

引用

IEEE Symposium on Computational Intelligence and Games, CIG

作者： Dennis J. N. J. Soemers Mark H. M. Winands Department of Data Science and Knowledge Engineering Maastricht University

ISBN: (纸本)9781509018840

Hierarchical Task Network Planning is an Automated Planning technique. It is, among other domains, used in Artificial Intelligence for video games. Generated plans cannot always be fully executed, for example due to nondeterminism or imperfect information. In such cases, it is often desirable to re-plan. This is typically done completely from scratch, or done using techniques that require conditions and effects of tasks to be defined in a specific format (typically based on First-Order Logic). In this paper, an approach for Plan Reuse is proposed that manipulates the order in which the search tree is traversed by using a similarity function. It is tested in the SimpleFPS domain, which simulates a First-Person Shooter game, and shown to be capable of finding (optimal) plans with a decreased amount of search effort on average when re-planning for variations of previously solved problems.

关键词： Planning Compounds Games Silicon Engines Optimization C++ languages

来源：评论

学校读者我要写书评

暂无评论

Enhancements for real-time Monte-Carlo Tree Search in General Video Game Playing

Enhancements for real-time Monte-Carlo Tree Search in Genera...

引用

IEEE Symposium on Computational Intelligence and Games, CIG

作者： Dennis J. N. J. Soemers Chiara F. Sironi Torsten Schuster Mark H. M. Winands Department of Data Science and Knowledge Engineering Maastricht University

ISBN: (纸本)9781509018840

General Video Game Playing (GVGP) is a field of Artificial Intelligence where agents play a variety of real-time video games that are unknown in advance. This limits the use of domain-specific heuristics. Monte-Carlo Tree Search (MCTS) is a search technique for game playing that does not rely on domain-specific knowledge. This paper discusses eight enhancements for MCTS in GVGP; Progressive History, N-Gram Selection Technique, Tree Reuse, Breadth-First Tree Initialization, Loss Avoidance, Novelty-Based Pruning, knowledge-Based Evaluations, and Deterministic Game Detection. Some of these are known from existing literature, and are either extended or introduced in the context of GVGP, and some are novel enhancements for MCTS. Most enhancements are shown to provide statistically significant increases in win percentages when applied individually. When combined, they increase the average win percentage over sixty different games from 31.0% to 48.4% in comparison to a vanilla MCTS implementation, approaching a level that is competitive with the best agents of the GVG-AI competition in 2015.

关键词： Games Monte Carlo methods History Real-time systems Silicon knowledge based systems Avatars

来源：评论

学校读者我要写书评

暂无评论

Inverse extreme learning machine for learning with label proportions

Inverse extreme learning machine for learning with label pro...

引用

IEEE International Conference on Big data

作者： Limeng Cui Jiawei Zhang Zhensong Chen Yong Shi Philip S. Yu School of Computer and Control Engineering University of Chinese Academy of Sciences Beijing China Department of Computer Science Florida State University FL USA Chinese Academy of Sciences Key Laboratory of Big Data Mining and Knowledge Management Beijing China Department of Computer Science University of Illinois at Chicago IL USA

In large-scale learning problem, the scalability of learning algorithms is usually the key factor affecting the algorithm practical performance, which is determined by both the time complexity of the learning algorithms and the amount of supervision information (i.e., labeled data). Learning with label proportions (LLP) is a new kind of machine learning problem which has drawn much attention in recent years. Different from the well-known supervised learning, LLP can estimate a classifier from groups of weakly labeled data, where only the positive/negative class proportions of each group are known. Due to its weak requirements for the input data, LLP presents a variety of real-world applications in almost all the fields involving anonymous data, like computer vision, fraud detection and spam filtering. However, even through the required labeled data is of a very small amount, LLP still suffers from the long execution time a lot due to the high time complexity of the learning algorithm itself. In this paper, we propose a very fast learning method based on inversing output scaling process and extreme learning machine, namely Inverse Extreme Learning Machine (IELM), to address the above issues. IELM can speed up the training process by order of magnitudes for large datasets, while achieving highly competitive classification accuracy with the existing methods at the same time. Extensive experiments demonstrate the significant speedup of the proposed method. We also demonstrate the feasibility of IELM with a case study in real-world setting: modeling image attributes based on ImageNet Object Attributes dataset.

关键词： Training Calibration Support vector machines Supervised learning Visualization Optimization

来源：评论

学校读者我要写书评

暂无评论

Do your social profiles reveal what languages you speak? Language inference from social media profiles 38th

Do your social profiles reveal what languages you speak? Lan...

引用

38th European Conference on Information Retrieval Research, ECIR 2016

作者： Xu, Yu Ghorab, M. Rami Wang, Zhongqing Zhou, Dong Lawless, Séamus ADAPT Centre Knowledge and Data Engineering Group School of Computer Science and Statistics Trinity College Dublin Dublin Ireland Natural Language Processing Lab Soochow University Suzhou China School of Computer Science and Engineering Hunan University of Science and Technology Xiangtan China

ISBN: (纸本)9783319306704

In the multilingual World Wide Web, it is critical for Web applications, such as multilingual search engines and targeted international advertisements, to know what languages the user understands. However, online users are often unwilling to make the effort to explicitly provide this information. Additionally, language identification techniques struggle when a user does not use all the languages they know to directly interact with the applications. This work proposes a method of inferring the language(s) online users comprehend by analyzing their social profiles. It is mainly based on the intuition that a user’s experiences could imply what languages they know. This is nontrivial, however, as social profiles are usually incomplete, and the languages that are regionally related or similar in vocabulary may share common features;this makes the signals that help to infer language scarce and noisy. This work proposes a language and social relation-based factor graph model to address this problem. To overcome these challenges, it explores external resources to bring in more evidential signals, and exploits the dependency relations between languages as well as social relations between profiles in modeling the problem. Experiments in this work are conducted on a large-scale dataset. The results demonstrate the success of our proposed approach in language inference and show that the proposed framework outperforms several alternative methods. © Springer International Publishing Switzerland 2016.

关键词： Search engines

来源：评论

学校读者我要写书评

暂无评论

Strategy intervention for the evolution of fairness

arXiv

引用

arXiv 2017年

作者： Zhang, Yanling Fu, Feng Key Laboratory of Knowledge Automation for Industrial Processes of Ministry of Education School of Automation and Electrical Engineering University of Science and Technology Beijing Beijing China Department of Mathematics Dartmouth College HanoverNH United States Department of Biomedical Data Science Geisel School of Medicine Dartmouth College HanoverNH United States

Masses of experiments have shown individual preference for fairness which seems irrational. The reason behind it remains a focus for research. The effect of spite (individuals are only concerned with their own relative standing) on the evolution of fairness has attracted increasing attention from experiments, but only has been implicitly studied in one evolutionary model. The model did not involve high-offer rejections, which have been found in the form of non-monotonic rejections (rejecting offers that are too high or too low) in experiments. Here, we introduce a high offer and a non-monotonic rejection in structured populations of finite size, and use strategy intervention to explicitly study how spite influences the evolution of fairness: five strategies are in sequence added into the competition of a fair strategy and a selfish strategy. We find that spite promotes fairness, altruism inhibits fairness, and the non-monotonic rejection can cause fairness to overcome selfishness, which cannot happen without high-offer rejections. Particularly for the group-structured population with seven discrete strategies, we analytically study the effect of population size, mutation, and migration on fairness, selfishness, altruism, and spite. A larger population size cannot change the dominance of fairness, but it promotes altruism and inhibits selfishness and spite. Intermediate mutation maximizes selfishness and fairness, and minimizes spite;intermediate mutation maximizes altruism for intermediate migration and minimizes altruism otherwise. The existence of migration inhibits selfishness and fairness, and promotes altruism;sufficient migration promotes spite. Our study may provide important insights into the evolutionary origin of fairness. Copyright © 2017, The Authors. All rights reserved.

关键词： Population statistics

来源：评论

学校读者我要写书评

暂无评论

Security Analysis Model, System Architecture and Relational Model of Enterprise Cloud Services

引用

International Journal of Automation and computing 2016年第6期13卷 574-584页

作者： Dang-Dang Niu Lei Liu Xin Zhang Shuai Lu Zhuang Li College of Computer Science and Technology Jilin University Changchun 130012 China Data Center Consolidation (Beijing) Industrial and Commercial Bank of China Beijing 100096 China College of Mathematics Jilin University Changchun 130012 China Key Laboratory of Symbolic Computation and Knowledge Engineering Jilin University Changchun 130012 China

Cloud computing is one of the fastest growing and popular computer technologies, and there are more and more enterprise services based on the cloud computing. In order to save costs, more and more enterprises and their employees have hired the enterprise cloud services, and put much important information in the cloud gradually. Cloud service systems have become the main targets of malicious attacks. However, the cloud computing technologies are still not perfect, and the management and maintenance of enterprise cloud services are more complex compared to traditional network services of cloud computing. So, enterprise cloud services are more likely to encounter some security problems, and the influenced scale of these security problems is broad. But there are few researches on the security of enterprise cloud services. In this paper, we analyze the software as a service（Saa S） enterprise cloud services and introduce the research status of security problems in cloud computing environment. Combining with the analysis of the characteristics and application architecture of Saa S enterprise cloud services, we propose the security problems analysis model, the analysis system architecture and the relational model. Our researches can support further research of the automatic generation of solutions and guide the deployment of security policies of Saa S enterprise cloud services.

关键词： cloud deployment perfect maintenance likely users bases encounter relational costs

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：