检索结果-内蒙古大学图书馆

arXiv 2019年

作者： Zhang, Si-Ping Zhang, Ji-Qiang Chen, Li Liu, Xu-Dong Key Laboratory of Biomedical Information Engineering Ministry of Education Key Laboratory of Neuro-informatics & Rehabilitation Engineering Ministry of Civil Affairs Institute of Health and Rehabilitation Science School of Life Science and Technology Xi'an Jiaotong University Xi'an710049 China Beijing Advanced Innovation Center for Big Data and Brain Computing Beihang University Beijing100191 China School of Physics and Information Technology Shaanxi Normal University Xi'an710062 China

Large-scale cooperation underpins the evolution of ecosystems and the human society, and the collective behaviors by self-organization of multi-agent systems are the key for understanding. As artificial intelligence (AI) prevails in almost all branches of science, it would be of great interest to see what new insights of collective behavior could be obtained from a multi-agent AI system. Here, we introduce a typical reinforcement learning (RL) algorithm - Q learning into evolutionary game dynamics, where agents pursue optimal action on the basis of the introspectiveness rather than the birth-death or imitation processes in the traditional evolutionary game (EG). We investigate the cooperation prevalence numerically for a general 2 × 2 game setting. We find that the cooperation prevalence in the multi-agent AI is amazingly of equal level as in the traditional EG in most cases. However, in the snowdrift games with RL we also reveal that explosive cooperation appears in the form of periodic oscillation, and we study the impact of the payoff structure on its emergence. Finally, we show that the periodic oscillation can also be observed in some other EGs with the RL algorithm, such as the rock-paper-scissors game. Our results offer a reference point to understand emergence of cooperation and oscillatory behaviors in nature and society from AI's perspective. Copyright © 2019, The Authors. All rights reserved.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Anomaly Prediction in Passenger Flow with Knowledge Transfer Method

Anomaly Prediction in Passenger Flow with Knowledge Transfer...

引用

IEEE International Symposium on Dependable, Autonomic and Secure computing (DASC)

作者： Zhipu Xie Weifeng Lv Syed Muhammad Asim Ali Bowen Du Runhe Huang Key State Laboratory of Software Development Environment Beihang University Beijing China Beijing Advanced Innovation Center for Big Data and Brain Computing Beihang University Beijing Hosei University Tokyo Japan

ISBN: (纸本)9781538675199

Predicting anomaly in travel demand is a crucial finding from smart card data analytics. The output of these predictions is a significant contribution to planning sustainable public transport system and generating possible knowledge for transportation learning models. This paper investigates the anomaly effects of the surge in bus passengers demand and compare it with an increase in taxi demand. Indeed, both short-term and long-term demands reveal different patterns of passengers in uncertain situations. In pursuit of our goal, we estimated the similarity in stations by both selected and latent features where pre-trained knowledge are combined as an ensemble with different weights. We present Surge Prediction and Knowledge Transfer (SPKT) model that uses Seq2Seq method combined with Multi-source Transfer Learning method on travel patterns extracted from smart card data to classify source stations and target station. To illustrate the demands blueprint, we considered multiple source stations as input to the predictor, to develop a mechanism that bridges the knowledge transfer learning with the targeted stations. To exemplify our method, we use a case study of an event with passenger surge. From experiments, we found that transferring knowledge can make the surge prediction better compared to only limited training data for the target stations. The results have proved the effectiveness of surge predictions and knowledge transfer for learning models.

关键词： Surges Knowledge transfer Predictive models Public transportation Feature extraction Real-time systems

来源：评论

学校读者我要写书评

暂无评论

Dynamic network embedding via incremental skip-gram with negative sampling

arXiv

引用

arXiv 2019年

作者： Peng, Hao Li, Jianxin Yan, Hao Gong, Qiran Wang, Senzhang Liu, Lin Wang, Lihong Ren, Xiang Beijing Advanced Innovation Center for Big Data and Brain Computing Beihang University Beijing China State Key Laboratory of Software Development Environment Beihang University Beijing China Collage of Computer Science and Technology Nanjing University of Aeronautics and Astronautics Nanjing China National Computer Network Emergency Response Technical Team Coordination Center of China Beijing China Department of Computer Science University of Southern California Los Angeles United States

Network representation learning, as an approach to learn low dimensional representations of vertices, has attracted considerable research attention recently. It has been proven extremely useful in many machine learning tasks over large graph. Most existing methods focus on learning the structural representations of vertices in a static network, but cannot guarantee an accurate and efficient embedding in a dynamic network scenario. The fundamental problem of continuously capturing the dynamic properties in an efficient way for a dynamic network remains unsolved. To address this issue, we present an efficient incremental skip-gram algorithm with negative sampling for dynamic network embedding, and provide a set of theoretical analyses to characterize the performance guarantee. Specifically, we first partition a dynamic network into the updated, including addition/deletion of links and vertices, and the retained networks over time. Then we factorize the objective function of network embedding into the added, vanished and retained parts of the network. Next we provide a new stochastic gradient-based method, guided by the partitions of the network, to update the nodes and the parameter vectors. The proposed algorithm is proven to yield an objective function value with a bounded difference to that of the original objective function. The first order moment of the objective difference converges in order of O( 1/n2 ), and the second order moment of the objective difference can be stabilized in order of O(1). Experimental results show that our proposal can significantly reduce the training time while preserving the comparable performance. We also demonstrate the correctness of the theoretical analysis and the practical usefulness of the dynamic network embedding. We perform extensive experiments on multiple real-world large network datasets over multi-label classification and link prediction tasks to evaluate the effectiveness and efficiency of the proposed framework, and up

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

Escaping from a degenerate version of the four hill potential

arXiv

引用

arXiv 2019年

作者： Zotosa, Euaggelos E. Chen, Wei Jung, Christof Department of Physics School of Science Aristotle University of Thessaloniki ThessalonikiGR-541 24 Greece Beijing Advanced Innovation Center for Big Data and Brain Computing Beihang University Beijing100191 China LMIB & School of Mathematics and Systems Science Beihang University Beijing100191 China Instituto de Ciencias Físicas Universidad Nacional Autónoma de México Av. Universidad s/n Cuernavaca62251 Mexico

We examine the escape from the four hill potential by using the method of grid classification, when polar coordinates are used for expressing the initial conditions of the orbits. In particular, we investigate how the energy of the orbits influences several aspects of the escape dynamics, such as the escape period and the chosen channels of escape. Color-coded basin diagrams are deployed for presenting the basins of escape using multiple types of planes with two dimensions. We demonstrate that the value of the energy highly influences the escape mechanism of the orbits, as well as the degree of fractality of the dynamical system, which is numerically estimated by computing both the fractal dimension and the entropy of the basin boundaries. Copyright © 2019, The Authors. All rights reserved.

关键词： Fractal dimension

来源：评论

学校读者我要写书评

暂无评论

Detecting Systemically Important Platforms in P2P Market of China

Detecting Systemically Important Platforms in P2P Market of ...

引用

International Conference on Services Systems and Services Management, ICSSSM

作者： Shan Lu Xiaolei Xu Huiwen Wang Jichang Zhao Zhen Wu School of Economics and Management Beihang University Beijing China National Computer network Coordination Center of China Beijing China Beijing Advanced Innovation Center for Big Data and Brain Computing Beihang University Beijing China

Fueled by advances in technology and shifts in generational values, the market of online peer-to-peer (P2P) platforms is growing prosperously in China. While the development of this rapidly-evolving industry has stimulated the financial market where traditional banks could not reach, collapses of well-known platforms due to malpractice, fraud or business failure are raising great concerns about systemic risk, as troubles of systemically important platforms may trigger wide range of failures because of the network of financial exposures among the industry. However, the network of Chinese P2P lending platforms remains unknown. To fill this vital gap, we performed the first complex network analysis of the Chinese P2P lending platforms using empirical platform-level data. The network analysis enables us to detect the systematically important platforms, through the static importance indicators as well as cascading scheme. A further grouping analysis presents the different characteristic of the platform with different importance levels, which in turn proves the network modeling is able to function effectively in detectina the systemic important platforms.

关键词： Internet Peer-to-peer computing Industries Companies Economic indicators

来源：评论

学校读者我要写书评

暂无评论

Angular triplet-center loss for multi-view 3D shape retrieval

arXiv

引用

arXiv 2018年

作者： Li, Zhaoqun Xu, Cheng Leng, Biao School of Computer Science and Engineering Beihang University Beijing100191 Research Institute of Beihang University in Shenzhen Shenzhen518057 Beijing Advanced Innovation Center for Big Data and Brain Computing Beihang University Beijing100191

How to obtain the desirable representation of a 3D shape, which is discriminative across categories and polymerized within classes, is a significant challenge in 3D shape retrieval. Most existing 3D shape retrieval methods focus on capturing strong discriminative shape representation with softmax loss for the classification task, while the shape feature learning with metric loss is neglected for 3D shape retrieval. In this paper, we address this problem based on the intuition that the cosine distance of shape embeddings should be close enough within the same class and far away across categories. Since most of 3D shape retrieval tasks use cosine distance of shape features for measuring shape similarity, we propose a novel metric loss named angular triplet-center loss, which directly optimizes the cosine distances between the features. It inherits the triplet-center loss property to achieve larger inter-class distance and smaller intra-class distance simultaneously. Unlike previous metric loss utilized in 3D shape retrieval methods, where Euclidean distance is adopted and the margin design is difficult, the proposed method is more convenient to train feature embeddings and more suitable for 3D shape retrieval. Moreover, the angle margin is adopted to replace the cosine margin in order to provide more explicit discriminative constraints on an embedding space. Extensive experimental results on two popular 3D object retrieval benchmarks, ModelNet40 and ShapeNetCore 55, demonstrate the effectiveness of our proposed loss, and our method has achieved state-of-the-art results on various 3D shape datasets. Copyright © 2018, The Authors. All rights reserved.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

Reliable Shortest Path Guidance in Stochastic Road Networks Using Convolution-Based Path Finding Algorithm 18

Reliable Shortest Path Guidance in Stochastic Road Networks ...

引用

18th COTA International Conference of Transportation Professionals: Intelligence, Connectivity, and Mobility, CICTP 2018

作者： Chen, Peng Tong, Rui Lu, Guangquan Wang, Yunpeng Beijing Key Laboratory for Cooperative Vehicle Infrastructure Systems and Safety Control School of Transportation Science and Engineering Beihang Univ. Xue Yuan Rd. No. 37 Hai Dian District Beijing100191 China Beijing Advanced Innovation Center for Big Data and Brain Computing Beihang Univ. Xue Yuan Rd. No. 37 Hai Dian District Beijing100191 China

ISBN: (数字)9780784481523

ISBN: (纸本)9780784481523

Most existing research on routing guidance only pays attention to the average value of path travel time, which fails to consider travel time variability (TTV) and travel time reliability preferences by different travelers. In this study, a convolution-based modified genetic algorithm (CMGA) is proposed to find the reliable shortest path in stochastic road networks. By accounting for traveler risk tolerance, the algorithm enables the provision of personalized routing guidance for individual travelers. To support online applications in a large-scale network, reasonable heuristic constraints are imposed to help reduce the computational workload and accelerate the convergence speed of the search process. Numerical case studies based on a grid network with random offsets are provided, and the results help verify that the algorithm has the potential to solve reliable shortest path searching problems in a large-scale network with desirable efficiency. © 2018 American Society of Civil Engineers.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Graphical representation and hierarchical decomposition mechanism for vertex-cover solution space

arXiv

引用

arXiv 2019年

作者： Wei, Wei Feng, Xiangnan Wang, Jiannan Liu, Xue Zheng, Zhiming School of Mathematical Sciences Beihang University Beijing100191 China Key Laboratory of Mathematics Informatics and Behavioral Semantics Ministry of Education 100191 China Research Institute of Frontier Science Beihang University Beijing100191 China Beijing Advanced Innovation Center for Big Data and Brain Computing Beihang University Beijing100191 China Peng Cheng Laboratory Guangdong Shenzhen518055 China Center for Humans and Machines Max Planck Institute for Human Development Berlin14195 Germany

In this paper, solution space organization of minimum vertex-cover problem is deeply investigated using the König-Egérvary (KE) graph and theorem, in which a hierarchical decomposition mechanism named KE-layer structure of general graphs is proposed to reveal the complexity of vertex-cover. An algorithm to verify the KE graph is given by the solution space expression of vertex-cover, and the relation between multi-layer KE graphs and maximal matching is illustrated and proved. Furthermore, a framework to calculate the KE-layer number and approximate the minimal vertex-cover is provided, with different strategies of switching nodes and counting energy. The phase transition phenomenon between different KE-layers are studied with the transition points located, and searching of vertex-cover got by this strategy presents comparable advantage against several other methods. The graphical representation and hierarchical decomposition provide a new perspective to illustrate the intrinsic complexity for large-scale graphs/systems recognition. Copyright © 2019, The Authors. All rights reserved.

关键词： Graphic methods

来源：评论

学校读者我要写书评

暂无评论

The power of trading polarity: Evidence from China stock market crash

arXiv

引用

arXiv 2018年

作者： Lu, Shan Zhao, Jichang Wang, Huiwen School of Economics and Management Beihang University Beijing China Beijing Key Laboratory of Emergency Support Simulation Technologies for City Operations Beijing China Beijing Advanced Innovation Center for Big Data and Brain Computing Beijing China

The imbalance of buying and selling functions profoundly in the formation of market trends, however, a fine-granularity investigation of the imbalance is still missing. This paper investigates a unique transaction dataset that enables us to inspect the imbalance of buying and selling on the man-times level at high frequency, what we call 'trading polarity', for a large cross-section of stocks from Shenzhen Stock Exchange. The trading polarity measures the market sentiment toward stocks from a view of very essence of trading desire. When using the polarity to examine market crash, we find that trading polarity successfully reects the changing of market-level behavior in terms of its ipping times, depth, and length. We further investigate the relationship between polarity and return. At market-level, trading polarity is negatively correlated with returns, while at stock-level, this correlation changes according to market conditions, which becomes a good signal of market psychology transition. Also, the significant correlation disclosed by the market polarity and market emotion implies that our presented polarity, which essentially calculated in the context of high-frequency trading data, can real-timely reect the sentiment of the market. The trading polarity indeed provides a new way to understand and foresee the market behavior. Copyright © 2018, The Authors. All rights reserved.

关键词： Large dataset

来源：评论

学校读者我要写书评

暂无评论

Triangular architecture for rare language translation

arXiv

引用

arXiv 2018年

作者： Ren, Shuo Chen, Wenhu Liu, Shujie Li, Mu Zhou, Ming Ma, Shuai SKLSDE Lab Beihang University Beijing China Beijing Advanced Innovation Center for Big Data and Brain Computing Beijing China University of California Santa BarbaraCA United States Microsoft Research in Asia Beijing China

Neural Machine Translation (NMT) performs poor on the low-resource language pair (X;Z), especially when Z is a rare language. By introducing another rich language Y , we propose a novel triangular training architecture (TA-NMT) to leverage bilingual data (Y;Z) (may be small) and (X;Y ) (can be rich) to improve the translation performance of lowresource pairs. In this triangular architecture, Z is taken as the intermediate latent variable, and translation models of Z are jointly optimized with a unified bidirectional EM algorithm under the goal of maximizing the translation likelihood of (X;Y ). Empirical results demonstrate that our method significantly improves the translation quality of rare languages on MultiUN and IWSLT2012 datasets, and achieves even better performance combining back-translation methods. Copyright © 2018, The Authors. All rights reserved.

关键词： Neural machine translation

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：