检索结果-内蒙古大学图书馆

arXiv 2020年

作者： Mukherjee, Somabha Patra, Rohit K. Johnson, Andrew L. Morita, Hiroshi Department of Statistics and Data Science National University of Singapore Singapore Department of Statistics University of Florida United States Industrial and Systems Engineering Texas A&M University United States Graduate School of Information Science and Technology Osaka University Japan

We develop a new approach for the estimation of a multivariate function based on the economic axioms of quasiconvexity (and monotonicity). On the computational side, we prove the existence of the quasiconvex constrained least squares estimator (LSE) and provide a characterization of the function space to compute the LSE via a mixed integer quadratic programme. On the theoretical side, we provide finite sample risk bounds for the LSE via a sharp oracle inequality. Our results allow for errors to depend on the covariates and to have only two finite moments. We illustrate the superior performance of the LSE against some competing estimators via simulation. Finally, we use the LSE to estimate the production function for the Japanese plywood industry and the cost function for hospitals across the US. Copyright © 2020, The Authors. All rights reserved.

关键词： Cost functions

来源：评论

学校读者我要写书评

暂无评论

Learn to predict sets using feed-forward neural networks

arXiv

引用

arXiv 2020年

作者： Rezatofighi, Seyed Hamid Zhu, Alan Tianyu Kaskman, Roman Motlagh, Farbod T. Shi, Javen Qinfeng Milan, Anton Cremers, Daniel Leal-Taixé, Laura Reid, Ian The Department of Data Science and AI Faculty of Information Technology Monash University Melbourne Australia Department of Electrical and Computer Systems Engineering Monash University Melbourne Australia The School of Computer Science The university of Adelaide Australia Amazon Technical University of Munich Germany

This paper addresses the task of set prediction using deep feed-forward neural networks. A set is a collection of elements which is invariant under permutation and the size of a set is not fixed in advance. Many real-world problems, such as image tagging and object detection, have outputs that are naturally expressed as sets of entities. This creates a challenge for traditional deep neural networks which naturally deal with structured outputs such as vectors, matrices or tensors. We present a novel approach for learning to predict sets with unknown permutation and cardinality using deep neural networks. In our formulation we define a likelihood for a set distribution represented by a) two discrete distributions defining the set cardinally and permutation variables, and b) a joint distribution over set elements with a fixed cardinality. Depending on the problem under consideration, we define different training models for set prediction using deep neural networks. We demonstrate the validity of our set formulations on relevant vision problems such as: 1) multi-label image classification where we outperform the other competing methods on the PASCAL VOC and MS COCO datasets, 2) object detection, for which our formulation outperforms popular state-of-the-art detectors, and 3) a complex CAPTCHA test, where we observe that, surprisingly, our set-based network acquired the ability of mimicking arithmetics without any rules being coded. Copyright © 2020, The Authors. All rights reserved.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Impacts of preferences on the emergence of cooperation

引用

Physical Review E 2020年第5期102卷 052414-052414页

作者： Shiping Gao Jinming Du Jinling Liang School of Mathematics Southeast University Nanjing 210096 China Institute of Industrial and Systems Engineering College of Information Science and Engineering Northeastern University Shenyang 110891 China Liaoning Engineering Laboratory of Operations Analytics and Optimization for Smart Industry Northeastern University Shenyang 110891 China Key Laboratory of Data Analytics and Optimization for Smart Industry (Northeastern University) Ministry of Education Shenyang 110891 China

Behavior decision making, where individuals can efficiently express their preferences for all options, has a great impact on cooperation. Hereby, we institute a minimal model in well-mixed populations where whether and how to sanction defectors are decided by cooperators via different decision-making mechanisms. The results illustrate that whether cooperation can outbreak depends on the cooperators' preferences for sanction and complying with the electoral outcome. We highlight the role of individuals' preferences in the emergence of cooperation and show that there exists an intermediate degree of the cooperators' preference for sanction at which the cooperators' preference for complying with the electoral outcome has a negligible impact on cooperation. We point out whether conformity facilitates the emergence of cooperation depends on the cooperators' preference for sanction. We find, compared with individual decision making, whether collective decision making is more conducive to promoting cooperation crucially depends on cooperators' preferences as well as the consensus required for employing sanction.

关键词： Evolutionary dynamics Collective behavior Evolutionary games Fitness models Stochastic analysis

来源：评论

学校读者我要写书评

暂无评论

Evolution of cooperation under punishment

引用

Physical Review E 2020年第6期101卷 062419-062419页

Punishment has been considered as an effective mechanism for promoting and sustaining cooperation. In most existing models, punishment always comes as a third strategy alongside cooperation and defection, and it is commonly assumed to be executed based on individual decision rules rather than collective decision rules. Differently from previous works, we employ a democratic procedure by which cooperators cast votes independently and simultaneously for whether to impose punishment on defectors, and we establish a relationship between the cooperators' willingness to punish defectors (WTPD) and whether the punishment is inflicted on defectors. The results illustrate that the population can evolve to full cooperation under consensual punishment. It is noteworthy that, compared with autonomous punishment, whether consensual punishment is more in favor of cooperation crucially depends on the minimum number of votes required for punishment execution as well as the cooperators' WTPD. Our findings highlight the importance of collective decision making in the evolution of cooperation and may provide a mathematical framework for explaining the prevalence of democracy in modern societies.

关键词： Evolutionary dynamics

来源：评论

学校读者我要写书评

暂无评论

Triplet Deep Subspace Clustering via Self-Supervised data Augmentation

Triplet Deep Subspace Clustering via Self-Supervised Data Au...

引用

IEEE International Conference on data Mining (ICDM)

作者： Zhao Zhang Xianzhen Li Haijun Zhang Yi Yang Shuicheng Yan Meng Wang School of Computer Science and Information Engineering Hefei University of Technology Hefei China Key Laboratory of Knowledge Engineering with Big Data (Ministry of Education) & Intelligent Interconnected Systems Laboratory of Anhui Province Hefei University of Technology Hefei China School of Computer Science and Technology Soochow University Suzhou China Harbin Institute of Technology (Shenzhen) Shenzhen China Centre for Artificial Intelligence University of Technology Sydney Sydney NSW Australia Sea AI Lab (SAIL) & National University of Singapore Singapore

ISBN: (纸本)9781665423991

Deep subspace clustering (DSC) with the auto-encoder and self-expression layer is of great concern due to encouraging performance. However, existing methods usually adopt a “single-task” strategy based on a single dataset, without considering other related tasks or data. As such, they cannot discover other useful information to improve the clustering task. Besides, the local structure preservation of the latent codes in mapping is usually ignored. In this paper, we therefore present an effective “multi-task” strategy via the self-supervised data augmentation, and propose a new end-to-end trainable Triplet Deep Subspace Clustering Network (TDSC-net). Specifically, TDSC-net firstly generates triplet data (i.e., anchor, positive and negative data) from input data by a spectral clustering module and a self-supervised data augmentation module. This can enable it to inherit the merits of self-supervised learning and multitask learning implicitly. After that, TDSC-net builds a triplet deep autoencoder network with a self-expression layer, which takes the triplet data as input, where they share the common network layers (i.e., autoencoder and self-expression layers) over the triple tasks for complementary learning and mutual supervision. A triplet loss is also included to retain the local information of deep latent codes, which will also benefit the self-expression. Furthermore, TDSC-net separates the self-expression layer from decoding process to improve the efficiency of reconstruction. Extensive results on several public datasets demonstrate the effectiveness of our triplet-task DSC strategy.

关键词： Codes Conferences Multitasking Decoding data mining Task analysis

来源：评论

学校读者我要写书评

暂无评论

Designing optimal multiplex networks for certain Laplacian spectral properties

引用

Physical Review E 2020年第2期102卷 022302-022302页

作者： Heman Shakeri Ali Tavasoli Ehsan Ardjmand Pietro Poggi-Corradini School of Data Science University of Virginia Charlottesville Virginia 22904 USA Department of Mechanical Engineering Payame Noor University Tehran Iran Department of Analytics and Information Systems College of Business Ohio University Athens Ohio 45701 USA Mathematics Department Kansas State University Manhattan Kansas 66506 USA

We discuss the design of interlayer edges in a multiplex network, under a limited budget, with the goal of improving its overall performance. We analyze the following three problems separately; first, we maximize the smallest nonzero eigenvalue, also known as the algebraic connectivity; second, we minimize the largest eigenvalue, also known as the spectral radius; and finally, we minimize the spectral width. Maximizing the algebraic connectivity requires identical weights on the interlayer edges for budgets less than a threshold value. However, for larger budgets, the optimal weights are generally nonuniform. The dual formulation transforms the problem into a graph realization (embedding) problem that allows us to give a fuller picture. Namely, before the threshold budget, the optimal realization is one-dimensional with nodes in the same layer embedded to a single point, while beyond the threshold, the optimal embeddings generally unfold into spaces with dimension bounded by the multiplicity of the algebraic connectivity. Finally, for extremely large budgets the embeddings again revert to lower dimensions. Minimizing the largest eigenvalue is driven by the spectral radius of the individual networks and its corresponding eigenvector. Before a threshold, the total budget is distributed among interlayer edges corresponding to the nodal lines of this eigenvector, and the optimal largest eigenvalue of the Laplacian remains constant. For larger budgets, the weight distribution tends to be almost uniform. In the dual picture, the optimal graph embedding is one-dimensional and nonhomogeneous at first, with the nodes corresponding to the layer with the largest spectral radius distributed on a line according to its eigenvector, while the other layer is embedded at the origin. Beyond this threshold, the optimal embedding expands to be multidimensional, and for larger values of the budget, the two layers fill the embedding space. Finally, we show how these two problems are conn

关键词： Network diffusion Network formation & growth Network optimization Network structure Synchronization

来源：评论

学校读者我要写书评

暂无评论

Hyperspectral image classification using Uniform Manifold Approximation and Projection with fusion deep learning network

引用

Applied Soft Computing 2025年 180卷

作者： Chen Lou Mohammed A.A. Al-qaness Sike Ni Dalal Al-Alimi Robertas Damaševičius Saeed Hamood Alsamhi College of Physics and Electronic Information Engineering Zhejiang Normal University Jinhua 321004 China Zhejiang Institute of Photoelectronics Jinhua 321004 China Faculty of Engineering Sana’a University Sana’a 12544 Yemen Centre of Real Time Computer Systems Kaunas University of Technology Kaunas 51368 Lithuania Insight Centre for Data Analytics University of Galway Ireland School of ICT Bahrain Polytechnic Isa Town Bahrain Department of Computer Science and Engineering College of Informatics Korea University Seoul 02841 Republic of Korea

Hyperspectral images (HSI) are crucial for remote sensing applications as they provide detailed spectral information that accurately identifies and analyzes various materials and land features. HSI classification faces challenges due to large data volumes and high dimensionality. Dimensionality reduction techniques help address these problems by simplifying model computation, reducing redundancy, and improving feature selection. However, traditional methods struggle to capture nonlinear structures and local–global relationships in hyperspectral data. We propose a new multi-feature fusion classification model called the Uniform Manifold Approximation and Projection (UMAP) and Simple Attention Module (SimAM) mechanism fusion network (UMAPSAMFN). The main workflow of the model consists of several steps. The network uses UMAP to map high-dimensional HSI data into a low-dimensional space while maintaining a local and global structure. The feature data are sent to the convolutional neural network (CNN) and graph convolutional network (GCN) modules to capture pixel-level features and contextual information. These data are separately processed through multi-head attention modules to enhance the ability to represent feature information. Finally, the processed data are jointly fed into a fusion module with an attention mechanism to boost feature information and achieve deep modeling results. The experimental results on three benchmark HSI datasets show that UMAPSAMFN consistently exhibits the highest classification accuracy, with overall classification accuracies of 93.28%, 96.13%, and 97.73% on the Indian Pines, Pavia University, and Salinas datasets, respectively.

关键词：

来源：评论

学校读者我要写书评

暂无评论

On values of the higher derivatives of the Barnes zeta function at non-positive integers

arXiv

引用

arXiv 2020年

作者： Sakane, Shinpei Aoki, Miho Department of Information Systems Design and Data Science Graduate School of Natural Science and Technology Shimane University 1060 Nishikawatsu Matsue Shimane690-8504 Japan Department of Mathematics Interdisciplinary Faculty of Science and Engineering Shimane University 1060 Nishikawatsu Matsue Shimane690-8504 Japan

Let x be a complex number which has a positive real part, and w1, . . ., wN be positive rational numbers. We show that wsζN (s, x | w1, . . ., wN) can be expressed as a finite linear combination of the Hurwitz zeta functions over Q(x), where ζN (s, x | w1, . . ., wN) is the Barnes zeta function and w is a positive rational number explicitly determined by w1, . . ., wN . Furthermore, we give generalizations of Kummer’s formula on the gamma function and Koyama-Kurokawa’s formulae on the multiple gamma functions, and an explicit formula for the values at non-positive integers for higher order derivatives of the Barnes zeta function in the case that x is a positive rational number, involving the generalized Stieltjes constants and the values at positive integers of the Riemann zeta function. Our formulae also makes it possible to calculate an approximation in the case that w1, . . ., wN and x are positive real *** Codes 11M41, 11M06, 11M35, 33B15 Copyright © 2020, The Authors. All rights reserved.

关键词： Rational functions

来源：评论

学校读者我要写书评

暂无评论

A unified adaptive recoding framework for Batched network coding

arXiv

引用

arXiv 2021年

作者： Yin, Hoover H.F. Tang, Bin Ng, Ka Hei Yang, Shenghao Wang, Xishi Zhou, Qiaoqiao The N-hop Technologies Limited Hong Kong The Institute of Network Coding The Chinese University of Hong Kong Hong Kong The School of Computer and Information Hohai University Nanjing China The Department of Physics The Chinese University of Hong Kong Hong Kong The School of Science and Engineering The Chinese University of Hong Kong Shenzhen China Shenzhen Key Laboratory of IoT Intelligent Systems and Wireless Network Technology Shenzhen Research Institute of Big Data Shenzhen China The Department of Information Engineering The Chinese University of Hong Kong Hong Kong

Batched network coding is a variation of random linear network coding which has low computational and storage costs. In order to adapt to random fluctuations in the number of erasures in individual batches, it is not optimal to recode and transmit the same number of packets for all batches. Different distributed optimization models, which are called adaptive recoding schemes, were formulated for this purpose. The key component of these optimization problems is the expected value of the rank distribution of a batch at the next network node, which is also known as the expected rank. In this paper, we put forth a unified adaptive recoding framework with an arbitrary recoding field size. We show that the expected rank functions are concave when the packet loss pattern is a stationary stochastic process, which covers but not limited to independent packet loss and Gilbert-Elliott packet loss model. Under this concavity assumption, we show that there always exists a solution which not only can minimize the randomness on the number of recoded packets but also can tolerate rank distribution errors due to inaccurate measurements or limited precision of the machine. We provide an algorithm to obtain such an optimal optimal solution, and propose tuning schemes that can turn any feasible solution into a desired optimal solution. © 2021, CC BY-NC-ND.

关键词： Packet loss

来源：评论

学校读者我要写书评

暂无评论

Dictionary Pair-based data-Free Fast Deep Neural Network Compression

Dictionary Pair-based Data-Free Fast Deep Neural Network Com...

引用

IEEE International Conference on data Mining (ICDM)

作者： Yangcheng Gao Zhao Zhang Haijun Zhang Mingbo Zhao Yi Yang Meng Wang School of Computer Science and Information Engineering Hefei University of Technology Hefei China Key Laboratory of Knowledge Engineering with Big Data (Ministry of Education) & Intelligent Interconnected Systems Laboratory of Anhui Province Hefei University of Technology Hefei China Harbin Institute of Technology (Shenzhen) Xili University Town Shenzhen China City University of Hong Kong Hong Kong SAR Centre for Artificial Intelligence University of Technology Sydney Sydney NSW Australia

ISBN: (纸本)9781665423991

Deep neural network (DNN) compression can reduce the memory footprint of deep networks effectively, so that the deep model can be deployed on the portable devices. However, most of the existing model compression methods cost lots of time, e.g., vector quantization or pruning, which makes them inept to the real-world applications that need fast online computation. In this paper, we therefore explore how to accelerate the model compression process by reducing the computation cost. Then, we propose a new deep model compression method, termed Dictionary Pair-based data-Free Fast DNN Compression, which aims at reducing the memory consumption of DNNs without extra training and can greatly improve the compression efficiency. Specifically, our proposed method performs tensor decomposition on the DNN model with a fast dictionary pair learning-based reconstruction approach, which can be deployed on different layers (e.g., convolution and fully-connection layers). Given a pre-trained DNN model, we first divide the parameters (i.e., weights) of each layer into a series of partitions for dictionary pair-based fast reconstruction, which can potentially discover more fine-grained information and provide the possibility for parallel model compression. Then, dictionaries of less memory occupation are learned to reconstruct the weights. Extensive experiments on popular DNNs (i.e., VGG-16, ResNet-18 and ResNet-50) showed that our proposed weight compression method can significantly reduce the memory footprint and speed up the compression process, with less performance loss.

关键词： Deep learning Training Performance evaluation Dictionaries Tensors Costs Computational modeling

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：