检索结果-内蒙古大学图书馆

Disentangled features with direct sum decomposition for zero shot learning

NEUROCOMPUTING 2021年 426卷 216-226页

作者： Li, Bonan Han, Congying Guo, Tiande Zhao, Tong Univ Chinese Acad Sci Sch Math Sci 19A Yuquan Rd Beijing 100049 Peoples R China Chinese Acad Sci Key Lab Big Data Min & Knowledge Management 80 Zhonguancun East Rd Beijing 100190 Peoples R China

The core problem of zero-shot learning (ZSL) is extracting concise feature from cumbersome and intricate semantic space. While semantic vectors were mainly used to constrain the distance between different classes in embedding space in existing ZSL methods, we first emphasize the importance of the relationship between different dimensions in semantic space. In this paper, we propose a novel inductive approach, Multiple Semantic Subspaces Network (MSSN), to simplify the complex and intractable semantic features. Our method generates multiple disentangled subfeatures via direct sum decomposition, which not only retain completely semantic information, but also obtain simple independent hierarchical features. Specially, instead of original space, using projection subspace to map embedding space can reduce the difficulty of model optimization and enhance the generalization ability of the model. Full experiments are achieved on almost all datasets and comparision with many algorithms which exist in the present latest literature. Compared with nineteen competitors, the results show that our model outperforms the state-of-the-art on conventional ZSL setting and has a very competitive performance on generalized ZSL setting. (C) 2020 Elsevier B.V. All rights reserved.

关键词： Zero shot learning Subspace Direct sum decomposition 68T05

来源：评论

学校读者我要写书评

暂无评论

Can investor sentiment be used to predict the stock price? Dynamic analysis based on China stock market

引用

PHYSICA A-STATISTICAL MECHANICS AND ITS APPLICATIONS 2017年 469卷 390-396页

作者： Guo, Kun Sun, Yi Qian, Xin Chinese Acad Sci Res Ctr Fictitious Econ & Data Sci Beijing Peoples R China Univ Chinese Acad Sci Sch Econ & Management Beijing Peoples R China Chinese Acad Sci Key Lab Big Data Min & Knowledge Management Beijing Peoples R China Northeastern Univ Sch Business Adm Shenyang Peoples R China

With the development of the social network, the interaction between investors in stock market became more fast and convenient. Thus, investor sentiment which can influence their investment decisions may be quickly spread and magnified through the network, and to a certain extent the stock market can be affected. This paper collected the user comments data from a popular professional social networking site of China stock market called Xueqiu, then the investor sentiment data can be obtained through semantic analysis. The dynamic analysis on relationship between investor sentiment and stock market is proposed based on Thermal Optimal Path (TOP) method. The results show that the sentiment data was not always leading over stock market price, and it can be used to predict the stock price;only when the stock has high investor attention. (C) 2016 Elsevier B.V. All rights reserved.

关键词： Investor sentiment Thermal optimal path Stock market Dynamic analysis

来源：评论

学校读者我要写书评

暂无评论

A LOW-DIMENSIONAL SDP RELAXATION BASED SPATIAL BRANCH AND BOUND METHOD FOR NONCONVEX QUADRATIC PROGRAMS

引用

JOURNAL OF INDUSTRIAL AND management OPTIMIZATION 2020年第5期16卷 2087-2102页

作者： Zhou, Jing Deng, Zhibin Zhejiang Univ Technol Dept Appl Math Coll Sci Hangzhou 310032 Zhejiang Peoples R China Univ Chinese Acad Sci Sch Econ & Management Beijing 100190 Peoples R China Chinese Acad Sci Key Lab Big Data Min & Knowledge Management Beijing 100190 Peoples R China

In this paper, we propose a novel low-dimensional semidefinite programming (SDP) relaxation for convex quadratically constrained nonconvex quadratic programming problems. This new relaxation is derived by simultaneous matrix diagonalization method under the difference of convex decomposition scheme. The highlight of the relaxation is the low dimensionality of the positive semidefinite constraint, which only depends on the number of negative eigenvalues in the objective function. We prove that a mixed SOCP and SDP relaxation appeared in the literature is equivalent to the proposed relaxation, while the proposed relaxation has fewer constraints. We also provide conditions under which the proposed relaxation is as tight as the classical SDP relaxation and provides an optimal value for the original problem. For general cases, a spatial branch-and-bound algorithm is designed for finding a global optimal solution. Extensive numerical experiments support that the proposed algorithm outperforms two cutting-edge algorithms when the problem size is medium or large and the number of negative eigenvalues in the nonconvex objective function is relatively small.

关键词： Second order cone programming relaxation semidefinite programming relaxation nonconvex quadratic program branch-and-bound algorithm difference of convex decomposition

来源：评论

学校读者我要写书评

暂无评论

RLPS: A Reinforcement Learning-Based Framework for Personalized Search

引用

ACM TRANSACTIONS ON INFORMATION SYSTEMS 2021年第3期39卷 p1-29页

作者： Yao, Jing Dou, Zhicheng Xu, Jun Wen, Ji-Rong Renmin Univ China Sch Informat 59 Zhongguancun St Beijing 100872 Peoples R China Renmin Univ China Sch Artificial Intelligence 59 Zhongguancun St Beijing 100872 Peoples R China MOE Beijing Key Lab Big Data Management & Anal Method Key Lab Data Engn & Knowledge Engn 59 Zhongguancun St Beijing 100872 Peoples R China

Personalized search is a promising way to improve search qualities by taking user interests into consideration. Recently, machine learning and deep learning techniques have been successfully applied to search result personalization. Most existing models simply regard the personal search history as a static set of user behaviors and learn fixed ranking strategies based on all the recorded data. Though improvements have been achieved, the essence that the search process is a sequence of interactions between the search engine and user is ignored. The user's interests may dynamically change during the search process, therefore, it would be more helpful if a personalized search model could track the whole interaction process and adjust its ranking strategy continuously. In this article, we adapt reinforcement learning to personalized search and propose a framework, referred to as RLPS. It utilizes a Markov Decision Process (MDP) to track sequential interactions between the user and search engine, and continuously update the underlying personalized ranking model with the user's real-time feedback to learn the user's dynamic interests. Within this framework, we implement two models: the listwise RLPS-L and the hierarchical RLPS-H. RLPS-L interacts with users and trains the ranking model with document lists, while RLPS-H improves model training by designing a layered structure and introducing document pairs. In addition, we also design a feedback-aware personalized ranking component to capture the user's feedback, which impacts the user interest profile for the next query. Significant improvements over existing personalized search models are observed in the experiments on the public AOL search log and a commercial log.

关键词： Personalized search reinforcement learning Markov decision process (MDP)

来源：评论

学校读者我要写书评

暂无评论

A faster stochastic alternating direction method for large scale convex composite problems

引用

APPLIED INTELLIGENCE 2022年第12期52卷 14233-14245页

作者： Hu, Jia Guo, Tiande Zhao, Tong Univ Chinese Acad Sci Sch Math Sci 19A Yuquan Rd Beijing 100049 Peoples R China Chinese Acad Sci Key Lab Big Data Min & Knowledge Management 80 Zhonguancun East Rd Beijing 100190 Peoples R China

Inspired by the fact that certain randomization schemes incorporated into the stochastic (proximal) gradient methods allow for a large reduction in computational time, we incorporate such a scheme into stochastic alternating direction method of multipliers (ADMM), yielding a faster stochastic alternating direction method (FSADM) for solving a class of large scale convex composite problems. In the numerical experiments, we observe a reduction of this method in computational time compared to previous methods. More importantly, we unify the stochastic ADMM for solving general convex and strongly convex composite problems (i.e., the iterative scheme does not change when the the problem goes from strongly convex to general convex). In addition, we establish the convergence rates of FSADM for these two cases.

关键词： Alternating direction method of multipliers Convex composite optimization Stochastic approximation Variance reduction

来源：评论

学校读者我要写书评

暂无评论

Classifying With Adaptive Hyper-Spheres: An Incremental Classifier Based on Competitive Learning

引用

IEEE TRANSACTIONS ON SYSTEMS MAN CYBERNETICS-SYSTEMS 2020年第4期50卷 1218-1229页

作者： Li, Tie Kou, Gang Peng, Yi Shi, Yong Univ Elect Sci & Technol China Sch Management & Econ Chengdu 611731 Peoples R China Southwestern Univ Finance & Econ Sch Business Adm Chengdu 611130 Peoples R China Chinese Acad Sci Key Lab Big Data Min & Knowledge Management Beijing 100190 Peoples R China

Nowadays, datasets are always dynamic and patterns in them are changing. Instances with different labels are intertwined and often linearly inseparable, which bring new challenges to traditional learning algorithms. This paper proposes adaptive hyper-sphere (AdaHS), an adaptive incremental classifier, and its kernelized version: Nys-AdaHS. The classifier incorporates competitive training with a border zone. With adaptive hidden layer and tunable radii of hyper-spheres, AdaHS has strong capability of local learning like instance-based algorithms, but free from slow searching speed and excessive memory consumption. The experiments showed that AdaHS is robust, adaptive, and highly accurate. It is especially suitable for dynamic data in which patterns are changing, decision borders are complicated, and instances with the same label can be spherically clustered.

关键词： Kernel Heuristic algorithms Training data models Adaptation models Subspace constraints Neurons Adaptive algorithms Nystrom method pattern clustering self-organizing feature maps (SOFMs)

来源：评论

学校读者我要写书评

暂无评论

Research on knowledge Sharing and Transfer in Remanufacturing Engineering management Based on SECI Model

引用

Frontiers of Engineering management 2016年第2期3卷 136-143页

作者： Ling-ling Zhang Ming-hui Zhao Qiao Wang School of Economics and Management University of Chinese Academy of Sciences Key Laboratory of Big Data Mining and Knowledge Management Chinese Academy of Sciences

In this paper, an application mode and method of knowledge management in remanufacturing engineering management is established based on Nonaka's SECI model. The relationships between knowledge transfer,knowledge sharing and remanufacturing engineering management are highlighted. It is noticeable that a great deal of knowledge transfer and sharing activities, which can improve the performance of remanufacturing engineering management constantly, are involved in remanufacturing engineering.

关键词： remanufacturing engineering management knowledge transfer and sharing knowledge management

来源：评论

学校读者我要写书评

暂无评论

Attention Transfer Network for Nature Image Matting

引用

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY 2021年第6期31卷 2192-2205页

作者： Zhou, Fenfen Tian, Yingjie Qi, Zhiquan Univ Chinese Acad Sci Sch Comp Sci & Technol Beijing 100190 Peoples R China Chinese Acad Sci Res Ctr Fictitious Econ & Data Sci Beijing 100190 Peoples R China Chinese Acad Sci Key Lab Big Data Min & Knowledge Management Beijing 100190 Peoples R China

Natural image matting is an important problem that widely applied in computer vision and graphics. Recent deep learning matting approaches have made an impressive process in both accuracy and efficiency. However, there are still two fundamental problems remain largely unsolved: 1) accurately separating an object from the image with similar foreground and background color or lots of details;2) exactly extracting an object with fine structures from complex background. In this paper, we propose an attention transfer network (ATNet) to overcome these challenges. Specifically, we firstly design a feature attention block to effectively distinguish the foreground object from the color-similar regions by activating foreground-related features as well as suppressing others. Then, we introduce a scale transfer block to magnify the feature maps without adding extra information. By integrating the above blocks into an attention transfer module, we effectively reduce the artificial content in results and decrease the computational complexity. Besides, we use a perceptual loss to measure the difference between the feature representations of the predictions and the ground-truths. It can further capture the high-frequency details of the image, and consequently, optimize the fine structures of the object. Extensive experiments on two publicly common datasets (i.e., Composition-1k matting dataset, and *** dataset) show that the proposed ATNet obtains significant improvements over the previous methods. The source code and compiled models have been made publicly available at https://***/ailsaim/ATNet.

关键词： Image color analysis Semantics Loss measurement Task analysis Machine learning Feature extraction Computer vision Natural image matting feature attention scale transfer perceptual loss

来源：评论

学校读者我要写书评

暂无评论

Computing the intersections of three conics according to their Jacobian curve

引用

JOURNAL OF SYMBOLIC COMPUTATION 2016年 73卷 175-191页

作者： Feng, Ruyong Shen, Li-Yong Chinese Acad Sci AMSS Key Lab Math Mech Beijing 100864 Peoples R China Univ Chinese Acad Sci Sch Math Sci Beijing Peoples R China Chinese Acad Sci Key Lab Big Data Min & Knowledge Management Beijing 100864 Peoples R China

In this study, we describe the intersection of three conics based on the singularities of their corresponding Jacobian curve. In particular, we show that certain singular points and sub-lines of the Jacobian curve are the precise common points and common tangent lines of the conics, respectively. Based on our results, these points or the tangent line can be computed as the singularities of the Jacobian curve. These results facilitate investigations of the relationships between a net of conics and their Jacobian curve. (C) 2015 Elsevier Ltd. All rights reserved.

关键词： Algebraic condition Conic Intersection Jacobian curve Singularity

来源：评论

学校读者我要写书评

暂无评论

RPD-GAN: Learning to Draw Realistic Paintings With Generative Adversarial Network

引用

IEEE TRANSACTIONS ON IMAGE PROCESSING 2020年 29卷 8706-8720页

作者： Gao, Xiang Tian, Yingjie Qi, Zhiquan Univ Chinese Acad Sci Sch Comp Sci & Technol Beijing 100049 Peoples R China Chinese Acad Sci Res Ctr Fictitious Econ & Data Sci Beijing 100190 Peoples R China Chinese Acad Sci Key Lab Big Data Min & Knowledge Management Beijing 100190 Peoples R China

Painting style transfer is an attractive and challenging computer vision problem that aims to transfer painting styles onto natural images. Existing advanced methods tackle this problem from the perspective of Neural Style Transfer (NST) or unsupervised cross-domain image translation. For both two types of methods, attention has been focused on reproducing artistic painting styles of representative artists (e.g., Vincent Van Gogh). In this article, instead of transferring styles of artistic paintings, we focus on automatic generation of realistic paintings, for example, making the machine draw a gouache before a still life, paint a sketch of a landscape, or draw a pen-and-ink portrait of a person, etc. Besides capturing the precise target styles, synthesis of realistic paintings is more demanding in preserving original content features and image structures, for which existing advanced methods are not sufficient to generate satisfactory results. Aimed at this problem, we propose RPD-GAN (Realistic Painting Drawing Generative Adversarial Network), an unsupervised cross-domain image translation framework for realistic painting style transfer. At the heart of our model is the decomposition of the image stylization mapping into four stages: feature encoding, feature de-stylization, feature re-stylization, and feature decoding, where the functionalities of these stages are implemented by additionally embedding a content-consistency constraint and a style-alignment constraint at feature space to the classic CycleGAN architecture. By enforcing these constraints, both the content-preserving and style-capturing capabilities of the model are enhanced, leading to higher-quality stylization results. Extensive experiments demonstrate the effectiveness and superiority of our RPD-GAN in drawing realistic paintings.

关键词： Painting Gallium nitride Feature extraction Generative adversarial networks Task analysis Generators Semantics Style transfer generative adversarial networks image-to-image transformation

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：