检索结果-内蒙古大学图书馆

arXiv 2018年

作者： Liu, Fanghui Huang, Xiaolin Gong, Chen Yang, Jie Li, Li Institute of Image Processing and Pattern Recognition Shanghai Jiao Tong University Shanghai200240 China Key Laboratory of Intelligent Perception and Systems for High-Dimensional Information Ministry of Education School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing210094 China Department of Automation Tsinghua University

Kernel methods have been extensively used in a variety of machine learning tasks such as classification, clustering, and dimensionality reduction. For complicated practical tasks, the traditional kernels, e.g., Gaussian kernel and sigmoid kernel, or their combinations are often not sufficiently flexible to fit the data. In this paper, we present a Data-Adaptive Nonparametric Kernel (DANK) learning framework in a data-driven manner. To be specific, in model formulation, we impose an adaptive matrix on the kernel/Gram matrix in an entry-wise strategy. Since we do not specify the formulation of the adaptive matrix, each entry in the adaptive matrix can be directly and flexibly learned from the data. Therefore, the solution space of the learned kernel is largely expanded, which makes our DANK model flexible to capture the data with different local statistical properties. Specifically, the proposed kernel learning framework can be seamlessly embedded to support vector machines (SVM) and support vector regression (SVR), which has the capability of enlarging the margin between classes and reducing the model generalization error. Theoretically, we demonstrate that the objective function of our DANK model embedded in SVM/SVR is gradient-Lipschitz continuous. Thereby, the training process for kernel and parameter learning in SVM/SVR can be efficiently optimized in a unified framework. Further, to address the scalability issue in nonparametric kernel learning framework, we decompose the entire optimization problem in DANK into several smaller easy-to-solve problems, so that our DANK model can be efficiently approximated by this partition. The effectiveness of this approximation is demonstrated by both empirical studies and theoretical guarantees. Experimentally, the proposed DANK model embedded in SVM/SVR achieves encouraging performance on various classification and regression benchmark datasets when compared with other representative kernel learning based algorithms. Copyrig

关键词： Matrix algebra

来源：评论

学校读者我要写书评

暂无评论

Hierarchical P systems with randomized right-hand sides of rules 18th

Hierarchical P systems with randomized right-hand sides of r...

引用

18th International Conference on Membrane Computing, CMC 1018

作者： Alhazov, Artiom Freund, Rudolf Ivanov, Sergiu Institute of Mathematics and Computer Science Academy of Sciences of Moldova Academiei 5 Chişinău2028 Moldova Key Laboratory of Image Information Processing and Intelligent Control of Education Ministry of China School of Automation Huazhong University of Science and Technology Wuhan430074 China Faculty of Informatics TU Wien Favoritenstraße 9–11 Vienna1040 Austria LACL Université Paris Est – Créteil Val de Marne 61 av. Général de Gaulle Créteil94010 France TIMC-IMAG/DyCTiM Faculty of Medicine of Grenoble 5 avenue du Grand Sablon La Tronche38700 France

ISBN: (纸本)9783319733586

P systems are a model of hierarchically compartmentalized multiset rewriting. We introduce a novel kind of P systems in which rules are dynamically constructed in each step by non-deterministic pairing of left-hand and right-hand sides. We define three variants of right-hand side randomization and compare each of them with the power of conventional P systems. It turns out that all three variants enable non-cooperative P systems to generate exponential (and thus non-semi-linear) number languages. We also give a binary normal form for one of the variants of P systems with randomized rule right-hand sides. © 2018, Springer International Publishing AG.

关键词： Hierarchical systems

来源：评论

学校读者我要写书评

暂无评论

Machine discovery of partial differential equations from spatiotemporal data

arXiv

引用

arXiv 2019年

作者： Yuan, Ye Li, Junlin Li, Liang Jiang, Frank Tang, Xiuchuan Zhang, Fumin Liu, Sheng Goncalves, Jorge Voss, Henning U. Li, Xiuting Kurths, Jürgen Ding, Han School of Artificial Intelligence and Automation State Key Laboratory of Digital Manufacturing Equipments and Technology Huazhong University of Science and Technology Wuhan430074 China School of Artificial Intelligence and Automation Key Laboratory of Image Processing and Intelligent Control Huazhong University of Science and Technology Wuhan430074 China School of Electrical Engineering and Computer Science KTH Royal Institute of Technology Stockholm11428 Sweden School of Mechanical Science and Engineering Huazhong University of Science and Technology Wuhan430074 China School of Electrical and Computer Engineering Georgia Institute of Technology Atlanta30332 United States School of Power and Mechanical Engineering Wuhan University Wuhan430074 China Department of Engineering University of Cambridge CambridgeCB2 1PZ United Kingdom Luxembourg Centre for Systems Biomedicine University of Luxembourg BelvauxL-4367 Luxembourg Citigroup Biomedical Imaging Center Weill Cornell Medical College New York10021 United States Research Domain IV - Transdisciplinary Concepts & Methods Potsdam Institute for Climate Impact Research Potsdam14473 Germany School of Mechanical Science and Engineering State Key Laboratory of Digital Manufacturing Equipments and Technology Huazhong University of Science and Technology Wuhan430074 China

The study presents a general framework for discovering underlying Partial Differential Equations (PDEs) using measured spatiotemporal data. The method, called Sparse Spatiotemporal System Discovery (S3d), decides which physical terms are necessary and which can be removed (because they are physically negligible in the sense that they do not affect the dynamics too much) from a pool of candidate functions. The method is built on the recent development of Sparse Bayesian Learning;which enforces the sparsity in the to-be-identified PDEs, and therefore can balance the model complexity and fitting error with theoretical guarantees. Without leveraging prior knowledge or assumptions in the discovery process, we use an automated approach to discover ten types of PDEs, including the famous Navier-Stokes and sine-Gordon equations, from simulation data alone. Moreover, we demonstrate our data-driven discovery process with the Complex Ginzburg-Landau Equation (CGLE) using data measured from a traveling-wave convection experiment. Our machine discovery approach presents solutions that has the potential to inspire, support and assist physicists for the establishment of physical laws from measured spatiotemporal data, especially in notorious fields that are often too complex to allow a straightforward establishment of physical law, such as biophysics, fluid dynamics, neuroscience or nonlinear optics. Copyright © 2019, The Authors. All rights reserved.

关键词： Nonlinear optics

来源：评论

学校读者我要写书评

暂无评论

Predicting essential proteins based on gene expression data, subcellular localization and PPI data 1

引用

12th International Conference on Bio-Inspired Computing: Theories and Applications, BIC-TA 2017

作者： Lei, Xiujuan Wang, Siguo Pan, Linqiang School of Computer Science Shaanxi Normal University Xi’anShaanxi710119 China Key Laboratory of Image Information Processing and Intelligent Control School of Automation Huazhong University of Science and Technology WuhanHubei430074 China School of Electric and Information Engineering Zhengzhou University of Light Industry ZhengzhouHenan450002 China

ISBN: (数字)9789811071799

ISBN: (纸本)9789811071782

Predicting essential proteins is indispensable for understanding the minimal requirements of cellular survival and development. In recent years, many methods combined with the topological features of PPI networks have been proposed. However, most of these approaches ignored the intrinsic characteristics of biological attributes. This paper integrates Gene expression data, Subcellular localization and PPI networks to identify essential proteins, named GSP. We use local average connectivity and edge clustering coefficient unite with gene expression data to measure centralities of nodes. Compared with non-essential proteins, essential proteins appear more frequently in some subcellular localizations such as Nucleus and considering that different compartments play different roles, thus we integrate subcellular localization information to identify essential proteins. The computational experiment results on the yeast PPI networks show that the proposed method GSP outperforms other state-of-art methods including DC, EC, IC, SC, NC, LAC, PeC, WDC and UDoNC. © Springer Nature Singapore Pte Ltd 2017.

关键词： Proteins

来源：评论

学校读者我要写书评

暂无评论

Coarse-to-Fine Learning for Single-image Super-Resolution

引用

IEEE Transactions on Neural Networks and Learning Systems 2017年第5期28卷 1109-1122页

作者： Zhang, Kaibing Tao, Dacheng Gao, Xinbo Li, Xuelong Li, Jie School of Computer and Information Science Hubei Engineering University Xiaogan Hubei432000 China Centre for Quantum Computation and Intelligent Systems Faculty of Engineering and Information Technology University of Technology Sydney 81 Broadway Street UltimoNSW2007 Australia State Key Laboratory of Integrated Services Networks School of Electronic Engineering Xidian University Xi'an Shaanxi710071 China State Key Laboratory of Transient Optics and Photonics Xi'An Institute of Optics and Precision Mechanics Chinese Academy of Sciences Xi'an Shaanxi710119 China Video and Image Processing System Laboratory School of Electronic Engineering Xidian University Xi'an Shaanxi710071 China

This paper develops a coarse-to-fine framework for single-image super-resolution (SR) reconstruction. The coarse-to-fine approach achieves high-quality SR recovery based on the complementary properties of both example learning-and reconstruction-based algorithms: example learning-based SR approaches are useful for generating plausible details from external exemplars but poor at suppressing aliasing artifacts, while reconstruction-based SR methods are propitious for preserving sharp edges yet fail to generate fine details. In the coarse stage of the method, we use a set of simple yet effective mapping functions, learned via correlative neighbor regression of grouped low-resolution (LR) to high-resolution (HR) dictionary atoms, to synthesize an initial SR estimate with particularly low computational cost. In the fine stage, we devise an effective regularization term that seamlessly integrates the properties of local structural regularity, nonlocal self-similarity, and collaborative representation over relevant atoms in a learned HR dictionary, to further improve the visual quality of the initial SR estimation obtained in the coarse stage. The experimental results indicate that our method outperforms other state-of-the-art methods for producing high-quality images despite that both the initial SR estimation and the followed enhancement are cheap to implement. © 2012 IEEE.

关键词： Optical resolving power

来源：评论

学校读者我要写书评

暂无评论

Complete stability of delayed recurrent neural networks with Gaussian activation functions

引用

Neural networks : the official journal of the International Neural Network Society 2017年 85卷 21-32页

作者： Peng Liu Zhigang Zeng Jun Wang School of Automation Huazhong University of Science and Technology Wuhan 430074 China Key Laboratory of Image Processing and Intelligent Control of Education Ministry of China Wuhan 430074 China. Electronic address: liupengjz@***. Key Laboratory of Image Processing and Intelligent Control of Education Ministry of China Wuhan 430074 China. Electronic address: zgzeng@***. Department of Computer Science City University of Hong Kong Kowloon Tong Hong Kong. Electronic address: jwang.cs@cityu.edu.hk.

This paper addresses the complete stability of delayed recurrent neural networks with Gaussian activation functions. By means of the geometrical properties of Gaussian function and algebraic properties of nonsingular M-matrix, some sufficient conditions are obtained to ensure that for an n-neuron neural network, there are exactly 3 equilibrium points with 0≤k≤n, among which 2 and 3-2 equilibrium points are locally exponentially stable and unstable, respectively. Moreover, it concludes that all the states converge to one of the equilibrium points; i.e., the neural networks are completely stable. The derived conditions herein can be easily tested. Finally, a numerical example is given to illustrate the theoretical results.

关键词： Complete stability Gaussian functions Recurrent neural networks Time-varying delays

来源：评论

学校读者我要写书评

暂无评论

Multi-label inductive matrix completion for joint MGMT and IDH1 status prediction for glioma patients 1

引用

20th International Conference on Medical image Computing and computer-Assisted Intervention, MICCAI 2017

作者： Chen, Lei Zhang, Han Thung, Kim-Han Liu, Luyan Lu, Junfeng Wu, Jinsong Wang, Qian Shen, Dinggang Jiangsu Key Laboratory of Big Data Security and Intelligent Processing Nanjing University of Posts and Telecommunications Nanjing China Department of Radiology and BRIC University of North Carolina Chapel Hill United States School of Biomedical Engineering Med-X Research Institute Shanghai Jiao Tong University Shanghai China Department of Neurosurgery Huashan Hospital Fudan University Shanghai China Shanghai Key Lab of Medical Image Computing and Computer Assisted Intervention Shanghai China

ISBN: (数字)9783319661858

ISBN: (纸本)9783319661841

MGMT promoter methylation and IDH1 mutation in high-grade gliomas (HGG) have proven to be the two important molecular indicators associated with better prognosis. Traditionally, the statuses of MGMT and IDH1 are obtained via surgical biopsy, which is laborious, invasive and time-consuming. Accurate presurgical prediction of their statuses based on preoperative imaging data is of great clinical value towards better treatment plan. In this paper, we propose a novel Multi-label Inductive Matrix Completion (MIMC) model, highlighted by the online inductive learning strategy, to jointly predict both MGMT and IDH1 statuses. Our MIMC model not only uses the training subjects with possibly missing MGMT/IDH1 labels, but also leverages the unlabeled testing subjects as a supplement to the limited training dataset. More importantly, we learn inductive labels, instead of directly using transductive labels, as the prediction results for the testing subjects, to alleviate the overfitting issue in small-sample-size studies. Furthermore, we design an optimization algorithm with guaranteed convergence based on the block coordinate descent method to solve the multivariate non-smooth MIMC model. Finally, by using a precious single-center multi-modality presurgical brain imaging and genetic dataset of primary HGG, we demonstrate that our method can produce accurate prediction results, outperforming the previous widely-used single- or multi-task machine learning methods. This study shows the promise of utilizing imaging-derived brain connectome phenotypes for prognosis of HGG in a non-invasive manner. © Springer International Publishing AG 2017.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

On the periodic dynamics of memristor-based neural networks with leakage and time-varying delays

引用

Neurocomputing 2017年 219卷 163-173页

作者： Ping Jiang Zhigang Zeng Jiejie Chen School of Automation Huazhong University of Science and Technology Wuhan 430074 China School of Computer Hubei PolyTechnic University Huangshi 435002 China Key Laboratory of Image Processing and Intelligent Control of Education Ministry of China Wuhan 430074 China School of Computer Science and Technology Hubei Normal University Huangshi 435000 China

In this paper, the periodic dynamics have been studied for a general kind of memristor-based neural networks with leakage and time-varying delays. Some new sufficient conditions have been derived ensuring that the existence, uniqueness and globally exponential stability of the periodic solution for the neural network by using differential inclusions theory, the topological degree theory in set-valued analysis and Lyapunov function technique and so on. As a special case, we have shown that the existence, uniqueness and global exponential stability of equilibrium point for the autonomous neural networks with leakage delays.

关键词： Memristor-based neural networks Leakage delays Time-varying delays Periodic solution Global exponential stability

来源：评论

学校读者我要写书评

暂无评论

Nuclear norm regularized coding with local position-patch and nonlocal similarity for face hallucination

引用

Digital Signal processing 2017年 64卷 107-120页

作者： Guangwei Gao Jian Yang Zhihui Lai Pu Huang Jielin Jiang Hao Gao Dong Yue Institute of Advanced Technology Nanjing University of Posts and Telecommunications Nanjing 210023 PR China Fujian Provincial Key Laboratory of Information Processing and Intelligent Control Minjiang University Fuzhou 350121 PR China School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing 210094 PR China College of Computer Science and Software Engineering Shenzhen University Shenzhen 518060 PR China Key Laboratory of Image and Video Understanding for Social Safety Nanjing University of Science and Technology Nanjing 210094 PR China School of Computer and Software Nanjing University of Information Science and Technology Nanjing 210044 PR China

Learning-based face hallucination methods have received much attention and progress in past few decades. Specially, position-patch based approaches have been proposed to replace the probabilistic graph-based or manifold learning-based ones. As opposed to the existing patch based methods, where the input image patch matrix is converted into vectors before combination coefficients calculation, in this paper, we propose to directly use the image matrix based regression model for combination coefficients computation to preserve the essential structural information of the input patch matrix. For each input low-resolution (LR) patch matrix, its combination coefficients over the training image patch matrices at the same position can be computed. Then the corresponding high-resolution (HR) patch matrix can be obtained with the LR training patches replaced by the corresponding HR ones. The nonlocal self-similarities are finally utilized to further improve the hallucination performance. Various experimental results on standard face databases indicate that our proposed method outperforms some state-of-the-art algorithms in terms of both visual quantity and objective metrics.

关键词： Face hallucination Position-patch Matrix based regression Nuclear norm Nonlocal similarity

来源：评论

学校读者我要写书评

暂无评论

Membrane algorithm with genetic operation and VRPTW-based public optimization system 11th

Membrane algorithm with genetic operation and VRPTW-based pu...

引用

11th International Conference on Bio-inspired Computing – Theories and Applications, BIC-TA 2016

作者： Duan, Yingying Zhou, Kang Qi, Huaqing Zhang, Zhiqiang School of Math and Computer Wuhan Polytechnic University Wuhan430023 China Department of Economics and Management Wuhan Polytechnic University Wuhan430023 China Key Laboratory of Image Information Processing and Intelligent Control School of Automation Huazhong University of Science and Technology Wuhan430074 China

ISBN: (纸本)9789811036101

That combining membrane computing with optimization technology offers a new information interaction model for the research of problems in optimization filed. Based on this, a membrane algorithm owned six basic membranes is proposed to solve the defects of the slow convergence and the small diversity in solving vehicle routing problem with time window. In order to further improve the efficiency and the precision, some new rules are designed: for the former problem, a node classifier is introduced to improve the efficiency by filtering directly a plenty of in-feasible solutions;two methods for the latter problems: an uncertain segment crossover is designed in the corresponding membrane in order to explore directly two feasible segments and segment-node insertion operation is introduced in order to make two individuals inserted synchronously another path. In order to verify the effectiveness of the algorithm, a series of experiments are designed. Known through the results of experiments that these two properties of membranes make the search ability of the algorithm improving quickly for local and global exploration and node classifier improves effectively the running efficiency of this algorithm, which proves that membrane algorithm can accelerate the convergence speed and increase diversity of population. © Springer Nature Singapore Pte Ltd. 2016.

关键词： Membranes

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：