检索结果-内蒙古大学图书馆

A PLS kernel algorithm FOR DATA SETS WITH MANY VARIABLES AND FEW OBJECTS .2. CROSS-VALIDATION, MISSING DATA AND EXAMPLES

引用

JOURNAL OF CHEMOMETRICS 1995年第6期9卷 459-470页

作者： RANNAR, S GELADI, P LINDGREN, F WOLD, S Research Group for Chemometrics Department of Organic Chemistry University of Umeå Sweden

This is Part II of a series concerning the PLS kernel algorithm for data sets with many variables and few objects. Here the issues of cross-validation and missing data are investigated. Both partial and full cross-validation are evaluated in terms of predictive residuals and speed and are illustrated on real examples. Two related approaches to the solution of the missing data problem are presented. One is a full EM algorithm and the second a reduced EM algorithm which applies when the number of missing values is small. The two examples are multivariate calibration data sets. The first set consists of UV-visible data measured on mixtures of four metal ions. The second example consists of FT-IR measurements on mixtures consisting of four different organic substances.

关键词： PLS kernel algorithm MULTIVARIATE CALIBRATION EM algorithm CROSS-VALIDATION MISSING DATA

来源：评论

学校读者我要写书评

暂无评论

COMMENTS ON THE PLS kernel algorithm

引用

JOURNAL OF CHEMOMETRICS 1994年第2期8卷 169-174页

作者： DEJONG, S TERBRAAK, CJF AGR MATH GRP GLW DLO 6700 AC WAGENINGENNETHERLANDS

Lindgren et al. (J. Chemometrics, 7, 45-59 (1993)) published a so-called kernel algorithm for PLS regression of V against X when the number of objects is very large. The algorithm is based solely on deflation of the cross-product matrices X(T)X, Y(T)Y and X(T)Y. The algorithm is now described in a shorter and more transparent way and compared with a similar algorithm for the singular value decomposition of X(T)Y.

关键词： kernel algorithm PLS SVD

来源：评论

学校读者我要写书评

暂无评论

An Information Theoretic kernel algorithm for Robust Online Learning

An Information Theoretic Kernel Algorithm for Robust Online ...

引用

International Joint Conference on Neural Networks (IJCNN)

作者： Fan, Haijin Song, Qing Xu, Zhao Nanyang Technol Univ Sch Elect & Elect Engn Singapore 639798 Singapore

ISBN: (纸本)9781467314909

kernel methods are widely used in nonlinear modeling applications. In this paper, a robust information theoretic sparse kernel algorithm is proposed for online learning. In order to reduce the computational cost and make the algorithm suitable for online applications, we investigate an information theoretic sparsification rule based on the mutual information between the system input and output to determine the update of the dictionary (support vectors). According to the rule, only novel and informative samples are selected to form a sparse and compact dictionary. Furthermore, to improve the generalization ability, a robust learning scheme is proposed to avoid the algorithm over learning the redundant samples, which assures the convergence of the learning algorithm and makes the learning algorithm converge to its steady state much faster. Experiment are conducted on practical and simulated data and results are shown to validate the effectiveness of our proposed algorithm.

关键词： kernel algorithm robust learning instantaneous mutual information dead zone

来源：评论

学校读者我要写书评

暂无评论

An information theoretic kernel algorithm for robust online learning

An information theoretic kernel algorithm for robust online ...

引用

International Joint Conference on Neural Networks

作者： Haijin Fan Song, Qing Zhao Xu School of Electronic and Electrical Engineering Nanyang Technological University

ISBN: (纸本)9781467314886

关键词： kernel algorithm Robust learning Instantaneous mutual information Dead zone e-learning systems input learning algorithms Seeds Converge simulated data algorithms Dictionaries as Topic kernel kernel method

来源：评论

学校读者我要写书评

暂无评论

Research on Matrix Factorization algorithm based on Multiple kernel Learning in Collaborative Filtering

Research on Matrix Factorization Algorithm based on Multiple...

引用

The 2018 International Conference on Transportation & Logistics,Information & Communication,Smart City(TLICSC 2018)

作者： Zhaoyong Liu Yiting Zhang Sichuan Vocational College of Chemical Technology Luzhou City

ISBN: (纸本)9781510876996

The matrix factorization(MF) algorithm plays an important role in collaborative filtering(CF).The traditional MF algorithms usually assume that the correlated data is distributed on a linear hyperplane,which is not always the ***,it is a hot topic to combine the kernel algorithm with the matrix factorization algorithm for collaborative *** at the shortcomings of the existing CF algorithm,an single matrix factorization method based on dictionary is firstly proposed for collaborative *** this basis,considering that data can be efficiently embedded into high dimensional space,only one kernel function can not achieve the limitation of optimality energy,a matrix factorization algorithm based on multi kernel learning(MKLMF) is proposed for collaborative *** MKLMF algorithm assumes that there are a set of ppositive defined base kernels,and then the two potential factor matrices are embedded into the high dimensional Hilbert space by the best linear group of the learned p ***,the product of the two potential factor matrices is used to realize the nonlinear reconstruction of the scoring matrix in the original space.A full simulation experiment is carried out with real data *** simulation results show that the proposed algorithm can accurately grasp the nonlinear correlation between data,and the prediction accuracy is better than the latest CF algorithm.

关键词： Matrix factorization Collaborative filtering kernel algorithm potential factor matrices prediction accuracy

来源：评论

学校读者我要写书评

暂无评论

KerbNet : A QoE-Aware kernel-Based Backdoor Attack Framework

引用

IEEE TRANSACTIONS ON DEPENDABLE AND SECURE COMPUTING 2024年第4期21卷 1605-1620页

作者： Gong, Xueluan Chen, Yanjiao Huang, Huayang Kong, Weihan Wang, Ziyao Shen, Chao Wang, Qian Wuhan Univ Sch Comp Sci Wuhan 430072 Peoples R China Zhejiang Univ Coll Elect Engn Hangzhou 310027 Peoples R China Wuhan Univ Sch Cyber Sci & Engn Wuhan 430072 Peoples R China Sch Cyber Sci & Engn Xian 710049 Shaanxi Peoples R China Xi An Jiao Tong Univ MOE Key Lab Intelligent Networks & Network Secur Xian 710049 Shaanxi Peoples R China

Deep neural networks are vulnerable to backdoor attacks, where a specially-designed trigger will lead to misclassification of any benign samples. However, existing backdoor attacks usually impose conspicuous patch triggers on images, which are easily detected by humans and defense algorithms. Existing works on invisible triggers, however, either have reduced attack success rate or yield detectable patterns to visual inspections. In this article, we propose KerbNet, a kernel-based backdoor attack framework, which applies kernel operations to clean samples as the trigger to incur misclassification. The kernel-processed samples achieve a high attack success rate while appearing natural with high Quality-of-Experience (QoE). We carefully design the kernel trigger generation algorithm by exploiting the neural network structure to propagate the influence of the trigger to the target misclassification label under the QoE constraint. We conduct extensive experiments on five datasets, i.e., MNIST, GTSRB, CIFAR-10, CelebA, and ImageNette to evaluate the effectiveness and practicality of KerbNet under the impact of various factors, including neuron-residing layer, kernel size, base image, loss function, model structure, and so on. We also show that our proposed attacks can evade state-of-the-art defense strategies and visual inspections. Code will be available after publication.

关键词： kernel Inspection Visualization Quality of experience Training Biological neural networks Smoothing methods Deep neural network backdoor attack quality-of-experience kernel algorithm

来源：评论

学校读者我要写书评

暂无评论

kernel-PCA algorithms for wide data .2. Fast cross-validation and application in classification of NIR data

引用

CHEMOMETRICS AND INTELLIGENT LABORATORY SYSTEMS 1997年第2期37卷 271-280页

作者： Wu, W Massart, DL deJong, S FREE UNIV BRUSSELS INST PHARMACEUTCHEMOACB-1090 BRUSSELSBELGIUM UNILEVER RES LABS VLAARDINGEN NL-3130 AC VLAARDINGENNETHERLANDS

Four PCA algorithms, namely NIPALS, the power method (POWER), singular value decomposition (SVD) and eigenvalue decomposition (EVD), and their kernel versions are systematically applied to three NIR data sets from the pharmaceutical industry. Cross-validation is used to determine the number of PC factors needed as the input for linear discriminant analysis (LDA). LDA with PCA as the dimension reduction method successfully classifies all three data sets. The kernel algorithms are faster than their corresponding classic algorithms. Of the four classic algorithms, SVD is the fastest. When only the first few PCs are desired, the kernel-POWER method is the fastest of all the algorithms, When all PCs are required, EVD is the most efficient of the four kernel algorithms. When cross-validation is applied, kernel-EVD greatly reduces the elapsed time compared to the classic algorithms. To further speed up cross-validation, two matrix updating methods are proposed. Compared to the normal cross-validation procedure, the first method slightly improves the speed of cross-validation by using the normal kernel-EVD. The second method greatly speeds up cross-validation, but needs a modified kernel-EVD algorithm.

关键词： PCA algorithm kernel algorithm fast cross-validation wide data near-infrared spectroscopy pattern recognition

来源：评论

学校读者我要写书评

暂无评论

Causal Inference of Gene Expression Data Using a Clustering-based Extension of kernel-Granger Causality 23

Causal Inference of Gene Expression Data Using a Clustering-...

引用

23rd Iranian Conference on Biomedical Engineering / 1st International Iranian Conference on Biomedical Engineering (ICBME)

作者： Haredasht, Fateme Nateghi Ghassemi, Farnaz Moradi, Mohammad Hassan Amirkabir Univ Technol Dept Biomed Engn Tehran Iran

ISBN: (纸本)9781509034529

Detecting causal relationships between time series data has been widely studied in many areas, including biology, neuroscience, economics, and climatology. One of the most popular causality inference methods is Granger causality approach that is a linear regression based model for determining whether one time series is useful in forecasting another;however, this approach cannot detect nonlinear relations in the data. Different extensions of Granger causality have been proposed for nonlinear dynamics of the time series data, which have problems in detecting false discoveries. Recently the properties of kernel algorithms have been used in order to achieve nonlinear evaluations of Granger causality. Real biological datasets have a significant problem which is about the big numbers of genes. However, the time steps in the dataset are very short. Due to this problem, the most algorithm in inferring nonlinear causal relationships would fail. In this paper, we propose a new method that deals with this high dimensionality problem and reduces the size of data. In this method, we cluster the hole data using hierarchical clustering with Euclidian Distance measure. Afterwards, we apply kernel-Granger causality to a reduced real biological dataset (yeast gene expression data) to infer causal network.

关键词： Granger causality kernel algorithm gene regulatory networks nonlinear systems hierarchical clustering microarray time series data

来源：评论

学校读者我要写书评

暂无评论

Rees algebras of additive group actions

引用

MATHEMATISCHE ZEITSCHRIFT 2022年第1期301卷 593-626页

作者： Dubouloz, Adrien Heden, Isac Kishimoto, Takashi Univ Bourgogne Franche Comte CNRS UMR5584 IMB F-21000 Dijon France Uppsala Univ Dept Math Box 480 S-75106 Uppsala Sweden Saitama Univ Dept Math Fac Sci Saitama 3388570 Japan

We establish basic properties of a sheaf of graded algebras canonically associated to every relative affine scheme f : X -> S endowed with an action of the additive group scheme G(a,S) over a base scheme or algebraic space S, which we call the (relative) Rees algebra of the G(a,S)-action. In the case of affine algebraic varieties defined over a field of characteristic zero, we establish further properties of the Rees algebra of a G(a)-action in terms of its associated locally nilpotent derivation. We give an algebro-geometric characterization of pairs consisting of an affine algebraic variety and a G(a)-action on it whose associated Rees algebras are finitely generated and provide an algorithm extending van den Essen's kernel algorithm for locally nilpotent derivations to compute generators of these Rees algebras. We illustrate these properties on several examples which played important historical roles in the development of the algebraic theory of locally nilpotent derivations and give applications to the construction of new families of affine threefolds with G(a)-actions.

关键词： Rees algebra Additive group action Locally nilpotent derivation Finite generation kernel algorithm

来源：评论

学校读者我要写书评

暂无评论

Study of Target Tracking and Recovery with Low Resolution Image Series 3

Study of Target Tracking and Recovery with Low Resolution Im...

引用

3rd IEEE International Conference on Computer and Communications (ICCC)

作者： Bao, Xueting Zhan, Hongchen Yuan, Jie Nanjing Univ Sch Informat Sci & Engn Jinling Coll Nanjing 210089 Jiangsu Peoples R China Nanjing Univ Sch Elect Sci & Engn Nanjing 210093 Jiangsu Peoples R China

ISBN: (纸本)9781509063529

Object tracking is one of the most important tasks in computer vision. It is aimed to track and identify the targets in every frame automatically, thus making it possible extracting the targets in the frames for the post-processing. The described method encompasses two important issues in image tracking system that have received increased attention in the few years: moving object tracking and object recognition. It is based on kernel algorithm and due to the continuously changing background and moving targets, object tracking has been a challenging task We review strategies under kernel algorithm and successfully track and restore the image.

关键词： object tracking image restoration kernel algorithm ensemble tracking image extraction

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：