检索结果-南通市图书馆

Robust AUC maximization for classification with pairwise confidence comparisons

在线全文

学校读者我要写书评

暂无评论

Frontiers of Computer Science 2024年第4期18卷 73-83页

作者： Haochen SHI Mingkun XIE Shengjun HUANG College of Computer Science and Technology Nanjing University of Aeronautics and AstronauticsNanjing 211106China College of Electronic and Information Engineering Nanjing University of Aeronautics and AstronauticsNanjing 211106China MIIT Key Laboratory of Pattern Analysis and Machine Intelligence Nanjing 211106China

Supervised learning often requires a large number of labeled examples,which has become a critical bottleneck in the case that manual annotating the class labels is *** mitigate this issue,a new framework called pairwise comparison(Pcomp)classification is proposed to allow training examples only weakly annotated with pairwise comparison,i.e.,which one of two examples is more likely to be *** previous study solves Pcomp problems by minimizing the classification error,which may lead to less robust model due to its sensitivity to class *** this paper,we propose a robust learning framework for Pcomp data along with a pairwise surrogate loss called *** provides an unbiased estimator to equivalently maximize AUC without accessing the precise class ***,we prove the consistency with respect to AUC and further provide the estimation error bound for the proposed *** studies on multiple datasets validate the effectiveness of the proposed method.

关键词： method pairwise weakly

pairwise NONADDITIVE DISCRIMINATING INTERACTION AMONG CHIRAL MOLECULES

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Chinese Science Bulletin 1981年第7期26卷 659-662页

作者：刘为民 Group of Theoretical Biology Shanghai Institute of Biochemistryn object is called chiral if it cannot be brought into congruence with its mirror image by translation and rotation. Many biological molecules possess chiral purity and the interaction among them is highly stereospecific. So the investigation of the interaction among chiral molecules from the microscopic view has its biological significance. The higher order perturbation theory of intermolecular forces and the researches on the pairwise nonadditive interaction among three ordinary molecules have provided a sound basis for this work. Since 1962 the discriminating interaction between two

An object is called chiral if it cannot be brought into congruence with its mirror image by translation and rotation. Many biological molecules possess chiral purity, and the interaction among them is highly stereospecific. So the investigation of the interaction among chiral molecules from the microscopic view has its biological significance. The higher order perturbation theory of intermolecular forces and the researches on the pairwise nonadditive interaction among three ordinary molecules have provided a sound basis for this work. Since 1962 the discriminating interaction between

关键词： chiral congruence perturbation ordinary pairwise mirror intermolecular rotation purity microscopic

pairwise comparisons in the analysis of carcinogenicity data

在线全文

学校读者我要写书评

暂无评论

Health 2012年第10期4卷 910-918页

作者： Mohammad A. Rahman Ram C. Tiwari Division of Biometrics-6 Office of Biostatistics Center for Drug Evaluation and Research Food and Drug Administration Silver Spring USA Office of Biostatistics Center for Drug Evaluation and Research Food and Drug Administration Silver Spring USA

Analysis of carcinogenicity data generally involves a trend test across all dose groups and a pairwise comparison of the high dose group with the control. The most commonly used test for a positive trend is the Cochran-Armitage test. This test is asymptotically normal. For the pairwise comparison of the high dose group with the control group, we propose two modifications: the first modification is to apply the test on the data from high dose and control groups after dropping the data from the low and the medium dose groups;the second modification is to adjust the test conditional on data from all dose groups. We compare the power performance of these two modifications for the pairwise comparisons.

关键词： Carcinogenicity Study Trend Test pairwise Test Exact Test

Hierarchical Hypercube Based pairwise Key Establishment Scheme for Sensor Networks

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

International Journal of Communications, Network and System Sciences 2009年第2期2卷 142-154页

作者： Lei WANG Department of Computer Science Lakehead University Thunder Bay Canada

Security schemes of pairwise key establishment, which enable sensors to communicate with each other se-curely, play a fundamental role in research on security issue in wireless sensor networks. A general frame-work for key predistribution is presented, based on the idea of KDC (Key Distribution Center) and polyno-mial pool schemes. By utilizing nice properties of H2 (Hierarchical Hypercube) model, a new security mechanism for key predistribution based on such model is also proposed. Furthermore, the working per-formance of tolerance resistance is seriously inspected in this paper. Theoretic analysis and experimental fig-ures show that the algorithm addressed in this paper has better performance and provides higher possibilities for sensor to establish pairwise key, compared with previous related works.

关键词： pairwise Key Sensor Networks Key Pool Key Predistribution H2 Framework

The Construction of pairwise Additive Minimal BIB Designs with Asymptotic Results

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Applied Mathematics 2014年第14期5卷 2130-2136页

作者： Kazuki Matsubara Sanpei Kageyama Graduate School of Science Hiroshima University Higashi-Hiroshima Japan Hiroshima Institute of Technology Hiroshima Japan

An asymptotic existence of balanced incomplete block (BIB) designs and pairwise balanced designs (PBD) has been discussed in [1]-[3]. On the other hand, the existence of additive BIB designs and pairwise additive BIB designs with k = 2?and?λ = 1?has been discussed with direct and recursive constructions in [4]-[8]. In this paper, an asymptotic existence of pairwise additive BIB designs is proved by use of Wilson’s theorem on PBD, and?also for some l?and k the exact existence of l?pairwise additive BIB designs with block size k and?λ = 1?is discussed.

关键词： Incidence Matrix pairwise Balanced Design (PBD) Balanced Incomplete Block Design (BIBD) Additive BIB Design pairwise Additive BIB Design Wilson’s Theorem

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

基于pairwise排序学习算法研究综述

科学技术与工程 2017年第21期17卷 184-190页

作者：熊李艳陈晓霞钟茂生黄晓辉华东交通大学信息工程学院南昌330013

Learning to Rank(L2R)技术是对搜索结果进行排序,是近几年的研究热点。现关于L2R中的pairwise方法进行研究分析,pairwise方法将排序问题转化为二元分类问题,其缺点是只考虑两篇文档的相对顺序,而不考虑文档出现在搜索结果列表中的位置... 详细信息

Learning to Rank(L2R)技术是对搜索结果进行排序,是近几年的研究热点。现关于L2R中的pairwise方法进行研究分析,pairwise方法将排序问题转化为二元分类问题,其缺点是只考虑两篇文档的相对顺序,而不考虑文档出现在搜索结果列表中的位置。另外,不同的查询拥有的文档对数目不同,结果会向拥有文档对较多的查询偏移。对常用的pairwise算法的损失函数及其求解方法、基本思想、算法框架、效用评价以及算法应用进行概括分析。

关键词： pairwise 损失函数优化方法

对联合线性混合模型使用pairwise方法做仿真模拟

在线全文

学校读者我要写书评

暂无评论

对联合线性混合模型使用Pairwise方法做仿真模拟

作者：陈宏霞东北师范大学

学位级别：硕士

一元纵向数据（追踪数据）是一被试群体在一个变量,多个时间的测量结果。纵向数据分析已经有成熟完善的统计模型和统计推断方法。多元纵向数据是一被试群体在多个变量,多个时间的测量结果。为了研究儿童多个行为指标的加工速度的重复测... 详细信息

一元纵向数据（追踪数据）是一被试群体在一个变量,多个时间的测量结果。纵向数据分析已经有成熟完善的统计模型和统计推断方法。多元纵向数据是一被试群体在多个变量,多个时间的测量结果。为了研究儿童多个行为指标的加工速度的重复测量数据,受作者Fieuws,S.＆ ***（2006）提出pairwise联合建模的思想方法启发,提出相应的模型,构造模拟数据来做pairwise方法处理,评估这种方法的可行性和优劣性。利用pairwise联合建模方式,进行1000次模拟实验,得到固定效应参数的估计值,在大样本理论的框架下,pairwise联合建模拟合与全模型相比,参数效率损失可以很小,即使是在不同的响应变量之间有相同的固定效应参数情况下,参数估计值和真实值依然很接近。

关键词：多元纵向数据随机效应模型 pairwise

基于改进pairwise损失函数的排序学习方法

同方学位论文库评论

在线全文

同方学位论文库

学校读者我要写书评

暂无评论

基于改进Pairwise损失函数的排序学习方法

基于pairwise排序学习的因子分解推荐算法

第六届全国信息检索学术会议

作者：吴佳金杨志豪林原林鸿飞大连理工大学信息检索研究室

排序学习是当前机器学习与信息检索交叉领域的研究热点。它利用机器学习方法自动地构造排序模型,用于排序新的数据。pairwise方法是一类重要的排序学习方法,它以偏序文档对作为训练样例,通过判断不同文档与查询的相关性大小关系来为文... 详细信息

排序学习是当前机器学习与信息检索交叉领域的研究热点。它利用机器学习方法自动地构造排序模型,用于排序新的数据。pairwise方法是一类重要的排序学习方法,它以偏序文档对作为训练样例,通过判断不同文档与查询的相关性大小关系来为文档排序。由于pairwise方法不考虑单个文档的相关性大小,若对文档对内两个文档的相关性均预测错误,则会导致连锁反应并影响最终排序性能;为解决该问题,本文分别基于单层神经网络和双层神经网络的RankNet算法,加入pointwise损失函数进行优化,并分别使用梯度下降算法和反向传播算法训练网络权重值,得到排序模型。在OHSUMED数据集上的实验结果表明,加入pointwise损失函数有助于改善pairwise方法的排序性能。

关键词：信息检索排序学习损失函数 pairwise RankNet

来源： cnki会议评论

在线全文

cnki会议

学校读者我要写书评

暂无评论

计算机应用与软件 2016年第6期33卷 255-259页

作者：周俊宇戴月明吴定会江南大学物联网工程学院江苏无锡214122

针对基于内存的协同过滤推荐算法存在推荐列表排序效果不佳的问题,提出基于pairwise排序学习的因子分解推荐算法(简称pairwise-SVD推荐算法)。新算法将因子分解的预测结果作为排序学习算法的输入,把排序问题转化成分类问题使用排序学习... 详细信息

针对基于内存的协同过滤推荐算法存在推荐列表排序效果不佳的问题,提出基于pairwise排序学习的因子分解推荐算法(简称pairwise-SVD推荐算法)。新算法将因子分解的预测结果作为排序学习算法的输入,把排序问题转化成分类问题使用排序学习理论进行排序产生推荐列表。实验结果表明相比基于内存的协同过滤推荐算法,pairwise-SVD推荐算法的排序效果更佳。其在指标Kendall-tau上提高了近一倍,在指标MRR上提高了近30%,且在指标MAP上也有小幅提高。

关键词： pairwise 因子分解协同过滤分类排序学习