Manifold Learning by Preserving Distance Orders.

Manifold Learning by Preserving Distance Orders.
复制标题

DOI:
10.1016/j.patrec.2013.11.022
复制
发表时间:
2014-03-01
影响因子:
5.1
通讯作者:
Erdogmus, Deniz
Erdogmus, Deniz
中科院分区:
计算机科学3区
文献类型:
--
作者:
Ataer-Cansizoglu, Esra;Akcakaya, Murat;Orhan, Umut;Erdogmus, Deniz

文献摘要

参考文献

相似文献

非线性降维对于高维数据的分析和解释是必不可少的。在这篇手稿中,我们提出了一个距离顺序保持流形学习算法,扩展了主要用于多维尺度(MDS)为基础的方法的基本均方误差成本函数。我们开发了一个约束优化问题,通过假设明确的限制,在低维空间的距离顺序。在这个优化问题中,作为MDS的推广,而不是迫使高维原始和低维投影空间中的距离之间的线性关系,我们学习了一个由径向基函数近似的非减关系。我们将所提出的方法与现有的流形学习算法进行比较,使用合成数据集的基础上常用的残差方差和建议的违反距离顺序度量的百分比。我们还对用于早产儿视网膜病变(ROP)诊断的视网膜图像数据集进行了实验。
Nonlinear dimensionality reduction is essential for the analysis and the interpretation of high dimensional data sets. In this manuscript, we propose a distance order preserving manifold learning algorithm that extends the basic mean-squared error cost function used mainly in multidimensional scaling (MDS)-based methods. We develop a constrained optimization problem by assuming explicit constraints on the order of distances in the low-dimensional space. In this optimization problem, as a generalization of MDS, instead of forcing a linear relationship between the distances in the high-dimensional original and low-dimensional projection space, we learn a non-decreasing relation approximated by radial basis functions. We compare the proposed method with existing manifold learning algorithms using synthetic datasets based on the commonly used residual variance and proposed percentage of violated distance orders metrics. We also perform experiments on a retinal image dataset used in Retinopathy of Prematurity (ROP) diagnosis.
DOI: 10.1137/s1052623497325107
发表时间: 1999-01-01
影响因子: 3.1
作者:
Byrd, RH;Hribar, ME;Nocedal, J
通讯作者: Nocedal, J
DOI: 10.1016/s0167-739x(98)00081-8
发表时间: 1999-04-01
期刊: FUTURE GENERATION COMPUTER SYSTEMS-THE INTERNATIONAL JOURNAL OF GRID COMPUTING AND ESCIENCE
影响因子: --
作者:
Dzwinel, W;Blasiak, J
通讯作者: Blasiak, J
DOI: 10.1016/j.jaapos.2007.09.005
发表时间: 2007-12-01
期刊: JOURNAL OF AAPOS
影响因子: 1.6
作者:
Gelman, Rony;Jiang, Lei;Chiang, Michael F.
通讯作者: Chiang, Michael F.
DOI: 10.1016/j.physleta.2009.04.007
发表时间: 2009-05-25
期刊: PHYSICS LETTERS A
影响因子: 2.6
作者:
Andrecut, M.
通讯作者: Andrecut, M.
DOI: 10.1090/s0025-5718-1980-0572855-7
发表时间: 1980-01-01
影响因子: 2
作者:
NOCEDAL, J
通讯作者: NOCEDAL, J