Learning vector quantization for (dis-)similarities

Learning vector quantization for (dis-)similarities
复制标题

学习向量量化的(不)相似性

DOI:
10.1016/j.neucom.2013.05.054
复制
发表时间:
2014
期刊:
影响因子:
6
通讯作者:
Xibin Zhu
Xibin Zhu
中科院分区:
计算机科学2区
文献类型:
--
作者:
Barbara Hammer;Daniela Hofmann;Frank-Michael Schleif;Xibin Zhu

文献摘要

参考文献

被引文献

相似文献

基于原型的方法通常显示非常直观的分类和学习规则。然而,流行的基于原型的分类器,如学习向量量化(LVQ),仅限于向量数据。在这篇文章中,我们讨论了如何将LVQ算法扩展到仅由配对相似性或不相似性表征的更一般的数据的技术。我们提出了一个基于数据的伪欧几里得嵌入背景的方法如何组合的一般框架。本文对现有的核广义相关LVQ方法和关系广义相关LVQ方法进行了综述,并为核鲁棒软LVQ方法和关系鲁棒软LVQ方法开辟了道路。有趣的是,基于成本函数的无监督原型技术也可以放在这个框架中,包括核和关系神经气体以及核和关系自组织映射(基于Heskes的成本函数)。我们在几个基准测试中演示了LVQ技术对相似或不相似数据的性能,达到了最先进的结果。
Prototype-based methods often display very intuitive classification and learning rules. However, popular prototype based classifiers such as learning vector quantization (LVQ) are restricted to vectorial data only. In this contribution, we discuss techniques how to extend LVQ algorithms to more general data characterized by pairwise similarities or dissimilarities only. We propose a general framework how the methods can be combined based on the background of a pseudo-Euclidean embedding of the data. This covers the existing approaches kernel generalized relevance LVQ and relational generalized relevance LVQ, and it opens the way towards two novel approach, kernel robust soft LVQ and relational robust soft LVQ. Interestingly, also unsupervised prototype based techniques which are based on a cost function can be put into this framework including kernel and relational neural gas and kernel and relational self-organizing maps (based on Heskes' cost function). We demonstrate the performance of the LVQ techniques for similarity or dissimilarity data in several benchmarks, reaching state of the art results.
6985条数字化胰蛋白酶G带人类中期染色体的定量分析
DOI: 10.1111/j.1399-0004.1980.tb02296.x
发表时间: 1980
期刊: Clinical Genetics
影响因子: 3.5
作者:
Claes Lundsieen;J. Philip;E. Granum
通讯作者: E. Granum
DOI: --
发表时间: 2005
期刊: Neural Computation
影响因子: 2.9
作者:
B. Hammer;A. Micheli;A. Sperduti
通讯作者: A. Sperduti
DOI: --
发表时间: 2006
期刊: Neural Networks
影响因子: 7.8
作者:
Hujun Yin
通讯作者: Hujun Yin
基于相似性的分类
DOI: --
发表时间: 2003
期刊: International Symposium on Intelligent Data Analysis
影响因子: --
作者:
A. Bernal;Karen Hospevian;Tayfun Karadeniz;J. Lassez
通讯作者: J. Lassez
DOI: --
发表时间: 2013
期刊: The European Symposium on Artificial Neural Networks
影响因子: --
作者:
Daniela Hofmann;B. Hammer
通讯作者: B. Hammer