Automatic configuration of spectral dimensionality reduction methods
Automatic configuration of spectral dimensionality reduction methods
复制标题
DOI：
10.1016/j.patrec.2010.05.025
复制
发表时间：
2010-09
期刊：
影响因子：
--
通讯作者：
Michal Lewandowski;D. Makris;Jean-Christophe Nebel
中科院分区：
文献类型：
--
作者：
Michal Lewandowski;D. Makris;Jean-Christophe Nebel
我们提出了一个先进的框架自动配置的光谱降维方法。这是通过引入，首先，互信息的措施，以评估发现的嵌入式空间的质量。其次，无监督径向基函数网络被指定用于空间之间的映射，其中学习过程来自图论，基于马尔可夫聚类算法。在合成数据集和真实的数据集上的实验证明了该方法的有效性。
We propose an advanced framework for the automatic configuration of spectral dimensionality reduction methods. This is achieved by introducing, first, the mutual information measure to assess the quality of discovered embedded spaces. Secondly, unsupervised Radial Basis Function network is designated for mapping between spaces where the learning process is derived from graph theory and based on Markov cluster algorithm. Experiments on synthetic and real datasets demonstrate the effectiveness of the proposed methodology.