|
|||||
|
|
Neighbor embedding XOM for dimension reduction and visualization |
|
| Authors: | Kerstin BunteAuthor Vitae Barbara HammerAuthor VitaeThomas VillmannAuthor Vitae Michael BiehlAuthor VitaeAxel WismüllerAuthor Vitae |
| Affiliation: | a Johann Bernoulli Institute for Mathematics and Computer Science, University of Groningen, 9700AK Groningen, The Netherlands b Department of Radiology, University of Rochester, 601 Elmwood Avenue, Rochester, NY 14642-648, USA c Department of Biomedical Engineering, University of Rochester, 601 Elmwood Avenue, Rochester, NY 14642-648, USA d Bielefeld University, CITEC, Universitätsstraße 23, 33615 Bielefeld, Germany e Department of Mathematics, University of Applied Sciences Mittweida, Germany f Department of Radiology, University of Munich, Klinikum Innenstadt, Ziemssenstr. 1, 80336 Munich, Germany |
| Abstract: | We present an extension of the Exploratory Observation Machine (XOM) for structure-preserving dimensionality reduction. Based on minimizing the Kullback-Leibler divergence of neighborhood functions in data and image spaces, this Neighbor Embedding XOM (NE-XOM) creates a link between fast sequential online learning known from topology-preserving mappings and principled direct divergence optimization approaches. We quantitatively evaluate our method on real-world data using multiple embedding quality measures. In this comparison, NE-XOM performs as a competitive trade-off between high embedding quality and low computational expense, which motivates its further use in real-world settings throughout science and engineering. |
| Keywords: | Dimension reduction Visualization Divergence optimization Nonlinear embedding Exploratory Observation Machine Stochastic neighbor embedding |
| 本文献已被 ScienceDirect 等数据库收录！ | |