Multiparameter Persistence Image for Topological Machine Learning
NIPS 2020(2020)
摘要
In the last decade, there has been increasing interest in topologicaldata analysis, a new methodology for using geometric structures indata for inference and learning. A central theme in the area is theidea of persistence, which in its most basic form studies how measuresof shape change as a scale parameter varies. There are now a number offrameworks that support statistics and machine learning in thiscontext. However, in many applications there are several differentparameters one might wish to vary: for example, scale and density. Incontrast to the one-parameter setting, techniques for applyingstatistics and machine learning in the setting of multiparameterpersistence are not well understood due to the lack of a conciserepresentation of the results.
更多查看译文
关键词
persistence,images,machine learning
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络