Multiresolution estimates of classification complexity

Sameer SinghIEEE TPAMI 2003 · DOI

Abstract

In this paper, we study two measures of classification complexity based on feature space partitioning: purity and neighborhood separability. The new measures of complexity are compared with probabilistic distance measures and a number of other nonparametric estimates of classification complexity on a total of 10 databases from the University of California, Irvine, (UCI) repository.
BibTeX
@article{singh2003multiresolution,
  author = {Sameer Singh},
  title = {{Multiresolution estimates of classification complexity}},
  journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
  year = {2003},
  doi = {10.1109/tpami.2003.1251146},
}

Loading related content...

Figure