Normalized Compression Distance of Multisets with Applications

Created by W.Langdon from gp-bibliography.bib Revision:1.7615

@Article{Cohen:2015:ieeeTPAMI,

• author = "Andrew R. Cohen and Paul M. B. Vitanyi",
• title = "Normalized Compression Distance of Multisets with Applications",
• journal = "IEEE Transactions on Pattern Analysis and Machine Intelligence",
• year = "2015",
• volume = "37",
• number = "8",
• pages = "1602--1614",
• month = aug,
• keywords = "genetic algorithms, genetic programming",
• ISSN = "0162-8828",
• DOI = "doi:10.1109/TPAMI.2014.2375175",
• abstract = "Pairwise normalized compression distance (NCD) is a parameter-free, feature-free, alignment-free, similarity metric based on compression. We propose an NCD of multisets that is also metric. Previously, attempts to obtain such an NCD failed. For classification purposes it is superior to the pairwise NCD in accuracy and implementation complexity. We cover the entire trajectory from theoretical underpinning to feasible practice. It is applied to biological (stem cell, organelle transport) and OCR classification questions that were earlier treated with the pairwise NCD. With the new method we achieved significantly better results. The theoretic foundation is Kolmogorov complexity.",
• notes = "Also known as \cite{6967789}",

}

Genetic Programming entries for Andrew R Cohen Paul M B Vitanyi

Citations