Abstract
The problem of classifying individual sequences into a finite number of classes with respect to a given set of training sequences using finite-state (FS) classifiers, is investigated. FS classifiers are sought that discrirninate between two given distinct sources of sequences. In practice, the sources are not known and hence such a classifier is not implementable. We propose a simple classification algorithm which is universal in the sense of being independent of the unknown sources. The proposed algorithm discriminates between the sources whenever they are distinguishable by some finite-memory classifier, for almost every given training sets from these sources. This algorithm is based on the Lempel-Ziv data compression algorithm and is associated with a new notion of empirical informational divergence between two individual sequences.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.