An Algorithm for Reselecting a Reference Objects

Pattern Recognition and Image Analysis - Tập 28 - Trang 684-687 - 2018
N. N. Bondarenko1
1Moscow State University, Moscow, Russia

Tóm tắt

The problem of optimally choosing a learning object is studied. The definition of essential totality of precedents is given. It is shown that an iterative procedure for generating the essential totality of precedents exists. The algorithm operation is checked on model data.

Tài liệu tham khảo

Yu. I. Zhuravlev and V. V. Nikiforov, “Recognition algorithms based on computation of estimates,” Cybern. 7 (3), 387–400 (1971). Yu. I. Zhuravlev, “On an algebraic approach to the solution of pattern recognition and classification problems,” Problemy Kibernet. No. 33, 5–68 (1978) [in Russian]. K. V. Rudakov, “On algebraic theory of universal and local limitations for classification problems,” in Recognition, Classification, and Prediction (Nauka, Moscow, 1989), pp. 176–201 [in Russian]. V. L. Matrosov, “Correct algebras of bounded capacity over sets of incorrect algorithms,” Soviet Math. Dokl. 22 (1), 19–24 (1980). A. G. D’yakonov, Algebraic closures of a generalized model of recognition algorithms based on the computation of estimates, Doctoral Dissertation in Mathematics and Physics (Lomonosov Moscow State University, Moscow, 2009).