The Improvement of Recognition Algorithms
as an Ill-Formalized Optimization Problem

Vl. D. Mazurov and A. L. Popov

Institute of Mathematics and Mechanics, Ural Division, Russian Academy of Sciences,
ul. S. Kovalevskoi 16, Yekaterinburg, 620219 Russia

Abstract—Pattern recognition methods are widely used to solve complicated practical problems that defy a
complete formal description. Therefore, it is of interest to consider how new objects can be classified more reli
ably on the basis of precedents. There is a great interest now also in the methods that organize control of the
state of objects being classified. This paper discusses techniques of ill-formalized optimization for solving these
recognition problems.

Pleiades Publishing home page | journal home page | top

If you have any problems with this server, contact webmaster.