Solution of instance-based recognition problems with a large number of classes
- Authors: Zhuravlev Y.I.1, Ryazanov V.V.2
-
Affiliations:
- Dorodnicyn Computing Center, Federal Research Center “Computer Science and Control,”
- Moscow Institute of Physics and Technology (State University)
- Issue: Vol 96, No 2 (2017)
- Pages: 488-490
- Section: Mathematics
- URL: https://journals.rcsi.science/1064-5624/article/view/225392
- DOI: https://doi.org/10.1134/S1064562417050271
- ID: 225392
Cite item
Abstract
A learning-based classification problem with a large number of classes is considered. The error-correcting-output-codes (ЕСОС) scheme is optimized. An initial binary matrix is formed at random so that the number of its rows is equal to the number of classes and each column corresponds to the union of several classes in two macroclasses. In the ЕСОС approach, a binary classification problem is solved for every object to be recognized and for every union. The object is assigned to the class with the nearest code row. A generalization of the ЕСОС approach is presented in which a discrete optimization problem is solved to find optimal unions, probabilities of correct classification are used in dichotomy problems, and the degree of dichotomy informativeness is taken into account. If the solution algorithms for the dichotomy problems are correct, the recognition algorithm for the original problem is correct as well.
About the authors
Yu. I. Zhuravlev
Dorodnicyn Computing Center, Federal Research Center “Computer Science and Control,”
Author for correspondence.
Email: zhur@ccas.ru
Russian Federation, Moscow, 119333
V. V. Ryazanov
Moscow Institute of Physics and Technology (State University)
Email: zhur@ccas.ru
Russian Federation, Dolgoprudnyi, Moscow oblast, 141700