Geodesic
Metrics of algebraic closures in pattern recognition problems with two nonoverlapping classes
Žurnal vyčislitelʹnoj matematiki i matematičeskoj fiziki, Tome 48 (2008) no. 5, pp. 916-927 Cet article a éte moissonné depuis la source Math-Net.Ru

Voir la notice de l'article

It is shown that, in the pattern recognition problem with two nonoverlapping classes, the matrices of estimates of the object closeness are described by a metric. The transition to the algebraic closure of the model of recognizing operators of finite degree corresponds to the application of a special transformation of this metric. It is proved that the minimal degree correct algorithm can be found as a polynomial of a special form. A simple criterion for testing classification implementations is obtained. 
@article{ZVMMF_2008_48_5_a12,
     author = {A. G. D'yakonov},
     title = {Metrics of algebraic closures in pattern recognition problems with two nonoverlapping classes},
     journal = {\v{Z}urnal vy\v{c}islitelʹnoj matematiki i matemati\v{c}eskoj fiziki},
     pages = {916--927},
     year = {2008},
     volume = {48},
     number = {5},
     language = {ru},
     url = {http://geodesic.mathdoc.fr/item/ZVMMF_2008_48_5_a12/}
}
TY  - JOUR
AU  - A. G. D'yakonov
TI  - Metrics of algebraic closures in pattern recognition problems with two nonoverlapping classes
JO  - Žurnal vyčislitelʹnoj matematiki i matematičeskoj fiziki
PY  - 2008
SP  - 916
EP  - 927
VL  - 48
IS  - 5
UR  - http://geodesic.mathdoc.fr/item/ZVMMF_2008_48_5_a12/
LA  - ru
ID  - ZVMMF_2008_48_5_a12
ER  - 
%0 Journal Article
%A A. G. D'yakonov
%T Metrics of algebraic closures in pattern recognition problems with two nonoverlapping classes
%J Žurnal vyčislitelʹnoj matematiki i matematičeskoj fiziki
%D 2008
%P 916-927
%V 48
%N 5
%U http://geodesic.mathdoc.fr/item/ZVMMF_2008_48_5_a12/
%G ru
%F ZVMMF_2008_48_5_a12
A. G. D'yakonov. Metrics of algebraic closures in pattern recognition problems with two nonoverlapping classes. Žurnal vyčislitelʹnoj matematiki i matematičeskoj fiziki, Tome 48 (2008) no. 5, pp. 916-927. http://geodesic.mathdoc.fr/item/ZVMMF_2008_48_5_a12/

[1] Zhuravlev Yu. I., “Ob algebraicheskom podkhode k resheniyu zadach raspoznavaniya ili klassifikatsii”, Probl. kibernetiki, 33, Nauka, M., 1978, 5–68

[2] Zhuravlev Yu. I., Nikiforov V. V., “Algoritmy raspoznavaniya, osnovannye na vychislenii otsenok”, Kibernetika, 1971, no. 3, 1–11 | Zbl

[3] Zhuravlev Yu. I., “Korrektnye algoritmy nad mnozhestvami nekorrektnykh (evristicheskikh) algoritmov. II”, Kibernetika, 1977, no. 6, 21–27 | Zbl

[4] Matrosov V. L., “O kriteriyakh polnoty modeli algoritmov vychisleniya otsenok i ee algebraicheskikh zamykanii”, Dokl. AN SSSR, 258:4 (1981), 791–796 | MR

[5] Dyakonov A. G., Algebra nad algoritmami vychisleniya otsenok: Uchebnoe posobie, Izdat. otd. f-ta VMiK MGU, M., 2006

[6] Dyakonov A. G., “Algebra nad algoritmami vychisleniya otsenok: minimalnaya stepen korrektnogo algoritma”, Zh. vychisl. matem. i matem. fiz., 45:6 (2005), 1134–1145 | MR

[7] Ilin V. A., Kim G. D., Lineinaya algebra i analiticheskaya geometriya, Izd-vo MGU, M., 1998

[8] Deza M., Dutour M., Data mining lor cones of metrics, quasi-metrics, hemi-metrics and super-metrics, CNRS/ENS, Paris, Tokyo, 2002, arXiv: math/0201011

[9] Sachkov V. H., Kombinatornye metody diskretnoi matematiki, Nauka, M., 1977

[10] Burges C. J. C., “A Tutorial on support vector machines for pattern recognition”, Data Mining and Knowledge Discovery, 2 (1998), 121–167 | DOI

[11] Vorontsov K. V., Lektsii po metodu opornykh vektorov www.ccas.ru/voron

[12] Haykin S. S., Neural networks: A comprehensive foundation, sec. ed., Prentice-Hall, 1998

[13] Zhuravlev Yu. I., Isaev I. V., “Postroenie algoritmov raspoznavaniya, korrektnykh dlya zadannoi kontrolnoi vyborki”, Zh. vychisl. matem. i matem. fiz., 19:3 (1979), 726–738 | MR | Zbl

[14] Maisuradze A. I., “Ob optimalnykh razlozheniyakh konechnykh metricheskikh konfiguratsii v zadachakh raspoznavaniya obrazov”, Zh. vychisl. matem. i matem. fiz., 44:9 (2004), 1697–1707 | MR

[15] Breitenbach M., Griidic G. Z., Clustering with local and global consistency, NIPS, Also Available as Techn. Rept. CU-CS-973-04, 2004 | Zbl