Izvestiya Instituta Matematiki i Informatiki Udmurtskogo Gosudarstvennogo Universiteta
RUS  ENG    JOURNALS   PEOPLE   ORGANISATIONS   CONFERENCES   SEMINARS   VIDEO LIBRARY   PACKAGE AMSBIB  
General information
Latest issue
Archive
Guidelines for authors

Search papers
Search references

RSS
Latest issue
Current issues
Archive issues
What is RSS



Izv. IMI UdGU:
Year:
Volume:
Issue:
Page:
Find






Personal entry:
Login:
Password:
Save password
Enter
Forgotten password?
Register


Izvestiya Instituta Matematiki i Informatiki Udmurtskogo Gosudarstvennogo Universiteta, 2006, Issue 2(36), Pages 61–64 (Mi iimi115)  

MATHEMATICS

Capacity of a family of decision rools in learning to pattern recognition

A. G. Itskov

Izhevsk State Technical University
References:
Abstract: A notion of the capacity of a family of decision rools is inspected. The bounded capacity provides convergence of the frequency of errors to the probability of errors. Some estimates of capacity for the families of linear and non-linear decision rools are given.
Bibliographic databases:
Document Type: Article
UDC: 519.92
Language: Russian
Citation: A. G. Itskov, “Capacity of a family of decision rools in learning to pattern recognition”, Izv. IMI UdGU, 2006, no. 2(36), 61–64
Citation in format AMSBIB
\Bibitem{Its06}
\by A.~G.~Itskov
\paper Capacity of a family of decision rools in learning to pattern recognition
\jour Izv. IMI UdGU
\yr 2006
\issue 2(36)
\pages 61--64
\mathnet{http://mi.mathnet.ru/iimi115}
Linking options:
  • https://www.mathnet.ru/eng/iimi115
  • https://www.mathnet.ru/eng/iimi/y2006/i2/p61
  • Citing articles in Google Scholar: Russian citations, English citations
    Related articles in Google Scholar: Russian articles, English articles
    Известия Института математики и информатики Удмуртского государственного университета
    Statistics & downloads:
    Abstract page:141
    Full-text PDF :80
    References:29
     
      Contact us:
     Terms of Use  Registration to the website  Logotypes © Steklov Mathematical Institute RAS, 2024