Tradeoff relation between mutual information and error probability in data classification problem

DOI10.1134/S0965542521070113MaRDI QIDQ2048809zbMATH OpenOpenAlexFDO

Authors A. M. Lange, M. M. Lange, S. V. Paramonov

Publication date 24 August 2021

Published in Computational Mathematics and Mathematical Physics (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1134/s0965542521070113

zbMATH Keywords

discriminant functionmutual informationlower bounderror probabilitydata classificationdecision algorithmensemble of sourceserror probability redundancymutual information-error probability relation

Mathematics Subject Classification ID

Statistics (62-XX) Computer science (68-XX)

Recommendations

• The MEE principle in data classification: a perceptron-based analysis
• Minimum error entropy classification.
• Generalized error bounds in pattern recognition
• scientific article; zbMATH DE number 1123573
• An information theoretic tradeoff between complexity and accuracy.

Cites work

• scientific article; zbMATH DE number 2061729 (Why is no real title available?)
• scientific article; zbMATH DE number 3316587 (Why is no real title available?)
• Information transmission with additional noise
• Limits on the majority vote accuracy in classifier fusion
• Pattern classification.

Cited in

(1)

• Accelerated algorithms for growing segments from image regions

This page was built for publication: Tradeoff relation between mutual information and error probability in data classification problem

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2048809)