Proceedings chapter
Open access

Multi-class Classifiers based on Binary Classifiers : Performance, Efficiency, and Minimum Coding Matrix Distances

Presented at Grenoble (France), 1-4 Sept. 2009
PublisherInstitute of Electrical and Electronics Engineers (IEEE)
Publication date2009

Using multiple binary classifiers is a popular way to construct multi-class classifiers. There exist several strategies to construct multi-class classifiers from binary classifiers. An important question is which strategy offers the highest probability of successful classification given the number of N binary classifiers used. The first result presented in this work is a method to approximate how many classes can be distinguished using N binary classifiers in practical systems rather than theoretical setups. We come to the conclusion that in this formulation, all methods share the same performance limit, which is determined using the first result. The next question is what the smallest number of binary classifiers is that is needed to attain a given probability of success. To investigate this, we introduce the concept of efficiency, which is the ratio between the number bits needed to count the number of distinguishable classes and the number of bits used. The last contribution concerns the conclusion that methods should exist that are more efficient than those currently employed.

  • Watermarking
  • encoding
  • pattern classification
  • probability
  • support vector machines
Citation (ISO format)
BEEKHOF, Fokko Pieter et al. Multi-class Classifiers based on Binary Classifiers : Performance, Efficiency, and Minimum Coding Matrix Distances. In: IEEE International Workshop on Machine Learning for Signal Processing, MLSP 2009. Grenoble (France). [s.l.] : Institute of Electrical and Electronics Engineers (IEEE), 2009. p. 1–5. doi: 10.1109/MLSP.2009.5306199
Main files (1)
Proceedings chapter (Published version)

Technical informations

Creation03/06/2015 5:12:05 PM
First validation03/06/2015 5:12:05 PM
Update time03/14/2023 10:58:19 PM
Status update03/14/2023 10:58:19 PM
Last indexation01/16/2024 5:07:20 PM
All rights reserved by Archive ouverte UNIGE and the University of GenevaunigeBlack