Stochastic organization of output codes in multiclass learning problems

Wolfgang Utschick, Werner Weichselberger

Research output: Contribution to journalArticlepeer-review

38 Scopus citations

Abstract

The best-known decomposition schemes of multiclass learning problems are one per class coding (OPC) and error-correcting output coding (ECOC). Both methods perform a prior decomposition, that is, before training of the classifier takes place. The impact of output codes on the inferred decision rules can be experienced only after learning. Therefore, we present a novel algorithm for the code design of multiclass learning problems. This algorithm applies a maximum-likelihood objective function in conjunction with the expectation-maximization (EM) algorithm. Minimizing the augmented objective function yields the optimal decomposition of the multiclass learning problem in two-class problems. Experimental results show the potential gain of the optimized output codes over OPC or ECOC methods.

Original languageEnglish
Pages (from-to)1065-1102
Number of pages38
JournalNeural Computation
Volume13
Issue number5
DOIs
StatePublished - May 2001

Fingerprint

Dive into the research topics of 'Stochastic organization of output codes in multiclass learning problems'. Together they form a unique fingerprint.

Cite this