Error correcting output coding
From Cohen Courses
Revision as of 14:38, 30 November 2010 by PastStudents (talk | contribs)
This is a method discussed in paper Ditterich and Bakiri, JAIR 1995.
Error Correcting Output Coding (ECOC) converts a m-class supervised learning problem into a n binary problems. The algorithm assigns each class a unique binary codewords of length n. Then it trains n classifiers to predict each bit in the codewords. The predicted class is the one whose codewords is the closest to the one predicted by the classifier.
