Decoding rules for error correcting output code ensembles

The ECOC technique for solving multi-class pattern recognition problems can be broken down into two distinct stages - encoding and decoding. Given a pattern vector of unknown class, the encoding stage consists in constructing a corresponding output code vector by applying to it each of the base classifiers in the ensemble. The decoding stage consists in making a classification decision based on the value of the output code. This paper focuses on the latter stage. Firstly, three different approaches to decoding rule design axe reviewed and a new algorithm is presented. This new algorithm is then compared experimentally with two common decoding rules and evidence is presented that the new rule has some advantages in the form of slightly improved classification accuracy and reduced sensitivity to optimal training.