Data Complexity Analysis for Classifier Combination
01 January 2001
Multiple classifier methods are effective solutions to difficult pattern recognition problems. However, empirical successes and failures have not been completely explained. Amid the excitement and confusion, uncertainty persists in the optimality of method choices for specific problems due to strong data dependence of classifier performance. In response to this, I propose that further exploration of the methodology be guided by detailed descriptions of geometrical characteristics of data and classifier models.