The MONK's Problems: A Performance Comparison of Different Learning Algorithms

S. Thrun, J. Bala, E. Bloedorn, I. Bratko, B. Cestnik, J. Cheng, K. De Jong, S. Dzeroski, S.E. Fahlman, D. Fisher, R. Hamann, K. Kaufman, S. Keller, I. Kononenko, J. Kreuziger, R.S. Michalski, T. Mitchell, P. Pachowicz, Y. Reich H. Vafaie, W. Van de Welde, W. Wenzel, J. Wnek, and J. Zhang

Once upon a time, in July 1991, the monks of Corsendonk Priory were faced with a school held in their priory, namely the 2nd European Summer School on Machine Learning. After listening more than one week to a wide variety of learning algorithms, they felt rather confused: Which algorithm would be optimal? And which one to avoid? As a consequence of this dilemma, they created a simple task on which all learning algorithms ought to be be compared: the three MONK's problems.

Click here to obtain the full paper (588760 bytes) and here to obtain the MONK's database (7561 compressed bytes)

@TECHREPORT{Thrun91c,
  AUTHOR         = {S. Thrun and J. Bala and E. Bloedorn and I. Bratko and 
                    B. Cestnik and J. Cheng and K. De Jong and 
                    S. Dzeroski and R. Hamann and K. Kaufman and 
                    S. Keller and I. Kononenko and J. Kreuziger and 
                    R.S. Michalski and T. Mitchell and P. Pachowicz and 
                    B. Roger and H. Vafaie and W. Van de Velde and 
                    W. Wenzel and J. Wnek and J. Zhang},
  YEAR           = {1991},
  TITLE          = {The \mbox{MONK's} Problems: A Performance Comparison 
                    of Different Learning Algorithms},
  NUMBER         = {CMU-CS-91-197},
  INSTITUTION    = {Carnegie Mellon University, Computer Science Department},
  ADDRESS        = {Pittsburgh, PA}
}