Source

orange / Orange / datasets / monks-2_test.htm

Full commit
<html>
<head>
<title>Monks Data Bases</title>
</head>
<body>
<h1>Info on Monks Data Bases</h1>
<pre>
1. Title: The Monk's Problems

2. Sources: 
    (a) Donor: Sebastian Thrun
	       School of Computer Science
	       Carnegie Mellon University
	       Pittsburgh, PA 15213, USA

	       E-mail: thrun@cs.cmu.edu

    (b) Date: October 1992

3. Past Usage: 

   - See File: thrun.comparison.ps.Z

   - Wnek, J., "Hypothesis-driven Constructive Induction," PhD dissertation, 
     School of Information Technology and Engineering, Reports of Machine 
     Learning and Inference Laboratory, MLI 93-2, Center for Artificial 
     Intelligence, George Mason University, March 1993.

   - Wnek, J. and Michalski, R.S., "Comparing Symbolic and 
     Subsymbolic Learning: Three Studies," in Machine Learning: A 
     Multistrategy Approach, Vol. 4., R.S. Michalski and G. Tecuci (Eds.), 
     Morgan Kaufmann, San Mateo, CA, 1993.

4. Relevant Information:

   The MONK's problem were the basis of a first international comparison
   of learning algorithms. The result of this comparison is summarized in
   "The MONK's Problems - A Performance Comparison of Different Learning
   algorithms" by S.B. 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 has been published as
   Technical Report CS-CMU-91-197, Carnegie Mellon University in Dec.
   1991.

   One significant characteristic of this comparison is that it was
   performed by a collection of researchers, each of whom was an advocate
   of the technique they tested (often they were the creators of the
   various methods). In this sense, the results are less biased than in
   comparisons performed by a single person advocating a specific
   learning method, and more accurately reflect the generalization
   behavior of the learning techniques as applied by knowledgeable users.

   There are three MONK's problems.  The domains for all MONK's problems
   are the same (described below).  One of the MONK's problems has noise
   added. For each problem, the domain has been partitioned into a train
   and test set.

5. Number of Instances: 432

6. Number of Attributes: 8 (including class attribute)

7. Attribute information:
    1. class: 0, 1 
    2. a1:    1, 2, 3
    3. a2:    1, 2, 3
    4. a3:    1, 2
    5. a4:    1, 2, 3
    6. a5:    1, 2, 3, 4
    7. a6:    1, 2
    8. Id:    (A unique symbol for each instance)

8. Missing Attribute Values: None

9. Target Concepts associated to the MONK's problem:

   MONK-1: (a1 = a2) or (a5 = 1)

   MONK-2: EXACTLY TWO of {a1 = 1, a2 = 1, a3 = 1, a4 = 1, a5 = 1, a6 = 1}

   MONK-3: (a5 = 3 and a4 = 1) or (a5 /= 4 and a2 /= 3)
           (5% class noise added to the training set)

</pre>
</body>
</html>