This Article 
 Bibliographic References 
 Add to: 
Learning Based on Conceptual Distance
November 1988 (vol. 10 no. 6)
pp. 897-909

An approach to concept learning from examples and concept learning by observation is presented that is based on a intuitive notion of conceptual distance between examples (concepts) and combines symbolical and numerical methods. The approach is based on the observation that very different examples generalize to an expression that is very far from each of them, while identical examples generalize to themselves. Following this idea the authors propose some domain-independent and intuitively justified estimates for the conceptual distance. A hierarchical conceptual clustering algorithm that groups objects so as to maximize the cohesiveness (a reciprocal of the conceptual distance) of the clusters is presented. It is shown that conceptual clustering can improve learning from complex examples describing objects and the relation between them.

[1] N. Benamou and Y. Kodratoff, "Conceptual hierarchical ascending classification," LRI, Univ. Paris-Sud, Res. Rep. 305, 1986.
[2] D. G. Bobrow and W. Winograd, "An overview of KRL, a knowledge representation language,"Cognitive Sci., vol. 1, pp. 3-46, 1977.
[3] P. R. Cohen and F. A. Feingenbaum, Eds., "Learning and inductive inference," inThe Handbook of Artificial Intelligence, vol. 3, Los Angeles, CA: Kaufmann, 1982, pp. 323-511.
[4] G. T. Dietterich and R. S. Michalski, "Inductive learning of structural descriptions: Evaluation criteria and comparative review of selected methods,"Artificial Intell. J., vol. 16, pp. 257-294, 1981.
[5] D. Fisher and P. Langley, "Approaches to conceptual clustering," inProc. Ninth Int. Joint Conf. Artificial Intell.Los Angeles, CA: Kaufmann, 1985, pp. 688-697.
[6] Y. Kodratoff, J. G. Ganascia, B. Clavieras, T. Bollinger, and G. Tecuci, "Careful generalization for concept learning," inProc. European Conf. Artificial Intell., Pisa, Italy, 1984, pp. 483-492; also available inAdvances in Artificial Intelligence, T. O'Shea, Ed. Amsterdam, The Netherlands: North-Holland, 1985, pp. 229-238.
[7] Y. Kodratoff, and J. G. Ganascia, "Improving the generalization step in learning," inMachine Learning: An Artificial Intelligence Approach, vol. 2, R. S. Michalski, J. G. Carbonell, and T. M. Mitchell, Eds. Los Angeles, CA: Morgan-Kaufmann, 1986, pp. 215-244.
[8] Y. Kodratoff and G. Tecuci, "Techniques of design and DISCIPLE learning apprentice,"Int. J. Expert Syst., vol. 1, no. 1, pp. 39-66, 1987.
[9] P. Langley, Ed.,Proc. Fourth Int. Workshop Machine Learning, Univ. California, Los Angeles, CA: Morgan-Kaufmann, 1987.
[10] R. S. Michalski, J. G. Carbonell, and T. M. Mitchell, Eds.,Machine Learning: An Artificial Intelligence Approach, vol. 1, Palo Alto, CA: Tioga, 1983.
[11] R. S. Michalski, J. G. Carbonell, and T. M. Mitchell, Eds.,Machine Learning: An Artificial Intelligence Approach, vol. 2. Los Altos, CA: Morgan Kaufmann, 1986.
[12] R. S. Michalski, and R. Stepp, "Learning by observation," inMachine Learning: An Artificial Intelligence Approach, R. S. Michalski, J. G. Carbonell, and T. M. Mitchell, Eds. Palo Alto, CA: Tioga, 1983, pp. 163-190 (now distributed in the U.S. by Kaufmann and in Europe by Springer-Verlag).
[13] R. S. Michalski, "Inductive learning as rule-guided transformation of symbolic descriptions: A theory and implementation," inAutomatic Program Construction Techniques, A. W. Biermann, G. Guiho, and Y. Kodratoff, Eds. New York: Macmillan, 1984, pp. 517-552.
[14] M. L. Minsky, "A framework for representing knowledge," inThe Psychology of Computer Vision, P. H. Winston, Ed. New York: McGraw-Hill, 1975, pp. 211-277.
[15] T. M. Mitchell, J. C. Carbonell, and R. S. Michalski, Eds.,Machine Learning: A Guide to Current Research. Amsterdam, The Netherlands: Kluwer, 1985.
[16] N. Sridharan and J. Bresina, "A mechanism for the management of partial and indefinite descriptions,"Rutgers Univ., Tech. Rep. CBM-TR-134, 1983.
[17] G. Tecuci, D. Mandutianu, and S. Voinea, "A hierarchical system for robot programming,"Comput. Artificial Intell., vol. 2, 1983.
[18] G. Tecuci, "Learning hierarchical descriptions from examples,"Comput. Artificial Intell., vol. 3, 1984.
[19] J. Van Ryzin, Ed.,Classification and Clustering. New York: Academic, 1977.

Index Terms:
symbolic methods; artificial intelligence; knowledge acquisition; conceptual distance; concept learning; numerical methods; hierarchical conceptual clustering; cohesiveness; artificial intelligence; knowledge acquisition; learning systems
Y. Kodratoff, G. Tecuci, "Learning Based on Conceptual Distance," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 10, no. 6, pp. 897-909, Nov. 1988, doi:10.1109/34.9111
Usage of this product signifies your acceptance of the Terms of Use.