Abstract
Learning from examples is a popular methodology giving the set of rules (or decision trees) able to properly classify objects from predefined set. One of the main problems with this methodology is discretization — the process of converting continuous values of used attributes into more practical discrete values. Fuzzy partitions, introduced in this paper, can be viewed as a convenient way for expressing uncertainty in both: membership to discrete value and classification of cases, absent in the initial training set.
This is a preview of subscription content, log in via an institution to check access.
Preview
Unable to display preview. Download preview PDF.
References
Chmielewski M.R., Grzymala-Busse J.W.: Global discretization of continuous attributes as preprocessing for machine learning. International Journal of Approximate Reasoning 15 (1996) 320–331
Grzymala-Busse J.W.: On the reduction of instance space in learning from examples. Methodologies of Intelligent Systems, 5. Elsevier Co.(1990) 388–395
Klir G.J., Folger T.A.: Fuzzy sets, uncertainty, and information. Prentice Hall. (1988)
Traczyk W.: Partitions in knowledge discovery and learning. Foundations of Computing and Decision Sciences 19 (1994) 145–156
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1997 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Traczyk, W. (1997). Fuzzy partitions in learning from examples. In: Reusch, B. (eds) Computational Intelligence Theory and Applications. Fuzzy Days 1997. Lecture Notes in Computer Science, vol 1226. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-62868-1_147
Download citation
DOI: https://doi.org/10.1007/3-540-62868-1_147
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-62868-2
Online ISBN: 978-3-540-69031-3
eBook Packages: Springer Book Archive