|
In data mining and treatment learning, wrappers were used by Ron Kohavi and George John. Their idea was to wrap their treatments learners in a preprocessor that would search to make subsets from the current set of attributes. Using wrappers, the attribute subset would continue to grow until the accuracy of the model was no longer more accurate. [1]
The TAR2 treatment learner used by Menzies and Hu did not use wrappers as it claimed their use made the treatment learning process too slow. [2]
External Sources
[1] R. Kohavi and G.H. John, "Wrappers for Feature Subset Selection," Artificial Intelligence, vol. 97, no. 1-2, 1997, pp 273-324
[2] T. Menzies, Y. Hu, Data Mining For Busy People. IEEE Computer, October 2003, pgs. 18-25.
|
