登入
選單
返回
Google圖書搜尋
Use of Randomization to Normalize Feature Merits
Thomas J. Watson IBM Research Center
Se June Hong
Jonathan Richard Morley Hosking
Shumuel Winograd
出版
IBM Thomas J. Watson Research Division
, 1995
URL
http://books.google.com.hk/books?id=Ga99HAAACAAJ&hl=&source=gbs_api
註釋
Abstract: "Feature merits are used for feature selection in classification and regression as well as for decision tree generation. Most of the merit functions exhibit a bias towards features that take a large variety of values. We present a scheme based on randomization for neutralizing this bias by normalizing the merits. The merit of a feature is normalized by division by the expected merit of a feature that is random noise taking the same distribution of values as the given feature. The noise feature is obtained by randomly permuting the values of the given feature. The scheme can be used for any merit function including the Gini and entropy measures. We demonstrate its effectiveness by applying it to the contextual merit defined by Hong (IBM Res. Rep. RC19964, 1994)."
