상세 보기
초록
In traditional logistic regression model, every value of feature has the same weight. In this paper, we propose a new weighting method for logistic regression, which assigns a different weight to each feature value. A gradient approach is used to calculate the optimal weights of feature values. © 2016 ACM.
키워드
Classification; Feature Weighting; Logistic Regression
- 제목
- Calculating different weights in feature values in logistic regression
- 저자
- Lee, C.-H.
- 발행일
- 2016-11-26
- 유형
- Conference Paper
- 저널명
- ACM International Conference Proceeding Series
- 페이지
- 148 ~ 150