An Optimization Approach of Deriving Bounds between Entropy and Error from Joint Distribution: Case Study for Binary Classifications
In this work, we propose a new approach of deriving the bounds between entropy and error from a joint distribution through an optimization means. The specific case study is given on binary classifications. Two basic types of classification errors are investigated, namely, the Bayesian and non-Bayesi...
Autors principals: | Bao-Gang Hu, Hong-Jie Xing |
---|---|
Format: | Article |
Idioma: | English |
Publicat: |
MDPI AG
2016-02-01
|
Col·lecció: | Entropy |
Matèries: | |
Accés en línia: | http://www.mdpi.com/1099-4300/18/2/59 |
Ítems similars
-
Theoretical Bounds on Performance in Threshold Group Testing Schemes
per: Jin-Taek Seong
Publicat: (2020-04-01) -
Analysis of the Upper Bound of Dynamic Error Obtained during Temperature Measurements
per: Krzysztof Tomczyk, et al.
Publicat: (2022-10-01) -
On the lower bound error for discrete maps using associative property
per: E.G. Nepomuceno, et al.
Publicat: (2017-01-01) -
Computable error bounds with improved applicability conditions for collocation methods
per: A. H. Ahmed
Publicat: (1998-01-01) -
On approximating the error function
per: Zhen-Hang Yang, et al.
Publicat: (2016-11-01)