Diferencia entre revisiones de «Fairness and bias correction in Machine Learning»
De FdIwiki ELP
(Página creada con «''Versión en español: Equidad y corrección de sesgos en Aprendizaje Automático'' Work in progress.») |
|||
Línea 1: | Línea 1: | ||
− | '' | + | ''Version in Spanish: [[Equidad y corrección de sesgos en Aprendizaje Automático|Equidad y corrección de sesgos en Aprendizaje Automático]]'' |
Work in progress. | Work in progress. | ||
+ | |||
+ | ==Metrics== | ||
+ | |||
+ | Most statistical measures of fairness rely on different metrics, so we will start by defining them. When working with a binary classifier, both the predicted and the actual classes can take two values: positive and negative. Now let us start explaining the different possible relations between predicted and actual outcome: | ||
+ | * True positive (TP): The case when both the predicted and the actual outcome are in the positive class. | ||
+ | * |
Revisión de 01:43 10 dic 2019
Version in Spanish: Equidad y corrección de sesgos en Aprendizaje Automático
Work in progress.
Metrics
Most statistical measures of fairness rely on different metrics, so we will start by defining them. When working with a binary classifier, both the predicted and the actual classes can take two values: positive and negative. Now let us start explaining the different possible relations between predicted and actual outcome:
- True positive (TP): The case when both the predicted and the actual outcome are in the positive class.