Cargando…
100% Classification Accuracy Considered Harmful: The Normalized Information Transfer Factor Explains the Accuracy Paradox
The most widely spread measure of performance, accuracy, suffers from a paradox: predictive models with a given level of accuracy may have greater predictive power than models with higher accuracy. Despite optimizing classification error rate, high accuracy models may fail to capture crucial informa...
Autores principales: | Valverde-Albacete, Francisco J., Peláez-Moreno, Carmen |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Public Library of Science
2014
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC3888391/ https://www.ncbi.nlm.nih.gov/pubmed/24427282 http://dx.doi.org/10.1371/journal.pone.0084217 |
Ejemplares similares
-
Assessing Information Transmission in Data Transformations with the Channel Multivariate Entropy Triangle
por: Valverde-Albacete, Francisco J., et al.
Publicado: (2018) -
Improved image classification explainability with high-accuracy heatmaps
por: Preechakul, Konpat, et al.
Publicado: (2022) -
The Case for Shifting the Rényi Entropy
por: Valverde-Albacete, Francisco J., et al.
Publicado: (2019) -
The Rényi Entropies Operate in Positive Semifields
por: Valverde-Albacete, Francisco J., et al.
Publicado: (2019) -
Interactive knowledge discovery and data mining on genomic expression data with numeric formal concept analysis
por: González-Calabozo, Jose M, et al.
Publicado: (2016)