Nota: La traducción de esta entrada está actualmente en revisión de calidad, por lo que parte del contenido se muestra temporalmente solo en inglés.
Esta entrada aún no se ha traducido a tu idioma, así que se muestra el original a continuación.
overfitting
This term is a technical specialization used primarily in statistics and machine learning. It describes a failure of generalization where a model captures random noise rather than the underlying pattern. In a professional context, it is often contrasted with underfitting, which occurs when a model is too simple to capture the trend.
As a noun, the term refers to the abstract phenomenon or the state of the model. When used as an adjective, it modifies the model or the specific characteristics of the algorithm. Because it is a technical gerund-derived noun, it is typically treated as an uncountable concept in data science discourse.
Meanings
Examples
The model is overfitting to the training set and failing on the test set.
I think we have a serious overfitting problem here.
Regularization is a common technique used to prevent overfitting.
Regularization is a common technique used to prevent overfitting.
Wait, is the accuracy too high? This looks like overfitting.
We need more diverse data to reduce the risk of overfitting.
The algorithm suffered from overfitting because the dataset was too small.
Maybe I should simplify the model to avoid overfitting.
Cross validation helps us detect overfitting early in the process.