Pérdida Binaria Entropía Pérdida (BCE Loss) is a widely used función de pérdida in aprendizaje automático, particularly for clasificación binaria problems. It measures the performance of a model whose output is a probability value between 0 and 1. The goal of using BCE Loss is to minimize the difference between the predicted probabilities and the actual binary class labels (0 or 1).
Matemáticamente, la pérdida de Entropía Cruzada Binaria se define como:
BCE Loss = – (1/N) * Σ [y * log(p) + (1 – y) * log(1 – p)]
Donde:
- N = número de muestras
- y = etiqueta binaria real (0 o 1)
- p = probabilidad predicha de la clase positiva
Esta fórmula calcula la pérdida promedio en todas las muestras en dataset. The log function penalizes incorrect predictions more heavily, which helps the model to learn effectively. If the predicted probability is close to the actual class, the loss is small, and if it is far off, the loss is significant.
La Pérdida de Entropía Cruzada Binaria es particularmente útil en escenarios como regresión logística, neural networks for binary classification, and other machine learning models where outputs can be interpreted as probabilities. By optimizing this loss function during training, models can improve their accuracy in classifying binary outcomes.