Entropia Cruzada Binária Entropia Perda (A.C. Loss) is a widely used função de perda in aprendizado de máquina, particularly for classificação binária 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).
Matematicamente, a Perda de Entropia Cruzada Binária é definida como:
BCE Loss = – (1/N) * Σ [y * log(p) + (1 – y) * log(1 – p)]
Onde:
- N = número de amostras
- y = rótulo binário real (0 ou 1)
- p = probabilidade prevista da classe positiva
Esta fórmula calcula a perda média em todas as amostras do conjunto de dados 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.
A Perda de Entropia Cruzada Binária é particularmente útil em cenários como regressão 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.