Функция потерь — математическая функция, которая измеряет различие между предсказанием модели и правильным целевым значением. Во время обучения параметры модели настраиваются для минимизации этой потери. Разным задачам нужны разные функции потерь, такие как среднеквадратичная ошибка для регрессии или log loss для вероятностной классификации.
During training or testing, a mathematical function that calculates the loss on a batch of examples. A loss function returns a lower loss for models that makes good predictions than for models that make bad predictions. The goal of training is typically to minimize the loss that a loss function returns. Many different kinds of loss functions exist. Pick the appropriate loss function for the kind of model you are building. For example: - L~2~ loss (or Mean Squared Error) is the loss function for linear regression. - Log Loss is the loss function for logistic regression.
A loss function is the difference between the training label values and the prediction made by the model. The parameters of the model are estimated by minimizing the loss function.