keras_API汇总积累（熟读手册）三损失函数

mean_squared_error(y_true, y_pred)

mean_absolute_error(y_true, y_pred)

mean_absolute_percentage_error(y_true, y_pred)

mean_squared_logarithmic_error(y_true, y_pred)

squared_hinge(y_true, y_pred)

hinge(y_true, y_pred)

categorical_hinge(y_true, y_pred)

logcosh(y_true, y_pred)

categorical_crossentropy(y_true, y_pred)

sparse_categorical_crossentropy(y_true, y_pred)

binary_crossentropy(y_true, y_pred)

kullback_leibler_divergence(y_true, y_pred)

poisson(y_true, y_pred)

cosine_proximity(y_true, y_pred)