keras/docs/sources/objectives.md

Usage of objectives

An objective function (or loss function, or optimization score function) is one of the two parameters required to compile a model:

model.compile(loss='mean_squared_error', optimizer='sgd')

You can either pass the name of an existing objective, or pass a Theano symbolic function that returns a scalar and takes the following two arguments:

• y_true: True labels. Theano tensor.
• y_pred: Predictions. Theano tensor of the same shape as y_true.

For a few examples of such functions, check out the objectives source.

Available objectives

• mean_squared_error / mse
• mean_absolute_error / mae
• squared_hinge
• hinge
• binary_crossentropy: Also known as logloss.
• categorical_crossentropy: Also known as multiclass logloss. Note: using this objective requires that your labels are binary arrays of shape (nb_samples, nb_classes).