Loss indicates the magnitude of error your model made on its prediction. It’s a method of evaluating how well your algorithm models your dataset. If your predictions are totally off, your loss function will output a higher number. If they’re pretty good, it’ll output a lower one.

The following loss functions are available on the Platform:

Binary crossentropy
Categorical crossentropy
Mean absolute error
Mean squared logarithmic error
Mean squared error
Poisson
Squared hinge