1
$\begingroup$

In Keras, the first object returned in the score list is loss.

score = model.evaluate(X_test, y_test,verbose=1)
print(score)

[1] [0.025217213829228164, 0.99487179487179489]

Is this the same thing as variance?

$\endgroup$
3
$\begingroup$

No. Loss measures the error between your predicted values and true values in a given train set. Whereas variance mesures how your model performs (i.e. how the loss changes) on different training sets. Also, variance is an atribute of a given model whereas loss depends on your dataset.

In other words, we can also say that loss on different sets is used to measure variance of a given model.

$\endgroup$

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.