0
$\begingroup$

enter image description here

This question is from a uni module about machine learning. I'm a bit stuck as I can't relate it to the bias-variance trade-off, to me the question implies all models have something to do with the trade off but I can only think of B being overfitted on its training data implying a low bias and high variance. I don't know how to explain A having both a high error in testing and training, and C I'm lost.

$\endgroup$

1 Answer 1

1
$\begingroup$

It seems to me differently:

B. An example of small bias and variance.

A. A large bias (low quality at the training stage).

C. A large variance (losses for different data vary greatly).

But all this is said, assuming that the loss scale does not need to be taken literally. Otherwise, I also don't know how to interpret graphs A and C: absolutely the same losses on the test, which do not depend on the quality of training.

$\endgroup$
1
  • 2
    $\begingroup$ thanks :), I see where I was I wrong now, these graphs were confusing me for a while and I wasn't thinking about it properly $\endgroup$
    – pixel.t87
    Dec 7, 2023 at 13:17

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge you have read our privacy policy.

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