0
$\begingroup$

What is the relation between any suitable measure of model complexity, number of training examples and network size in deep learning?

$\endgroup$
2
  • $\begingroup$ Please name one such measure of model complexity, so we can elaborate from there. $\endgroup$
    – lpounng
    Commented Jun 16, 2023 at 2:11
  • $\begingroup$ Let us use VC complexity. $\endgroup$ Commented Jun 16, 2023 at 9:28

1 Answer 1

0
$\begingroup$

In general, the higher the model complexity, the more training examples (and computation time) is required for the model to learn.

In general, network size is directly proportional to model complexity. The larger the network size, the more parameters, thus higher the complexity.

$\endgroup$

You must log in to answer this question.

Not the answer you're looking for? Browse other questions tagged .