0
$\begingroup$

For example, if there are 5 major data sets for a certain topic. Would it be possible to see if a deployed network was trained off of one them?

How would one approach this?

$\endgroup$
1
$\begingroup$

If you can see the loss for a specific dataset, then the most probable set would be the one with the lowest loss.

$\endgroup$

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