1
$\begingroup$

In my understanding, each hidden layer in neural network extract the implicit information of the features. So, can we know what kind of information does hidden layers process and how to understand them?

$\endgroup$
1
$\begingroup$

Yes (especially vision problems) and people have done that. We also had good coverage in here.

See @Chaconne's answer for this question

What did my neural network just learn? What features does it care about and why?

I also had an another there: in other domain, and when we have a large number of parameters, many people stop focusing on what are these implicit features, and the importance of the features.

$\endgroup$
  • $\begingroup$ @user195278 if the answer helped you to solve your struggle (it seems so), mark is as accepted answer. $\endgroup$ – Jan Kukacka Feb 27 '18 at 13:23

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.