In section of http://www.deeplearningbook.org/contents/mlp.html, the author says

"More rarely, softmax functions can be used inside the model itself, if we wish the model to choose between one of n different options for some internal variable"

I'm trying to think of an example of when one would want to do this. Can someone give an example (or point to a paper) where softmax is used inside the model?

  • 1
    $\begingroup$ I'm voting to close this question as off-topic because It is both a self-study question and is off topic because it is about programming. $\endgroup$ – Michael R. Chernick Mar 24 '17 at 21:54
  • $\begingroup$ It's about machine learning (which is on topic). "I'm trying to think of an example" doesn't appear to be clearly a self study question to me. $\endgroup$ – Glen_b -Reinstate Monica Mar 26 '17 at 4:22

Your Answer

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

Browse other questions tagged or ask your own question.