I found people used deep neural network to get optimal policy by solving a nonconvex optimization problem. Moreover, they didn't use any set of training data and claimed that it's the difference between their approach and the supervised learning. I wonder can people set loss function of neural network by themselves instead of choosing cross entropy or mean square error?

My experience in machine learning is very limited. I audited two machine learning courses offered by applied math department in my school. I read twenty or more papers on the application of machine learning. I began to use Keras very recently.

  • 1
    $\begingroup$ I think it'd be better if you ask these as separate questions with more context.. $\endgroup$ Jul 4 at 7:58
  • 1
    $\begingroup$ Hello. Please, follow the suggestion above. Edit this post to ask only one question and provide more context/background, i.e. what do you know about neural networks and/or machine/deep learning so far? $\endgroup$
    – nbro
    Jul 4 at 11:55
  • $\begingroup$ Thanks very much. I will ask them as separate questions with more context. $\endgroup$ Jul 4 at 14:41
  • $\begingroup$ This Towards Data Science post on deep learning to do quantile regression gets into how to implement your own loss function. $\endgroup$
    – Dave
    Jul 6 at 13:52

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.