I am making an RNN for sentiment classification. What activation functions would you use in order to achieve this goal (excluding the one present in the output layer)?

  • $\begingroup$ A quick search found this stackoverflow answer gives a very good explanation of the advantages of different activation functions in an RNN. Regarding the output activation, you can use sigmoid for binary classification or softmax for >=2 classes. $\endgroup$ – primussucks Aug 11 '20 at 18:01

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.