Is one hot encoding needed only with softmax? Or is it needed with sigmoid as well?
Need of one hot encoding
Hey @ambika11, one hot encoding is used when you have to predict or classify more than two classes. And softmax function is used in case we have to predict probabilities of multiple classes. So yes indirectly you can say that one hot encoding has to be used whenever you are using softmax. But one hot is used only with softmax is not the correct notion !
I hope you are able to understand !
Happy Learning 
I hope I’ve cleared your doubt. I ask you to please rate your experience here
Your feedback is very important. It helps us improve our platform and hence provide you
the learning experience you deserve.
On the off chance, you still have some questions or not find the answers satisfactory, you may reopen
the doubt.