Could you please elaborate on - “Embedding layer also gets trained”. How does that happen and what gets changed?
Embeddding Layer Training
hey @rishverma ,
There are to ways to use word embeddings in your model either create your custom word embeddings using Embedding Layer in keras or use pre-Trained word Embeddings like Glove ( provided by Standford ),FastText ( by FaceBook ).
So if you are using embedding Layer , then to get much general and better understanding of the text provided as input , weights and bias of this embedding gets updated the same way other layers like RNN , Dense ,etc. are updated using backpropagation. Hence , in this way embedding layer gets trained.
I hope this would have resolved your doubt.
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.