In RNN we do get one output for each time stamp of input right i.e. if we give input as "I am Good" we get three outputs representing I followed by am and Good so if we connect a dense layer followed by RNN layer does it just connect it with the final representation of our input.
I got this query because I'm new to RNN in most of the implementations either in Pytorch or Keras an RNN layer was mostly followed by a dense layer and I'm not sure how both are connected. Thanks for your help in advance.
