Different training and testing conditionals in Seq2SeqAE
mohitsharma0690 opened this issue · comments
Mohit Sharma commented
In the LSTM autoencder that you have the training and testing inputs are different. That is during training for the decoder you try to predict p(x[t+1] | x[<=t])
but in testing you rather condition it on the output of previous timesteps i.e. p(x[t+1] | y[<=t])
.
This seems a bit off to me. Is it expected to be like this? Is there some reference somewhere for doing it this way?
Mohit Sharma commented
Ahh I see why is it done this way!!