4
votes
Accepted
Why is it called a Seq2Seq model if the output is just a number?
The premise of your question is wrong. A model that goes from a sequence to a single prediction is simply NOT called a sequence to sequence to model.
The model type you are describing is called a ...
- 2,005
3
votes
Accepted
Seq2seq with RNNs, how is the training loop performed?
In seq2seq RNN training, we usually use a technique called "teacher forcing." With teacher forcing, the actual (ground truth) output word at each timestep is fed as input to the decoder in ...
Only top scored, non community-wiki answers of a minimum length are eligible
Related Tags
seq2seq × 25recurrent-neural-networks × 11
transformer × 9
natural-language-processing × 6
deep-learning × 4
sequence-modeling × 4
long-short-term-memory × 3
attention × 3
machine-translation × 3
encoder-decoder × 3
neural-networks × 2
reinforcement-learning × 2
papers × 2
applications × 2
time-series × 2
pretrained-models × 2
bidirectional-rnn × 2
comparison × 1
tensorflow × 1
reference-request × 1
backpropagation × 1
generative-adversarial-networks × 1
bert × 1
hidden-layers × 1
reinforce × 1