1
vote
Out-of-Range Target Variable in Sequence-based Machine Learning Model
"Interpolation is easy. Extrapolation is hard."
Extrapolating might be the right thing to do.
But always be suspect of a model that is leading
you to big unexplored regions of the state ...
1
vote
LSTM For Predicting Vector Sequences
There are many problems with that code:
It uses a lot of LSTM layers. Instead, start with a single LSTM.
As you are working with text:
Use token indices as input and have an initial embedding layer
...
1
vote
Converting a Standard LSTM RNN over to a Transformer Model
With a bit of elastic net, dynamic gradient clipping and adjustments to the transformer model build training is progressing nicely now.
Here is the build that fixed it:
...
Only top scored, non community-wiki answers of a minimum length are eligible
Related Tags
lstm × 1174keras × 354
rnn × 331
time-series × 313
deep-learning × 306
neural-network × 231
machine-learning × 225
python × 168
tensorflow × 137
nlp × 93
forecasting × 73
cnn × 54
classification × 43
pytorch × 42
regression × 41
sequence-to-sequence × 38
sequence × 33
prediction × 31
loss-function × 28
predictive-modeling × 27
word-embeddings × 26
training × 25
autoencoder × 22
normalization × 18
gru × 18