1
vote
Accepted
RNN/LSTM timeseries, with fixed attributes per run
You can create a sort of encoder-decoder network with two different inputs.
...
1
vote
Accepted
Training data for anomaly detection using LSTM Autoencoder
I will try to clarify the point as best as I can.
Ideally a model for anomaly détection should be trained with typical data, so that atypical data (anomalies) stand out.
However in practice this may ...
Only top scored, non community-wiki answers of a minimum length are eligible
Related Tags
lstm × 1103keras × 348
rnn × 310
deep-learning × 300
time-series × 287
neural-network × 225
machine-learning × 204
python × 164
tensorflow × 130
nlp × 83
forecasting × 61
cnn × 56
classification × 40
pytorch × 38
sequence-to-sequence × 35
regression × 34
sequence × 32
prediction × 29
predictive-modeling × 28
loss-function × 28
autoencoder × 28
training × 25
word-embeddings × 24
convolutional-neural-network × 19
multiclass-classification × 17