New answers tagged

0 votes

How to add multiple embeddings (layers) to LSTM layer

Let's consider the main approaches: Embed each categorical feature, then LSTM on top. I think you want to opt for individual recurrent layers when the features are sort of mutually exclusive, i.e. ...
Luca Anzalone's user avatar
0 votes

Does it makes sense to train the model on whole data?

Absolutely not! This is a basic tenet of Machine Learning. Due to the stochastic nature of training an ML model it's important to test the final model to ensure it satisfies our key criteria. The ...
fswings's user avatar
  • 298
0 votes

Prediction interval around LSTM time series forecast

You can easily quantify uncertainty for time series models using conformal prediction https://github.com/valeman/awesome-conformal-prediction Here is an article about doing it with classical models ...
valeman's user avatar
  • 11

Top 50 recent answers are included