What are the criteria used to choose between plain vanilla RNN and LSTM RNN when you have to model a generic time series?
Solved – How to choose between plain vanilla RNN and LSTM RNN when modelling a time series
lstmneural networksrecurrent neural networktime series
Best Answer
Empirically. The criteria is the performance on the validation set. Typically LSTM outperforms RNN, as it does a better job at avoiding the vanishing gradient problem, and can model longer dependences. Some other RNN variants sometimes outperform LSTM for some tasks, e.g. GRU.
FYI: