Hyperparameters and Error Metric
vgoklani opened this issue · 0 comments
vgoklani commented
Just a few basic questions:
- Why did you choose this particular network structure? Since you have two LSTM layers, would you get better performance from using the "relu" activation function?
- Why are you only running 1 epoch? Is that just for testing purposes?
- How are you measuring errors for forecasting, what is your chosen error metric? Most other results use RMSE, however, is there a better metric? RMSE feels like a necessary but not sufficient condition for measuring the "learning quality" of a neural net.