2

If loss is decreasing but val_loss not, what is the problem and how can I fix it?

I get such vague result: enter image description here

user3486308
  • 1,260
  • 5
  • 16
  • 27
  • Are you sure this isn't backwards? It would be odd for validation loss to be consistently lower than train. Not impossible, but atypical. – Sean Owen Mar 09 '19 at 22:11

1 Answers1

4

This indicates that model is not generalizing (it is over-fitting). Few options are :

  1. Get more training data
  2. Reduce complexity of model (Number of LSTM layers, complexity of dense layers)

Andrew NG has a good video on this topic :

https://www.youtube.com/watch?v=OSd30QGMl88

A tutorial specific to LSTM :

https://machinelearningmastery.com/diagnose-overfitting-underfitting-lstm-models/

Shamit Verma
  • 2,239
  • 1
  • 8
  • 14