If loss is decreasing but val_loss not, what is the problem and how can I fix it?
Asked
Active
Viewed 7,171 times
2
-
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 Answers
4
This indicates that model is not generalizing (it is over-fitting). Few options are :
- Get more training data
- 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
