0
$\begingroup$

I need some help in Interpreting a curve val_loss and loss in keras after training a model

These are the learning curves: after 100 epoch of training

Improve this question
$\endgroup$

1 Answer 1

Reset to default
1
$\begingroup$

The training loss decreases while the validation loss increases, which is a clear sign of overfitting. This means that your model is too specific to the training dataset and do not generalize to the testing dataset. To solve that problem you can decrease the complexity of the model or add regularization.

Improve this answer
$\endgroup$

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge you have read our privacy policy.

Not the answer you're looking for? Browse other questions tagged or ask your own question.