How interpret keras training loss without compare with validation loss?

Question

I have several implementation of the same neural network, but each one with different starting parameter.

This is one of my plot comparing the training loss of the base experiment with the training loss of another experiment.

I have also other exaples:

May anyone point me to some instruction on how understand these output from the keras fit()? Note that I don't have any validation set.

Thanks

Siva Dorai · Answer

In Keras model it defines its own bias and weight..and eventually they converge closer to Y as loss decreases..the output graphs would change based on learning rate, batch size and epochs

Abhishek Singla · Answer

Less loss means low bias on training set. It always recommended to first aim for a model with low bias so you go and choose "loss_exp-resLayer10".
It would have been better if we've loss for validation set because we can't assess the "overfitting". So in case, if your chosen model doesn't perform well on test data then use regularisation or any other method to overcome the overfitting issue.

How interpret keras training loss without compare with validation loss?

2 Answers

Add your own answers!

Ask a Question