Question

Which is to be compromised- Validation loss (or) Validation Accuracy??​

Answer 1

Answer:

While training a deep learning model I generally consider the training loss, validation loss and the accuracy as a measure to check overfitting and under fitting. ... Some argue that training loss > validation loss is better while some say that validation loss > training loss is better.

Answer 2

Answer:

 Answer: While training a deep learning model I generally consider the training loss, validation loss and the accuracy as a measure to check overfitting and under fitting. ... Some argue that training loss > validation loss is better while some say that validation loss > training loss is bette