0

Model architecture training and computing error printing error

entire project link: Github Repository

In a classification task using Neural Network, I computed the fraction of misclassification as an error. And I am getting a validation error less than the training error? I was trying to find the model with the lowest validation error and select that model. I found the validation error to be less than the training error which is unusual.

Dipen Pandit
  • 1
  • 1
    Hi @DipenPandit, welcome to the site. There are other answers on this site addressing this very same question, for instance: [Validation loss is lower than the training loss](https://datascience.stackexchange.com/questions/39661/validation-loss-is-lower-than-the-training-loss) – noe Jul 02 '23 at 07:56

0 Answers0