...

/

Model Validation - I

Model Validation - I

Study model validation in Keras.

Validation

The model performance on the training data is not a good indicator of how well the model will perform on the test data. For this, we should use the validation data to test the model’s performance.

Validation data is only held out from training and is only used to test the model’s performance.

The validation set checks overfitting and therefore eliminates errors that can be caused for future predictions and observations if an analysis corresponds too precisely to a specific dataset.

In ...

Effect of model complexity on the error