APPLICATION OF SUPERVISED LEARNING
DEEP LEARNING
|
Question
[CLICK ON ANY CHOICE TO KNOW THE RIGHT ANSWER]
|
If training accuracy is well above validation accuracy in all epochs, it is an indication of model
|
|
Underfitting
|
|
|
Overfitting
|
|
|
Correct fit
|
|
|
None of the above
|
Explanation:
Detailed explanation-1: -We can identify overfitting by looking at validation metrics, like loss or accuracy. Usually, the validation metric stops improving after a certain number of epochs and begins to decrease afterward. The training metric continues to improve because the model seeks to find the best fit for the training data.
Detailed explanation-2: -The standard deviation of cross validation accuracies is high compared to underfit and good fit model. Training accuracy is higher than cross validation accuracy, typical to an overfit model, but not too high to detect overfitting. But overfitting can be detected from the learning curve.
There is 1 question to complete.