COMPUTER SCIENCE AND ENGINEERING
MACHINE LEARNING
|
Question
[CLICK ON ANY CHOICE TO KNOW THE RIGHT ANSWER]
|
|
|
50%-60%
|
|
|
60%-70%
|
|
|
70%-80%
|
|
|
80%-90%
|
Detailed explanation-1: -Therefore, the epoch when the validation error starts to increase is precisely when the model is overfitting to the training set and does not generalize new data correctly. This is when we need to stop our training.
Detailed explanation-2: -Good accuracy in machine learning is subjective. But in our opinion, anything greater than 70% is a great model performance. In fact, an accuracy measure of anything between 70%-90% is not only ideal, it’s realistic. This is also consistent with industry standards.
Detailed explanation-3: -The answer is “NO”. A high accuracy measured on the training set is the result of Overfitting. So, what does this overfitting means? Overfitting occurs when our machine learning model tries to cover all the data points or more than the required data points present in the given dataset.
Detailed explanation-4: -Stop Training When Generalization Error Increases During training, the model is evaluated on a holdout validation dataset after each epoch. If the performance of the model on the validation dataset starts to degrade (e.g. loss begins to increase or accuracy begins to decrease), then the training process is stopped.