- In machine learning, underfitting is the situation in which the learned model is not a good approximation to the true underlying distribution in the training data.
Which of the following approaches reduces the chances of underfitting?
A.Using ensemble methods such as bagging
B.Gathering more training data
C.Choosing a more complex model
D.Applying regularization methods such as dropout
- In machine learning, overfitting is the situation in which the learned model is too good a fit to the training data and does not generalize well to unseen test data. The problem is that the model is adapting to the noise and outliers in the data.
Which of the following approaches reduces the chances of overfitting?
A.Using ensemble methods such as bagging
B.Gathering more training data
C.Choosing a more complex model
D.Applying regularization methods such as dropout
- Suppose that in a classification problem with a highly imbalanced dataset, the majority class is observed 99% of the time. Your model has 99% accuracy on the test data. Which of the following statements is true in this situation?
(1)Accuracy may not be a good indicator for imbalanced data problems.
(2)Accuracy is a good metric for all types of machine learning problems.
(3)Precision and recall are good metrics for imbalanced da