Machine Learning

Q6) [10 pts] In this problem, we will see how you can debug a classifier by looking at its train and test errors. Consider a classifier trained until convergence on some training data Dtrain, and tested on a separate test set Dtest. You look at the test error, and find that it is very high. You then compute the training error and find that it is close to 0 . (a) Short Answer: What is this scenario called? (b) Select ALL that apply: Which of the following are expected to help? A) Increasing the training data size. B) Decreasing the training data size. C) Increasing model complexity (For example, if your classifier is a decision tree, increase the depth). D) Decreasing model complexity. E) Training on a combination of Dtrain and Dtest and test on Dtest F) None of the above