Search the courses, subjects, tracks, games and features, or jump straight to a page.
3 cards from this section. Quick, good the night before a test.
Define what model evaluation is.
Think about why we test models.
What is the main purpose of the training set?
What do we do with data before we test it?
What is model evaluation?
Recall what we do after training a model.
Which of the following is used to assess the performance of models?
Consider which dataset isn't used during training.
You have a dataset with 90% class A and 10% class B. Your model predicts all as class A. Discuss how it would score on accuracy, precision, and recall.
Remember the definitions of each metric.
Design a plan for evaluating a new machine learning model intended for medical diagnosis showing both potential overfitting and underfitting.
Think about what methods help in avoiding each problem.
5 more questions in this section. Enroll free to practise them all.
Enroll free