Search the courses, subjects, tracks, games and features, or jump straight to a page.
4 cards from this section. Quick, good the night before a test.
What is evaluation in AI?
Think about what happens after the model is trained.
What is the training set used for?
Recall which dataset is fed into the model to learn.
What is the primary purpose of evaluating an AI model?
Consider the user experience with the model once it is deployed.
True or False: Overfitting occurs when a model performs poorly on both training and testing data.
Think about what happens when it learns too many details.
You have a dataset where you trained an AI to categorize images into two classes: cats and dogs. After evaluation, you found your model’s accuracy is 85%, but the precision is only 70%. What's the potential issue with the model?
Consider what high accuracy but low precision implies about false classifications.
In a K-Fold cross-validation with k=5, if you trained the model and got different accuracy scores for each fold, what could you conclude about the model’s performance?
Think about the importance of consistent performance across datasets.
5 more questions in this section. Enroll free to practise them all.
Enroll free