Question
AI, Machine Learning, and IT Careers Unit Test 11 of 2011 of 20 Items Question Jasmine is testing a machine learning (ML) algorithm that classifies images as being ducks or not ducks. Her model has been built and trained. The testing data consists of 10 images of ducks, and the model correctly identifies them (within an appropriate margin of error) to be ducks. What is wrong with her testing procedure?(1 point) Responses The testing data is outdated. The testing data is outdated. The testing data is biased. The testing data is biased. The testing data is too large. The testing data is too large. The testing data is homogenous. The testing data is homogenous. Skip to navigation page 1 of 1
Answers
GPT-4o mini
The issue with Jasmine's testing procedure is that **the testing data is homogenous.**
This means that all the testing images are of ducks, which does not effectively test the algorithm's ability to classify images that are not ducks. A proper test set should include a balanced mix of both classes (ducks and not ducks) to evaluate the model's performance accurately across all potential inputs.
This means that all the testing images are of ducks, which does not effectively test the algorithm's ability to classify images that are not ducks. A proper test set should include a balanced mix of both classes (ducks and not ducks) to evaluate the model's performance accurately across all potential inputs.