MDFT Academy Quizzes

How should you assemble your multiclass classification model?

You are building an app that can recognize handwriting. To train your model, you use a very large dataset with millions of handwritten examples. Your multiclass classifier is built up out of many slow-learning binary classification algorithms.

How should you assemble your binary classifiers into a multiclass classification model?

Choose the correct answer from the options below.

Please select at least one answer!

Congratulations, you are correct!

I'm sorry, your answer is not correct.

By using a 1-versus-all configuration is incorrect. In 1-versus-all, each binary classifier needs to compare one class against all other classes in the dataset. This will take a very long time if the binary classifiers are slow-learning.
By using a 1-versus-1 configuration is correct
By using an all-versus-all configuration is incorrect. There is no all-versus-all configuration.
By using an all-versus-1 configuration is incorrect. There is no all-versus-1 configuration.

Check out my video lesson to learn more about multiclass classification.

Learn about binary classification

5. Multiclass Classification

How should you assemble your multiclass classification model?