Compare image classification and image generation.
Match the model type to its output.
Choose two correct statements.
Discriminative models predict classes or values, while generative models create new content from a learned distribution.
Detailed explanation
It is used for prediction of existing categories or values.
It is used for prediction of existing categories or values.
It produces new content or samples.
It produces new content or samples.
It can contain errors and rights risks.
It can contain errors and rights risks.
It commonly returns a class, score, or probability.
It commonly returns a class, score, or probability.
Try it yourself
An example you can run in a temporary verification environment.
AWS公式AIF-C01 Domain 1.1の判別モデル、生成モデル、ユースケースを確認する。Expected result
予測とコンテンツ生成の目的からモデルの種類を区別できる。Key points
- Discriminative
- Generative
- Output purpose
Notes
- Environment: AWS公式AIF-C01試験ガイドとAWS公式ドキュメントの確認
- Command output formatting can vary slightly by distribution or tool version.
- Run the example in a temporary directory or process when possible.
Foundation review
Read the scope first
Check whether the command acts on the current shell, a new process, an existing process, or a file.
Verify the observable result
Use the supplied command and compare the output with the expected result.