Choosing transfer learning | AWS Certified AI Practitioner (AIF-C01) original practice question

1.3Standard

A pretrained model is available for a small business dataset.

Compare reuse options.

Choose two descriptions.

Hint 1: Focus on the requirement

Identify what must change and what must remain unchanged. Then choose the command whose scope matches that requirement.

Hint 2: Check each command's role

Separate commands that display information, change state, remove data, or affect a child process.

学習済み表現を再利用し、対象タスクのデータや計算量を減らせる場合がある: Existing knowledge can reduce data and compute.
対象データの分布・ライセンス・性能を確認し、必要な層だけ調整する: Source and use must fit.
転移学習では対象データの品質やライセンスを確認しなくてよい: Source constraints remain.
少量データなら必ず全パラメータを再学習する: Compute and overfitting risks exist.

Detailed explanation

CorrectReuse pretrained representations when they fit the target task

Existing knowledge can reduce data and compute.

CorrectCheck target distribution, license, and performance before tuning selected layers

Source and use must fit.

IncorrectTarget data quality and license do not matter for transfer learning

Source constraints remain.

IncorrectSmall data always requires retraining every parameter

Compute and overfitting risks exist.

An example you can run in a temporary verification environment.

AWS公式AIF-C01 Domain 1.3の転移学習、ファインチューニング、モデル適合性を確認する。

学習済みモデルを再利用する利点と、対象データ・ライセンス確認の必要性を説明できる。

Foundation review

Check whether the command acts on the current shell, a new process, an existing process, or a file.

Use the supplied command and compare the output with the expected result.

Question IDAWS-AIF-417

EnvironmentAWS公式AIF-C01試験ガイドとAWS公式ドキュメントの確認

Last technical review2026-08-20