A team is building a model to generate product descriptions for an e-commerce site. They have a small dataset of 5,000 high-quality product descriptions. The products are in a niche domain (e.g., handmade crafts). They have a limited compute budget. What is the most appropriate approach?

Train a language model from scratch on the 5,000 descriptions.

Fine-tune a small pre-trained model with a high learning rate for many epochs.

Use a pre-trained model as a fixed feature extractor and train a template-based generator.

Fine-tune a pre-trained language model like GPT on the 5,000 descriptions.

NetAppCertified AI Expert

Domain 2Objective 6

Compare the Differences Between Model Building and Fine-Tuning Models CERTIFIED-AI-EXPERT Practice Questions (Page 4)

Part of the AI Lifecycle domain, which accounts for 27% of the CERTIFIED-AI-EXPERT exam. NetApp does not publish an official question count, but from its 90-minute exam (~35–60 total, ~9–16 in this domain), expect 1–2 from this objective — we provide 16 practice questions to prepare you well beyond it. (estimate)

16questions here

4free pages

5concepts

27%of the exam

Questions 16–16

16application · medium
A team is building a model to generate product descriptions for an e-commerce site. They have a small dataset of 5,000 high-quality product descriptions. The products are in a niche domain (e.g., handmade crafts). They have a limited compute budget. What is the most appropriate approach?
Select an answer first

Finished these 1 questions?

Review the revealed explanations, or continue through the curriculum.

No more pagesBack to CERTIFIED-AI-EXPERT

Free Basic Practice is a study aid with revealable answers — not a scored exam. Examers.io is independent and not affiliated with or endorsed by NetApp. “CERTIFIED-AI-EXPERT” is a trademark of its owner, used for identification only.

Compare the Differences Between Model Building and Fine-Tuning Models CERTIFIED-AI-EXPERT Practice Questions (Page 4)

Questions 16–16

A team is building a model to generate product descriptions for an e-commerce site. They have a small dataset of 5,000 high-quality product descriptions. The products are in a niche domain (e.g., handmade crafts). They have a limited compute budget. What is the most appropriate approach?

Keep studying — AI Lifecycle