Q22 — AWS AIF-C01 Ch.1

Question 22 of 100 | ← Chapter 1

A company wants to use a domain-specific model. It wishes to avoid building a model from scratch. Instead, it wants to adapt a pre-trained model to create a model for its specific task. Which ML strategy satisfies these requirements?

• A. Increase the number of epochs.
• B. Use transfer learning. ✓
• C. Decrease the number of epochs.
• D. Use unsupervised learning.

Correct Answer: B. Use transfer learning.

Explanation

This question tests understanding of ML strategies for efficiency and domain adaptation. Transfer learning leverages knowledge from a pre-trained model (often on large general datasets) and fine-tunes it for a new, related task—avoiding training from scratch and reducing time, cost, and data requirements. Increasing or decreasing epochs relates to training duration but does not address model reuse. Unsupervised learning lacks labeled data and does not inherently involve adapting pre-trained models. Thus, option B ('Use transfer learning') is correct.