AI0-001 Machine Learning and Deep Learning Practice Question
A self-driving car company uses a reinforcement learning agent to navigate. The agent was trained in a simulated environment and achieved high rewards. When deployed in the real world, the agent fails to avoid obstacles. The team collects real-world driving data and uses it to fine-tune the model. However, fine-tuning leads to catastrophic forgetting of the simulated knowledge. Which technique should the team use to mitigate this? A. Increase the learning rate during fine-tuning. B. Use elastic weight consolidation (EWC) to regularize important weights. C. Train the model from scratch using only real-world data. D. Increase the number of layers in the network.
⚠ Common exam trap
CompTIA often tests the concept of catastrophic forgetting by presenting fine-tuning as a solution and then offering tempting but incorrect options like increasing learning rate or network depth, which candidates might mistakenly associate with improving generalization or capacity.
Answer choices
Why each option matters
Answer the question above first, then reveal the full breakdown to understand why each option is right or wrong.
Correct answer & explanation
✓
Use elastic weight consolidation (EWC) to regularize important weights.
Elastic Weight Consolidation (EWC) is a regularization technique specifically designed to prevent catastrophic forgetting when fine-tuning a neural network on a new task. It identifies the weights that are most important for the original task (simulated driving) and penalizes large changes to those weights during fine-tuning on real-world data, thereby preserving the learned knowledge while adapting to the new domain.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✗
Increase the number of layers in the network.
Why it's wrong here
Adding layers increases model capacity but does nothing to prevent weight overwriting during gradient updates, so catastrophic forgetting persists. It is tempting because deeper networks can capture richer representations, and would help if the simulated data were insufficient rather than being erased by fine-tuning.
- ✓
Use elastic weight consolidation (EWC) to regularize important weights.
Why this is correct
Elastic weight consolidation adds a regularisation penalty that protects weights important to previously learned simulated tasks, allowing real-world fine-tuning without overwriting that knowledge. This directly counteracts catastrophic forgetting, satisfying the stem's requirement to retain simulation knowledge while adapting to real driving.
- ✗
Train the model from scratch using only real-world data.
Why it's wrong here
Discarding simulated training data abandons the knowledge the team wants to preserve, directly causing the forgetting rather than mitigating it. It is tempting because real-world-only training removes the simulation-to-reality gap, and would be correct if simulated experience were misleading or unavailable.
- ✗
Increase the learning rate during fine-tuning.
Why it's wrong here
Raising the learning rate accelerates weight updates, overwriting the parameters encoding simulated driving and worsening catastrophic forgetting. It tempts because a higher rate speeds adaptation to real-world data, and would be correct when fine-tuning on a large, representative dataset where prior task performance need not be retained.
About these practice questions
One of 962 original AI0-001 practice questions on Courseiva, each with a full explanation and wrong-answer analysis — not exam dumps or protected exam content. Learn why practice questions differ from exam dumps →
JA
Written by Johnson Ajibi, MSc IT Security
Senior Network & Security Engineer · founder of Courseiva
This AI0-001 practice question is part of Courseiva's free CompTIA certification practice question bank. Courseiva provides original exam-style practice questions with explanations, topic-based practice, mock exams, readiness tracking, and study analytics to help learners prepare for the AI0-001 exam.