AI0-001 Machine Learning and Deep Learning Practice Question
A machine learning engineer is training a deep neural network for image classification. The training loss decreases steadily, but the validation loss starts to increase after 20 epochs. The engineer wants to implement a technique that dynamically adjusts the learning rate during training to improve convergence and generalization. Which method should the engineer use?
⚠ Common exam trap
Watch out — candidates often confuse regularization techniques like dropout with optimization techniques that adjust the learning rate, even though both can help with overfitting.
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
✓
Learning Rate Scheduler with exponential decay
A learning rate scheduler with exponential decay dynamically reduces the learning rate as training progresses, which helps the model converge more smoothly and can improve generalization. This directly addresses the need to adjust the learning rate during training to combat the rising validation loss, unlike fixed learning rates or other regularization techniques that do not modify the learning rate.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✗
Stochastic Gradient Descent (SGD) with a fixed learning rate
Why it's wrong here
SGD with a fixed learning rate does not adapt the learning rate during training. While it can converge, it often requires manual tuning and may oscillate or converge slowly. In this scenario, the validation loss is increasing, indicating overfitting; a fixed learning rate does not address this dynamic issue and may exacerbate instability if not properly tuned.
- ✗
Batch Normalization
Why it's wrong here
Batch Normalization normalizes layer inputs to stabilize and accelerate training, but it does not adjust the learning rate. While it can improve convergence and sometimes act as a regularizer, it does not provide the dynamic learning rate adjustment requested. Therefore, it does not fulfill the specific need in the scenario.
- ✗
Dropout regularization
Why it's wrong here
Dropout randomly deactivates neurons during training to reduce overfitting, which could help with the increasing validation loss. However, it does not dynamically adjust the learning rate. The question specifically asks for a technique that adjusts the learning rate during training, so dropout does not meet that requirement even though it addresses overfitting.
- ✓
Learning Rate Scheduler with exponential decay
Why this is correct
An exponential decay learning rate scheduler reduces the learning rate over time, which can help the model settle into a deeper minimum and improve generalization. As training progresses, smaller learning rates allow finer adjustments to weights, potentially mitigating the increasing validation loss by preventing overshooting and encouraging convergence to a smoother minimum.
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 and reviewed by Johnson Ajibi, MSc IT Security
Senior Network & Security Engineer · founder of Courseiva
Last reviewed September 2026 · checked against the official CompTIA exam blueprint
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.