AI0-001 AI Concepts and Techniques Practice Question
A team is training a deep learning model for image classification. They observe that training accuracy is high but validation accuracy is low, indicating overfitting. Which TWO techniques should they apply to reduce overfitting? (Select TWO)
⚠ Common exam trap
CompTIA AI often tests the misconception that increasing model complexity (more layers or data reduction) helps generalization, when in fact these actions typically worsen 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
✓
Use L2 regularization
Option A, using L2 regularization, is correct because adding a weight-decay penalty (e.g., lambda * sum of squared weights) to the loss function constrains the magnitude of the model's weights, discouraging the network from fitting noise in the training set and thereby reducing overfitting. Option C, adding dropout layers, is correct because dropout randomly deactivates a fraction of neurons (e.g., p=0.5) during each training step, preventing units from co-adapting and forcing the network to learn more robust, generalizable features. Option B, increasing the learning rate, is not appropriate because a larger learning rate typically causes unstable or divergent training rather than reducing overfitting. Option D, increasing the number of layers, would raise model capacity and generally worsen overfitting. Option E, reducing training data size, would make overfitting more severe by giving the model even less data to generalize from.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✓
Use L2 regularization
Why this is correct
L2 regularization adds a penalty on squared weight magnitudes to the loss function, constraining the model's capacity to memorise training samples. This reduces the gap between high training accuracy and low validation accuracy caused by overfitting.
- ✗
Increase learning rate
Why it's wrong here
Raising the learning rate increases step size, worsening divergence and overfitting rather than regularising the model. It is tempting because a higher rate speeds convergence when training is slow, but the stem's high training accuracy already shows the network fits the training set; the fix requires dropout or weight decay, not faster gradient descent.
- ✓
Add dropout layers
Why this is correct
Dropout layers randomly deactivate a proportion of neurons during each training pass, forcing the network to learn redundant, distributed representations rather than memorising training samples. This directly counteracts the high training accuracy and low validation accuracy described, reducing overfitting without altering the model's architecture or requiring additional data.
- ✗
Increase the number of layers
Why it's wrong here
Adding layers increases model capacity, letting the network memorise training samples and widening the train-validation gap. It is tempting because deeper architectures often improve representational power, and would be correct when underfitting — but here it worsens the overfitting already observed.
- ✗
Reduce training data size
Why it's wrong here
Shrinking the training set gives the model fewer examples to generalise from, so validation accuracy drops further. It is tempting when data collection is costly or training time must fall, and would be correct for a quick prototype — but reducing overfitting needs more data or augmentation, not less.
Quick reference
Cloud Service Model Comparison
| Model | You Manage | Provider Manages | Examples |
|---|---|---|---|
| IaaS | OS, runtime, apps, data | Hardware, hypervisor, networking | EC2, Azure VMs, GCP Compute Engine |
| PaaS | Apps and data | OS, runtime, middleware, hardware | Elastic Beanstalk, Azure App Service |
| SaaS | Data and settings only | Everything else | Microsoft 365, Salesforce, Workday |
| FaaS / Serverless | Function code only | Infra, scaling, runtime | Lambda, Azure Functions, Cloud Run |
| CaaS | Containers and apps | Kubernetes, OS, hardware | EKS, AKS, GKE |
About these practice questions
This AI0-001 question is part of Courseiva's 962-question bank — original exam-style content with full explanations and wrong-answer analysis, never real exam questions or exam dumps. 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.