Early Stopping for Overfitting in Deep Learning
A team is training a deep learning model for image classification. The training loss decreases rapidly but validation loss starts increasing after a few epochs. Which regularization technique should be applied to mitigate this issue?
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
✓
Early stopping
Early stopping halts training when validation loss starts increasing, preventing overfitting. Option A (data augmentation) is wrong because it increases data diversity but does not stop training when validation loss increases. Option B (L2 regularization) is wrong because it penalizes large weights but does not directly address the issue of validation loss increasing. Option D (dropout) is wrong because while it helps generalize by randomly dropping neurons, it does not stop training when overfitting occurs.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✗
Data augmentation
Why it's wrong here
Augmentation enlarges the training set with transformed copies, which reduces overfitting only when the model has insufficient data variety; here the gap between falling training loss and rising validation loss is countered by randomly deactivating units during training, forcing redundant representations. Augmentation suits scarce datasets, not this epoch-wise divergence.
- ✗
L2 regularization
Why it's wrong here
L2 reduces overfitting but doesn't stop training when validation loss increases.
- ✓
Early stopping
Why this is correct
Rising validation loss alongside falling training loss signals overfitting. Early stopping halts training at the epoch where validation loss is minimal, restoring the best generalising weights. This directly mitigates the divergence described, unlike dropout or weight decay, which alter the architecture or loss function.
- ✗
Dropout
Why it's wrong here
Dropout randomly deactivates units per training step, which curbs overfitting but also slows convergence and adds variance; the scenario's rapid training-loss drop with validation loss rising after a few epochs is addressed by penalising large weights through the loss function, shrinking the model's effective capacity directly.
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.