AI0-001 Machine Learning and Deep Learning Practice Question
A data scientist is training a deep neural network for sentiment analysis. The training loss decreases steadily but the validation loss starts to increase after 10 epochs. What is the most likely cause and best corrective action?
⚠ Common exam trap
CompTIA often tests the distinction between underfitting and overfitting by describing a diverging validation loss after initial improvement, leading candidates to mistakenly choose underfitting or vanishing gradients when the key indicator is the validation loss increase after a period of good training loss reduction.
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
✓
Overfitting; apply dropout and early stopping
The scenario describes a classic case of overfitting: the training loss decreases steadily, indicating the model is learning the training data well, but the validation loss increases after 10 epochs, meaning the model is memorizing noise and patterns specific to the training set rather than generalizing. The best corrective action is to apply dropout (which randomly drops neurons during training to reduce co-adaptation) and early stopping (which halts training when validation performance degrades), both of which are standard regularization techniques for deep neural networks.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✗
Underfitting; increase model complexity
Why it's wrong here
Underfitting shows high training loss alongside high validation loss, because the model cannot capture the training data's structure. Here training loss falls steadily, so capacity is sufficient. The rising validation loss indicates overfitting, corrected by early stopping, dropout, weight decay or additional training data.
- ✗
Vanishing gradients; use ReLU activation
Why it's wrong here
Vanishing gradients cause training loss to stall or barely fall, not to keep decreasing while validation loss climbs. ReLU activations mitigate that separate problem. The pattern described is overfitting, so the corrective action is regularisation or early stopping rather than changing the activation function.
- ✗
Data leakage; shuffle data before splitting
Why it's wrong here
Data leakage means test data contaminates training, which typically produces unrealistically low validation loss, not a rising one. Shuffling before splitting is a preprocessing safeguard. The described divergence is overfitting, addressed by early stopping, dropout, weight decay or more training data.
- ✓
Overfitting; apply dropout and early stopping
Why this is correct
Diverging training and validation loss after 10 epochs signals overfitting: the model memorises training data and generalises poorly. Dropout regularises the network, while early stopping halts training at the point validation loss begins rising, restoring generalisation.
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.