AI0-001 Machine Learning and Deep Learning Practice Question
Exhibit
Epoch 1/50 - loss: 2.3004 - acc: 0.5123 - val_loss: 2.5001 - val_acc: 0.4950 Epoch 10/50 - loss: 0.4567 - acc: 0.8712 - val_loss: 0.8903 - val_acc: 0.7520 Epoch 20/50 - loss: 0.1234 - acc: 0.9601 - val_loss: 0.9502 - val_acc: 0.7800 Epoch 30/50 - loss: 0.0456 - acc: 0.9905 - val_loss: 1.2004 - val_acc: 0.7705
Refer to the exhibit. What is the most likely issue and what action should be taken?
⚠ Common exam trap
CompTIA often tests the distinction between overfitting and underfitting by showing loss curves where training loss continues to drop while validation loss rises, tricking candidates into thinking the model needs more training or a lower learning rate.
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 early stopping around epoch 15
The training loss continues to decrease while the validation loss starts to increase after approximately epoch 15, which is a classic sign of overfitting. The model is memorizing the training data rather than generalizing, so applying early stopping around epoch 15 would prevent further divergence and preserve the best validation performance.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✗
Learning rate is too low; increase it
Why it's wrong here
A low learning rate produces slow but steady convergence, not the erratic or stalled loss curve shown. Raising it is tempting because learning-rate tuning is a frequent fix, but the exhibit's behaviour stems from another cause, so this adjustment would not correct the training outcome.
- ✗
Underfitting; increase model complexity
Why it's wrong here
Underfitting shows as poor accuracy on both training and validation sets, whereas the exhibit indicates the opposite pattern. Increasing model complexity is tempting because it is the standard remedy for high bias, but the observed curves reflect a different failure mode that added capacity would not fix.
- ✓
Overfitting; apply early stopping around epoch 15
Why this is correct
The exhibit shows training loss continuing to fall while validation loss rises after roughly epoch 15, the classic divergence signature of overfitting. Early stopping at that point halts training before the model memorises noise, preserving generalisation. Regularisation or more data would also help, but stopping is the direct fix.
- ✗
Data imbalance; use class weights
Why it's wrong here
Class weights address skewed label distributions, which the exhibit would show as one class dominating predictions or the confusion matrix. It is tempting because imbalance is common in classification, but the described symptom here points elsewhere, so reweighting classes would not resolve the actual training pathology.
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.