AI0-001 AI Concepts and Foundations Practice Question
Exhibit
Epoch 10/10 - loss: 0.01 - accuracy: 0.99 - val_loss: 0.45 - val_accuracy: 0.85
Refer to the exhibit. A data scientist observes the training output. Which issue is most likely?
⚠ Common exam trap
CompTIA often tests the distinction between overfitting and underfitting by showing a loss curve where training loss is low but validation loss rises, tricking candidates who focus only on the low training loss without checking validation performance.
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
The exhibit shows training loss decreasing while validation loss increases after a certain epoch, which is the classic signature of overfitting. The model is memorizing the training data rather than learning generalizable patterns, leading to poor performance on unseen data.
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
Why it's wrong here
Underfitting describes a model too simple to capture training patterns, shown by high training and validation loss together. The exhibit's training output would instead show training loss falling while validation loss rises, which is overfitting. Underfitting is the right diagnosis when both losses plateau at a high value.
- ✗
Data augmentation failure
Why it's wrong here
Data augmentation failure would show as degraded accuracy on transformed inputs or a training set that no longer matches validation distribution. The exhibit's diverging training and validation loss curves indicate overfitting, not augmentation problems. Augmentation is the correct focus when validation accuracy drops only on augmented classes.
- ✓
Overfitting
Why this is correct
Overfitting is indicated when training loss keeps falling while validation loss stops improving or rises, meaning the model memorises training data and generalises poorly. The widening gap between the two curves in the exhibit is the diagnostic signal.
- ✗
Model compression
Why it's wrong here
Model compression reduces size and inference cost after training; it does not produce the diverging loss curves shown. The exhibit indicates overfitting, where training loss keeps falling while validation loss rises. Compression would be the right consideration when deploying a trained model to constrained edge hardware.
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.