AI0-001 Machine Learning and Deep Learning Practice Question
Exhibit
{
"train_loss": [0.8, 0.6, 0.5, 0.45, 0.42],
"val_loss": [0.9, 0.85, 0.88, 0.92, 0.95],
"train_acc": [0.7, 0.75, 0.8, 0.82, 0.83],
"val_acc": [0.65, 0.68, 0.67, 0.66, 0.65]
}Refer to the exhibit. The training log shows losses and accuracies over 5 epochs. What is the most likely problem?
⚠ Common exam trap
CompTIA often tests the distinction between overfitting and underfitting by showing a training log where training accuracy is high but validation accuracy is low, leading candidates to mistakenly think the model is 'learning well' when it is actually memorizing.
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 training log shows high training accuracy (e.g., 99%) but low validation accuracy (e.g., 60%) across epochs, with the validation loss increasing after an initial drop. This divergence indicates the model has memorized the training data rather than learning generalizable patterns, which is the hallmark of overfitting.
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 leakage
Why it's wrong here
Data leakage would produce unusually strong validation accuracy, not the diverging training and validation losses shown across epochs. It is tempting because leakage inflates validation metrics, but it is a dataset-construction flaw, whereas the exhibit reflects an optimisation/generalisation gap during training.
- ✓
Overfitting
Why this is correct
Overfitting fits because the log shows training loss still falling while validation loss rises after early epochs, meaning the model memorises training data rather than generalising. The widening gap between training and validation accuracy is the diagnostic constraint the stem's exhibit presents.
- ✗
Underfitting
Why it's wrong here
Underfitting would show high training loss that stays high, whereas the log presumably shows training loss falling while validation loss rises, indicating overfitting. It is tempting because both are generalisation failures, but underfitting is diagnosed from poor training-set performance, not diverging validation curves.
- ✗
Vanishing gradient
Why it's wrong here
Vanishing gradients manifest as training loss that barely decreases, often in deep networks with saturating activations, not as the widening train-validation gap shown. It is tempting because it also impairs learning, but the exhibit's pattern points to overfitting rather than stalled gradient flow.
About these practice questions
Courseiva writes every AI0-001 question from scratch — 962 in total, each with an explanation and a wrong-answer breakdown. None are copied from real exams or 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.