AI0-001 AI Concepts and Techniques Practice Question
A team trains a neural network for image classification. During training, the loss decreases on the training set but increases on the validation set after a few epochs. What is the most likely cause?
⚠ Common exam trap
CompTIA AI often tests the distinction between overfitting and underfitting by presenting a scenario where training loss decreases but validation loss increases, which candidates may confuse with a learning rate issue or gradient problem.
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
Overfitting occurs when the model learns the training data too well, including noise and irrelevant patterns, causing it to memorize rather than generalize. This is evidenced by the loss decreasing on the training set while increasing on the validation set after a few epochs, as the model's performance on unseen data degrades.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✗
Vanishing gradients
Why it's wrong here
Vanishing gradients stall learning, so training loss would plateau rather than keep falling. The stem shows training loss still decreasing while validation loss rises, which is overfitting. Vanishing gradients would be the correct diagnosis where deep layers stop updating and accuracy stagnates early.
- ✗
Incorrect learning rate scheduling
Why it's wrong here
A misconfigured schedule alters convergence speed, but the described divergence between falling training loss and rising validation loss is the signature of overfitting. Scheduling errors would be the likely cause where both losses plateau or oscillate rather than separate.
- ✓
Overfitting
Why this is correct
Overfitting occurs when the model memorises training data, including noise, so training loss keeps falling while validation loss rises after a few epochs. The diverging curves in the stem are the classic signature: the network has learned patterns that do not generalise to unseen data.
- ✗
Underfitting
Why it's wrong here
Underfitting produces high loss on both training and validation sets because the model has not learnt the underlying pattern. Here training loss falls steadily, so the model fits the training data. Underfitting would be the correct diagnosis where both losses remain high and plateau.
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.