Courseiva
Machine Learning and Deep LearninghardMultiple ChoiceObjective-mapped

AI0-001 Machine Learning and Deep Learning Practice Question

An AI developer observes that the training accuracy of a neural network is high, but the test accuracy is low. The model uses a ReLU activation function and Adam optimizer. Which approach is most likely to improve test accuracy?

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

Add L2 regularization to the loss function

L2 regularization adds a penalty on large weights, reducing overfitting and improving test accuracy.

Answer analysis

Option-by-option breakdown

For each option: why learners choose it and why it is or isn't the right answer here.

  • Increase the learning rate

    Why it's wrong here

    Higher learning rate may cause divergence or make overfitting worse.

  • Add L2 regularization to the loss function

    Why this is correct

    L2 regularization penalizes large weights, preventing overfitting.

  • Switch to a stochastic gradient descent optimizer

    Why it's wrong here

    SGD may not directly address overfitting; Adam is already effective.

  • Increase the number of epochs

    Why it's wrong here

    More training can exacerbate overfitting.

About these practice questions

This AI0-001 question is part of Courseiva's 754-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 →

How Courseiva writes practice questions · Editorial policy

Same concept, more angles

4 more ways this is tested on AI0-001

These questions test the same concept from different angles. Work through them to make sure you can recognise it however the exam phrases it.

Variation 1. Refer to the exhibit. A developer is using the above configuration for a multi-class classification task. The model performs well on training data but poorly on validation data. Which modification could help?

medium
  • A.Remove dropout
  • B.Increase the dropout rate
  • C.Add L2 regularization to the dense layers
  • D.Increase the learning rate

Why C: The model is overfitting, as indicated by good performance on training data but poor on validation data. Adding L2 regularization to the dense layers penalizes large weights, reducing model complexity and improving generalization. This directly addresses overfitting without disrupting the training dynamics.

Variation 2. Refer to the exhibit. The training log shows losses and accuracies over 5 epochs. What is the most likely problem?

easy
  • A.Data leakage
  • B.Overfitting
  • C.Underfitting
  • D.Vanishing gradient

Why B: 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.

Variation 3. Refer to the exhibit. What is the most likely issue and what action should be taken?

medium
  • A.Learning rate is too low; increase it
  • B.Underfitting; increase model complexity
  • C.Overfitting; apply early stopping around epoch 15
  • D.Data imbalance; use class weights

Why C: 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.

Variation 4. 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?

medium
  • A.Underfitting; increase model complexity
  • B.Vanishing gradients; use ReLU activation
  • C.Data leakage; shuffle data before splitting
  • D.Overfitting; apply dropout and early stopping

Why D: 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.

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.