mediumMultiple Choice
AIF-C01 Practice Question: A machine learning engineer is training a neural…
A machine learning engineer is training a neural network and wants to prevent overfitting. Which technique should they apply?
⚠ Common exam trap
AWS often tests the distinction between optimization techniques (gradient descent, backpropagation) and regularization techniques (dropout), trapping candidates who confuse training algorithms with overfitting prevention methods.
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
✓
Dropout
Dropout is a regularization technique that randomly drops a fraction of neurons during training, which prevents the network from becoming overly reliant on any single neuron and reduces co-adaptation. This forces the model to learn more robust features, effectively reducing overfitting by acting as an ensemble of sub-networks.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✗
Gradient descent
Why it's wrong here
Gradient descent is the optimisation algorithm that updates weights to minimise loss; it does not itself constrain model capacity, so it cannot prevent overfitting. It is tempting because it is central to training, and regularisation techniques are applied within its update rule — but alone it only fits the training data.
- ✗
Backpropagation
Why it's wrong here
Backpropagation computes gradients of the loss with respect to weights; it is the training mechanism, not a regularisation technique, so it does not limit overfitting. It is tempting because it underpins neural network learning, and correct training is a prerequisite — but it addresses how weights are updated, not model generalisation.
- ✗
Boosting
Why it's wrong here
Boosting combines weak learners sequentially to reduce bias, which increases capacity and can worsen overfitting on a neural network. It is tempting because it is an ensemble method, and ensembles such as bagging do reduce variance — but boosting targets underfitting, not the overfitting described here.
- ✓
Dropout
Why this is correct
Dropout randomly deactivates a proportion of neurons during each training iteration, forcing the network to learn redundant representations rather than memorising training samples. This directly counteracts the overfitting the engineer wants to prevent, and at inference time all neurons are active with scaled weights.
Go deeper
Related to this question
About these practice questions
One of 862 original AIF-C01 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 AIF-C01 practice question is part of Courseiva's free Amazon Web Services 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 AIF-C01 exam.