NCA-GENL Core Machine Learning and AI Knowledge Practice Question
A machine learning engineer is training a deep neural network for image classification. They notice that the training loss decreases steadily, but the validation loss starts to increase after a few epochs. Which technique is most directly aimed at addressing this issue?
⚠ Common exam trap
The trap here is thinking that a larger training set or more complex model is always better, but when validation loss rises, regularization like dropout is needed.
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
✓
Adding dropout layers
The described behavior—training loss decreasing while validation loss increases—is a classic sign of overfitting. Dropout is a regularization method that randomly drops units during training, which reduces the network's capacity to memorize noise and encourages more generalizable representations. Other options either do not address overfitting or would exacerbate the problem.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✗
Increasing the learning rate
Why it's wrong here
Increasing the learning rate would likely make training less stable and could worsen the divergence between training and validation loss. The problem described is overfitting, where the model memorizes training data but fails to generalize. A higher learning rate does not prevent overfitting and may even accelerate it by allowing the model to fit noise more quickly.
- ✗
Removing batch normalization
Why it's wrong here
Batch normalization helps stabilize and accelerate training, and removing it could harm convergence and generalization. It is not a cause of overfitting; rather, it often has a mild regularizing effect. Eliminating it would likely degrade performance without addressing the growing validation loss.
- ✗
Reducing the size of the training set
Why it's wrong here
Reducing the training set size would deprive the model of data and likely lead to underfitting, not solve overfitting. The issue is that the model is too complex relative to the data, but simply using less data does not regularize it. In fact, more data is often a remedy for overfitting, so this approach is counterproductive.
- ✓
Adding dropout layers
Why this is correct
Dropout randomly deactivates neurons during training, which forces the network to learn more robust features and reduces co-adaptation. This regularization technique directly combats overfitting, where validation loss rises while training loss falls. By preventing the model from relying too heavily on any single neuron, dropout improves generalization to unseen data.
About these practice questions
One of 367 original NCA-GENL 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 and reviewed by Johnson Ajibi, MSc IT Security
Senior Network & Security Engineer · founder of Courseiva
Last reviewed September 2026 · checked against the official NVIDIA exam blueprint
This NCA-GENL practice question is part of Courseiva's free NVIDIA 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 NCA-GENL exam.