NCA-GENL Core Machine Learning and AI Knowledge Practice Question
A machine learning engineer is training a deep neural network and notices that the training loss decreases but the validation loss starts to increase after several epochs. Which two techniques are most appropriate to mitigate this issue? (Choose two.)
⚠ Common exam trap
The trap here is thinking that more training or a larger model will help, when the issue is actually overfitting.
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
✓
Use early stopping based on validation loss.
When validation loss increases while training loss decreases, the model is overfitting. L2 regularization penalizes complexity, and early stopping halts training at the optimal point. Both techniques reduce overfitting and improve generalization. Other options either worsen overfitting or are unrelated to 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.
- ✗
Increase the number of training epochs.
Why it's wrong here
Increasing epochs would likely worsen the problem because the model is already overfitting. The validation loss is rising, indicating that further training will continue to fit noise in the training data. This would lead to even poorer generalization. The goal is to prevent overfitting, not to train longer.
- ✗
Increase the learning rate.
Why it's wrong here
Increasing the learning rate may cause the training to become unstable or diverge, and it does not address overfitting. A higher learning rate can even lead to worse generalization. Overfitting is about model complexity relative to data, not optimization speed, so adjusting the learning rate is not the right fix here.
- ✓
Use early stopping based on validation loss.
Why this is correct
Early stopping monitors validation loss and halts training when it starts to increase, preventing the model from overfitting further. It effectively selects the model at the point of best generalization. This is a simple and widely used technique to combat overfitting without altering the model architecture.
- ✓
Apply L2 regularization to the model's weights.
Why this is correct
L2 regularization adds a penalty for large weights, which discourages the model from fitting noise and encourages simpler, more generalizable solutions. This directly addresses overfitting, where the model memorizes training data. By constraining weight magnitudes, validation loss can be reduced and generalization improved.
- ✗
Add more layers to the neural network.
Why it's wrong here
Adding more layers increases model capacity, which would likely exacerbate overfitting. A more complex model can fit training data even more closely, including noise, leading to worse validation performance. The problem is too much capacity relative to the data, so increasing capacity is counterproductive.
About these practice questions
Courseiva writes every NCA-GENL question from scratch — 367 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 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.